├── .gitignore ├── LICENSE.md ├── README.md ├── README_rkopt.md ├── README_rkopt_manual.md ├── cfg ├── baseline │ ├── r50-csp.yaml │ ├── x50-csp.yaml │ ├── yolor-csp-x.yaml │ ├── yolor-csp.yaml │ ├── yolor-d6.yaml │ ├── yolor-e6.yaml │ ├── yolor-p6.yaml │ ├── yolor-w6.yaml │ ├── yolov3-spp.yaml │ ├── yolov3.yaml │ └── yolov4-csp.yaml ├── deploy │ ├── yolov7-d6.yaml │ ├── yolov7-e6.yaml │ ├── yolov7-e6e.yaml │ ├── yolov7-tiny-silu.yaml │ ├── yolov7-tiny.yaml │ ├── yolov7-w6.yaml │ ├── yolov7.yaml │ └── yolov7x.yaml └── training │ ├── yolov7-d6.yaml │ ├── yolov7-e6.yaml │ ├── yolov7-e6e.yaml │ ├── yolov7-tiny-relu.yaml │ ├── yolov7-tiny.yaml │ ├── yolov7-w6.yaml │ ├── yolov7.yaml │ └── yolov7x.yaml ├── data ├── coco.yaml ├── hyp.scratch.custom.yaml ├── hyp.scratch.p5.yaml ├── hyp.scratch.p6.yaml └── hyp.scratch.tiny.yaml ├── deploy └── triton-inference-server │ ├── README.md │ ├── boundingbox.py │ ├── client.py │ ├── data │ ├── dog.jpg │ └── dog_result.jpg │ ├── labels.py │ ├── processing.py │ └── render.py ├── detect.py ├── export.py ├── figure ├── horses_prediction.jpg ├── mask.png ├── performance.png ├── pose.png ├── tennis.jpg ├── tennis_caption.png ├── tennis_panoptic.png └── tennis_semantic.jpg ├── hubconf.py ├── inference └── images │ ├── bus.jpg │ ├── horses.jpg │ ├── image1.jpg │ ├── image2.jpg │ ├── image3.jpg │ └── zidane.jpg ├── models ├── __init__.py ├── common.py ├── experimental.py └── yolo.py ├── paper └── yolov7.pdf ├── requirements.txt ├── scripts └── get_coco.sh ├── test.py ├── tools ├── YOLOv7-Dynamic-Batch-ONNXRUNTIME.ipynb ├── YOLOv7-Dynamic-Batch-TENSORRT.ipynb ├── YOLOv7CoreML.ipynb ├── YOLOv7onnx.ipynb ├── YOLOv7trt.ipynb ├── compare_YOLOv7_vs_YOLOv5m6.ipynb ├── compare_YOLOv7_vs_YOLOv5m6_half.ipynb ├── compare_YOLOv7_vs_YOLOv5s6.ipynb ├── compare_YOLOv7e6_vs_YOLOv5x6.ipynb ├── compare_YOLOv7e6_vs_YOLOv5x6_half.ipynb ├── instance.ipynb ├── keypoint.ipynb ├── reparameterization.ipynb └── visualization.ipynb ├── train.py ├── train_aux.py └── utils ├── __init__.py ├── activations.py ├── add_nms.py ├── autoanchor.py ├── aws ├── __init__.py ├── mime.sh ├── resume.py └── userdata.sh ├── datasets.py ├── general.py ├── google_app_engine ├── Dockerfile ├── additional_requirements.txt └── app.yaml ├── google_utils.py ├── loss.py ├── metrics.py ├── plots.py ├── torch_utils.py └── wandb_logging ├── __init__.py ├── log_dataset.py └── wandb_utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Repo-specific GitIgnore ---------------------------------------------------------------------------------------------- 2 | *.jpg 3 | *.jpeg 4 | *.png 5 | *.bmp 6 | *.tif 7 | *.tiff 8 | *.heic 9 | *.JPG 10 | *.JPEG 11 | *.PNG 12 | *.BMP 13 | *.TIF 14 | *.TIFF 15 | *.HEIC 16 | *.mp4 17 | *.mov 18 | *.MOV 19 | *.avi 20 | *.data 21 | *.json 22 | *.cfg 23 | !setup.cfg 24 | !cfg/yolov3*.cfg 25 | 26 | storage.googleapis.com 27 | runs/* 28 | data/* 29 | data/images/* 30 | !data/*.yaml 31 | !data/hyps 32 | !data/scripts 33 | !data/images 34 | !data/images/zidane.jpg 35 | !data/images/bus.jpg 36 | !data/*.sh 37 | 38 | results*.csv 39 | 40 | # Datasets ------------------------------------------------------------------------------------------------------------- 41 | coco/ 42 | coco128/ 43 | VOC/ 44 | 45 | coco2017labels-segments.zip 46 | test2017.zip 47 | train2017.zip 48 | val2017.zip 49 | 50 | # MATLAB GitIgnore ----------------------------------------------------------------------------------------------------- 51 | *.m~ 52 | *.mat 53 | !targets*.mat 54 | 55 | # Neural Network weights ----------------------------------------------------------------------------------------------- 56 | *.weights 57 | *.pt 58 | *.pb 59 | *.onnx 60 | *.engine 61 | *.mlmodel 62 | *.torchscript 63 | *.tflite 64 | *.h5 65 | *_saved_model/ 66 | *_web_model/ 67 | *_openvino_model/ 68 | darknet53.conv.74 69 | yolov3-tiny.conv.15 70 | *.ptl 71 | *.trt 72 | 73 | # GitHub Python GitIgnore ---------------------------------------------------------------------------------------------- 74 | # Byte-compiled / optimized / DLL files 75 | __pycache__/ 76 | *.py[cod] 77 | *$py.class 78 | 79 | # C extensions 80 | *.so 81 | 82 | # Distribution / packaging 83 | .Python 84 | env/ 85 | build/ 86 | develop-eggs/ 87 | dist/ 88 | downloads/ 89 | eggs/ 90 | .eggs/ 91 | lib/ 92 | lib64/ 93 | parts/ 94 | sdist/ 95 | var/ 96 | wheels/ 97 | *.egg-info/ 98 | /wandb/ 99 | .installed.cfg 100 | *.egg 101 | 102 | 103 | # PyInstaller 104 | # Usually these files are written by a python script from a template 105 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 106 | *.manifest 107 | *.spec 108 | 109 | # Installer logs 110 | pip-log.txt 111 | pip-delete-this-directory.txt 112 | 113 | # Unit test / coverage reports 114 | htmlcov/ 115 | .tox/ 116 | .coverage 117 | .coverage.* 118 | .cache 119 | nosetests.xml 120 | coverage.xml 121 | *.cover 122 | .hypothesis/ 123 | 124 | # Translations 125 | *.mo 126 | *.pot 127 | 128 | # Django stuff: 129 | *.log 130 | local_settings.py 131 | 132 | # Flask stuff: 133 | instance/ 134 | .webassets-cache 135 | 136 | # Scrapy stuff: 137 | .scrapy 138 | 139 | # Sphinx documentation 140 | docs/_build/ 141 | 142 | # PyBuilder 143 | target/ 144 | 145 | # Jupyter Notebook 146 | .ipynb_checkpoints 147 | 148 | # pyenv 149 | .python-version 150 | 151 | # celery beat schedule file 152 | celerybeat-schedule 153 | 154 | # SageMath parsed files 155 | *.sage.py 156 | 157 | # dotenv 158 | .env 159 | 160 | # virtualenv 161 | .venv* 162 | venv*/ 163 | ENV*/ 164 | 165 | # Spyder project settings 166 | .spyderproject 167 | .spyproject 168 | 169 | # Rope project settings 170 | .ropeproject 171 | 172 | # mkdocs documentation 173 | /site 174 | 175 | # mypy 176 | .mypy_cache/ 177 | 178 | 179 | # https://github.com/github/gitignore/blob/master/Global/macOS.gitignore ----------------------------------------------- 180 | 181 | # General 182 | .DS_Store 183 | .AppleDouble 184 | .LSOverride 185 | 186 | # Icon must end with two \r 187 | Icon 188 | Icon? 189 | 190 | # Thumbnails 191 | ._* 192 | 193 | # Files that might appear in the root of a volume 194 | .DocumentRevisions-V100 195 | .fseventsd 196 | .Spotlight-V100 197 | .TemporaryItems 198 | .Trashes 199 | .VolumeIcon.icns 200 | .com.apple.timemachine.donotpresent 201 | 202 | # Directories potentially created on remote AFP share 203 | .AppleDB 204 | .AppleDesktop 205 | Network Trash Folder 206 | Temporary Items 207 | .apdisk 208 | 209 | 210 | # https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore 211 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 212 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 213 | 214 | # User-specific stuff: 215 | .idea/* 216 | .idea/**/workspace.xml 217 | .idea/**/tasks.xml 218 | .idea/dictionaries 219 | .html # Bokeh Plots 220 | .pg # TensorFlow Frozen Graphs 221 | .avi # videos 222 | 223 | # Sensitive or high-churn files: 224 | .idea/**/dataSources/ 225 | .idea/**/dataSources.ids 226 | .idea/**/dataSources.local.xml 227 | .idea/**/sqlDataSources.xml 228 | .idea/**/dynamic.xml 229 | .idea/**/uiDesigner.xml 230 | 231 | # Gradle: 232 | .idea/**/gradle.xml 233 | .idea/**/libraries 234 | 235 | # CMake 236 | cmake-build-debug/ 237 | cmake-build-release/ 238 | 239 | # Mongo Explorer plugin: 240 | .idea/**/mongoSettings.xml 241 | 242 | ## File-based project format: 243 | *.iws 244 | 245 | ## Plugin-specific files: 246 | 247 | # IntelliJ 248 | out/ 249 | 250 | # mpeltonen/sbt-idea plugin 251 | .idea_modules/ 252 | 253 | # JIRA plugin 254 | atlassian-ide-plugin.xml 255 | 256 | # Cursive Clojure plugin 257 | .idea/replstate.xml 258 | 259 | # Crashlytics plugin (for Android Studio and IntelliJ) 260 | com_crashlytics_export_strings.xml 261 | crashlytics.properties 262 | crashlytics-build.properties 263 | fabric.properties 264 | -------------------------------------------------------------------------------- /README_rkopt.md: -------------------------------------------------------------------------------- 1 | # YOLOv7 - RKNN optimize 2 | 3 | 4 | ## Source 5 | 6 | Base on https://github.com/WongKinYiu/yolov7 with commit id as 44d8ab41780e24eba563b6794371f29db0902271 7 | 8 | 9 | 10 | ## What different 11 | 12 | With inference result values unchanged, the following optimizations were applied: 13 | 14 | - Optimize SPP block, getting better performance with same result 15 | - Change output node, remove post_process from the model. (post process block in model is unfriendly for quantization) 16 | 17 | 18 | 19 | ## How to use 20 | 21 | ``` 22 | python export.py --rknpu --weight yolov7-tiny.pt 23 | ``` 24 | 25 | - Replace 'yolov7-tiny.pt' with your model path 26 | - A file name "RK_anchors.txt" would be generated and it could be use during doing post_process in the outside. 27 | - **NOTICE: Please call with --rknpu param, do not changing the default rknpu value in export.py.** 28 | 29 | 30 | 31 | ## Deploy demo 32 | 33 | Please refer https://github.com/airockchip/rknn_model_zoo 34 | -------------------------------------------------------------------------------- /README_rkopt_manual.md: -------------------------------------------------------------------------------- 1 | # YOLOv7 - RKNN optimize 2 | 3 | 4 | ## Source 5 | 6 | Base on https://github.com/WongKinYiu/yolov7 with commit id as 44d8ab41780e24eba563b6794371f29db0902271 7 | 8 | 9 | 10 | ## What different 11 | 12 | Inference result unchanged: 13 | 14 | - Optimize SPP block, getting better performance with same result 15 | - Change output node, remove post_process from the model. (post process is unfriendly in quantization) 16 | 17 | 18 | 19 | ## How to use 20 | 21 | ``` 22 | python export.py --rknpu {rk_platform} --weight yolov7-tiny.pt 23 | ``` 24 | 25 | - rk_platform support rk1808, rv1109, rv1126, rk3399pro, rk3566, rk3562, rk3568, rk3588, rv1103, rv1106. (Actually the exported models are the same in spite of the exact platform ) 26 | 27 | - Replace 'yolov7-tiny.pt' with your model path 28 | - A file name "RK_anchors.txt" would be generated and it could be use during doing post_process in the outside. 29 | - **NOTICE: Please call with --rknpu param, do not changing the default rknpu value in export.py.** 30 | 31 | -------------------------------------------------------------------------------- /cfg/baseline/r50-csp.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # CSP-ResNet backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Stem, [128]], # 0-P1/2 16 | [-1, 3, ResCSPC, [128]], 17 | [-1, 1, Conv, [256, 3, 2]], # 2-P3/8 18 | [-1, 4, ResCSPC, [256]], 19 | [-1, 1, Conv, [512, 3, 2]], # 4-P3/8 20 | [-1, 6, ResCSPC, [512]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 6-P3/8 22 | [-1, 3, ResCSPC, [1024]], # 7 23 | ] 24 | 25 | # CSP-Res-PAN head 26 | head: 27 | [[-1, 1, SPPCSPC, [512]], # 8 28 | [-1, 1, Conv, [256, 1, 1]], 29 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 30 | [5, 1, Conv, [256, 1, 1]], # route backbone P4 31 | [[-1, -2], 1, Concat, [1]], 32 | [-1, 2, ResCSPB, [256]], # 13 33 | [-1, 1, Conv, [128, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [3, 1, Conv, [128, 1, 1]], # route backbone P3 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 2, ResCSPB, [128]], # 18 38 | [-1, 1, Conv, [256, 3, 1]], 39 | [-2, 1, Conv, [256, 3, 2]], 40 | [[-1, 13], 1, Concat, [1]], # cat 41 | [-1, 2, ResCSPB, [256]], # 22 42 | [-1, 1, Conv, [512, 3, 1]], 43 | [-2, 1, Conv, [512, 3, 2]], 44 | [[-1, 8], 1, Concat, [1]], # cat 45 | [-1, 2, ResCSPB, [512]], # 26 46 | [-1, 1, Conv, [1024, 3, 1]], 47 | 48 | [[19,23,27], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 49 | ] 50 | -------------------------------------------------------------------------------- /cfg/baseline/x50-csp.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # CSP-ResNeXt backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Stem, [128]], # 0-P1/2 16 | [-1, 3, ResXCSPC, [128]], 17 | [-1, 1, Conv, [256, 3, 2]], # 2-P3/8 18 | [-1, 4, ResXCSPC, [256]], 19 | [-1, 1, Conv, [512, 3, 2]], # 4-P3/8 20 | [-1, 6, ResXCSPC, [512]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 6-P3/8 22 | [-1, 3, ResXCSPC, [1024]], # 7 23 | ] 24 | 25 | # CSP-ResX-PAN head 26 | head: 27 | [[-1, 1, SPPCSPC, [512]], # 8 28 | [-1, 1, Conv, [256, 1, 1]], 29 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 30 | [5, 1, Conv, [256, 1, 1]], # route backbone P4 31 | [[-1, -2], 1, Concat, [1]], 32 | [-1, 2, ResXCSPB, [256]], # 13 33 | [-1, 1, Conv, [128, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [3, 1, Conv, [128, 1, 1]], # route backbone P3 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 2, ResXCSPB, [128]], # 18 38 | [-1, 1, Conv, [256, 3, 1]], 39 | [-2, 1, Conv, [256, 3, 2]], 40 | [[-1, 13], 1, Concat, [1]], # cat 41 | [-1, 2, ResXCSPB, [256]], # 22 42 | [-1, 1, Conv, [512, 3, 1]], 43 | [-2, 1, Conv, [512, 3, 2]], 44 | [[-1, 8], 1, Concat, [1]], # cat 45 | [-1, 2, ResXCSPB, [512]], # 26 46 | [-1, 1, Conv, [1024, 3, 1]], 47 | 48 | [[19,23,27], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 49 | ] 50 | -------------------------------------------------------------------------------- /cfg/baseline/yolor-csp-x.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.33 # model depth multiple 4 | width_multiple: 1.25 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # CSP-Darknet backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, BottleneckCSPC, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, BottleneckCSPC, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, BottleneckCSPC, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, BottleneckCSPC, [1024]], # 10 26 | ] 27 | 28 | # CSP-Dark-PAN head 29 | head: 30 | [[-1, 1, SPPCSPC, [512]], # 11 31 | [-1, 1, Conv, [256, 1, 1]], 32 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 33 | [8, 1, Conv, [256, 1, 1]], # route backbone P4 34 | [[-1, -2], 1, Concat, [1]], 35 | [-1, 2, BottleneckCSPB, [256]], # 16 36 | [-1, 1, Conv, [128, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [6, 1, Conv, [128, 1, 1]], # route backbone P3 39 | [[-1, -2], 1, Concat, [1]], 40 | [-1, 2, BottleneckCSPB, [128]], # 21 41 | [-1, 1, Conv, [256, 3, 1]], 42 | [-2, 1, Conv, [256, 3, 2]], 43 | [[-1, 16], 1, Concat, [1]], # cat 44 | [-1, 2, BottleneckCSPB, [256]], # 25 45 | [-1, 1, Conv, [512, 3, 1]], 46 | [-2, 1, Conv, [512, 3, 2]], 47 | [[-1, 11], 1, Concat, [1]], # cat 48 | [-1, 2, BottleneckCSPB, [512]], # 29 49 | [-1, 1, Conv, [1024, 3, 1]], 50 | 51 | [[22,26,30], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 52 | ] 53 | -------------------------------------------------------------------------------- /cfg/baseline/yolor-csp.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # CSP-Darknet backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, BottleneckCSPC, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, BottleneckCSPC, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, BottleneckCSPC, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, BottleneckCSPC, [1024]], # 10 26 | ] 27 | 28 | # CSP-Dark-PAN head 29 | head: 30 | [[-1, 1, SPPCSPC, [512]], # 11 31 | [-1, 1, Conv, [256, 1, 1]], 32 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 33 | [8, 1, Conv, [256, 1, 1]], # route backbone P4 34 | [[-1, -2], 1, Concat, [1]], 35 | [-1, 2, BottleneckCSPB, [256]], # 16 36 | [-1, 1, Conv, [128, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [6, 1, Conv, [128, 1, 1]], # route backbone P3 39 | [[-1, -2], 1, Concat, [1]], 40 | [-1, 2, BottleneckCSPB, [128]], # 21 41 | [-1, 1, Conv, [256, 3, 1]], 42 | [-2, 1, Conv, [256, 3, 2]], 43 | [[-1, 16], 1, Concat, [1]], # cat 44 | [-1, 2, BottleneckCSPB, [256]], # 25 45 | [-1, 1, Conv, [512, 3, 1]], 46 | [-2, 1, Conv, [512, 3, 2]], 47 | [[-1, 11], 1, Concat, [1]], # cat 48 | [-1, 2, BottleneckCSPB, [512]], # 29 49 | [-1, 1, Conv, [1024, 3, 1]], 50 | 51 | [[22,26,30], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 52 | ] 53 | -------------------------------------------------------------------------------- /cfg/baseline/yolor-d6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # expand model depth 4 | width_multiple: 1.25 # expand layer channels 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # CSP-Darknet backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | [-1, 1, DownC, [128]], # 2-P2/4 19 | [-1, 3, BottleneckCSPA, [128]], 20 | [-1, 1, DownC, [256]], # 4-P3/8 21 | [-1, 15, BottleneckCSPA, [256]], 22 | [-1, 1, DownC, [512]], # 6-P4/16 23 | [-1, 15, BottleneckCSPA, [512]], 24 | [-1, 1, DownC, [768]], # 8-P5/32 25 | [-1, 7, BottleneckCSPA, [768]], 26 | [-1, 1, DownC, [1024]], # 10-P6/64 27 | [-1, 7, BottleneckCSPA, [1024]], # 11 28 | ] 29 | 30 | # CSP-Dark-PAN head 31 | head: 32 | [[-1, 1, SPPCSPC, [512]], # 12 33 | [-1, 1, Conv, [384, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [-6, 1, Conv, [384, 1, 1]], # route backbone P5 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 3, BottleneckCSPB, [384]], # 17 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [-13, 1, Conv, [256, 1, 1]], # route backbone P4 41 | [[-1, -2], 1, Concat, [1]], 42 | [-1, 3, BottleneckCSPB, [256]], # 22 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 45 | [-20, 1, Conv, [128, 1, 1]], # route backbone P3 46 | [[-1, -2], 1, Concat, [1]], 47 | [-1, 3, BottleneckCSPB, [128]], # 27 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-2, 1, DownC, [256]], 50 | [[-1, 22], 1, Concat, [1]], # cat 51 | [-1, 3, BottleneckCSPB, [256]], # 31 52 | [-1, 1, Conv, [512, 3, 1]], 53 | [-2, 1, DownC, [384]], 54 | [[-1, 17], 1, Concat, [1]], # cat 55 | [-1, 3, BottleneckCSPB, [384]], # 35 56 | [-1, 1, Conv, [768, 3, 1]], 57 | [-2, 1, DownC, [512]], 58 | [[-1, 12], 1, Concat, [1]], # cat 59 | [-1, 3, BottleneckCSPB, [512]], # 39 60 | [-1, 1, Conv, [1024, 3, 1]], 61 | 62 | [[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 63 | ] -------------------------------------------------------------------------------- /cfg/baseline/yolor-e6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # expand model depth 4 | width_multiple: 1.25 # expand layer channels 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # CSP-Darknet backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | [-1, 1, DownC, [128]], # 2-P2/4 19 | [-1, 3, BottleneckCSPA, [128]], 20 | [-1, 1, DownC, [256]], # 4-P3/8 21 | [-1, 7, BottleneckCSPA, [256]], 22 | [-1, 1, DownC, [512]], # 6-P4/16 23 | [-1, 7, BottleneckCSPA, [512]], 24 | [-1, 1, DownC, [768]], # 8-P5/32 25 | [-1, 3, BottleneckCSPA, [768]], 26 | [-1, 1, DownC, [1024]], # 10-P6/64 27 | [-1, 3, BottleneckCSPA, [1024]], # 11 28 | ] 29 | 30 | # CSP-Dark-PAN head 31 | head: 32 | [[-1, 1, SPPCSPC, [512]], # 12 33 | [-1, 1, Conv, [384, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [-6, 1, Conv, [384, 1, 1]], # route backbone P5 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 3, BottleneckCSPB, [384]], # 17 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [-13, 1, Conv, [256, 1, 1]], # route backbone P4 41 | [[-1, -2], 1, Concat, [1]], 42 | [-1, 3, BottleneckCSPB, [256]], # 22 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 45 | [-20, 1, Conv, [128, 1, 1]], # route backbone P3 46 | [[-1, -2], 1, Concat, [1]], 47 | [-1, 3, BottleneckCSPB, [128]], # 27 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-2, 1, DownC, [256]], 50 | [[-1, 22], 1, Concat, [1]], # cat 51 | [-1, 3, BottleneckCSPB, [256]], # 31 52 | [-1, 1, Conv, [512, 3, 1]], 53 | [-2, 1, DownC, [384]], 54 | [[-1, 17], 1, Concat, [1]], # cat 55 | [-1, 3, BottleneckCSPB, [384]], # 35 56 | [-1, 1, Conv, [768, 3, 1]], 57 | [-2, 1, DownC, [512]], 58 | [[-1, 12], 1, Concat, [1]], # cat 59 | [-1, 3, BottleneckCSPB, [512]], # 39 60 | [-1, 1, Conv, [1024, 3, 1]], 61 | 62 | [[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 63 | ] -------------------------------------------------------------------------------- /cfg/baseline/yolor-p6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # expand model depth 4 | width_multiple: 1.0 # expand layer channels 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # CSP-Darknet backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | [-1, 1, Conv, [128, 3, 2]], # 2-P2/4 19 | [-1, 3, BottleneckCSPA, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 4-P3/8 21 | [-1, 7, BottleneckCSPA, [256]], 22 | [-1, 1, Conv, [384, 3, 2]], # 6-P4/16 23 | [-1, 7, BottleneckCSPA, [384]], 24 | [-1, 1, Conv, [512, 3, 2]], # 8-P5/32 25 | [-1, 3, BottleneckCSPA, [512]], 26 | [-1, 1, Conv, [640, 3, 2]], # 10-P6/64 27 | [-1, 3, BottleneckCSPA, [640]], # 11 28 | ] 29 | 30 | # CSP-Dark-PAN head 31 | head: 32 | [[-1, 1, SPPCSPC, [320]], # 12 33 | [-1, 1, Conv, [256, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [-6, 1, Conv, [256, 1, 1]], # route backbone P5 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 3, BottleneckCSPB, [256]], # 17 38 | [-1, 1, Conv, [192, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [-13, 1, Conv, [192, 1, 1]], # route backbone P4 41 | [[-1, -2], 1, Concat, [1]], 42 | [-1, 3, BottleneckCSPB, [192]], # 22 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 45 | [-20, 1, Conv, [128, 1, 1]], # route backbone P3 46 | [[-1, -2], 1, Concat, [1]], 47 | [-1, 3, BottleneckCSPB, [128]], # 27 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-2, 1, Conv, [192, 3, 2]], 50 | [[-1, 22], 1, Concat, [1]], # cat 51 | [-1, 3, BottleneckCSPB, [192]], # 31 52 | [-1, 1, Conv, [384, 3, 1]], 53 | [-2, 1, Conv, [256, 3, 2]], 54 | [[-1, 17], 1, Concat, [1]], # cat 55 | [-1, 3, BottleneckCSPB, [256]], # 35 56 | [-1, 1, Conv, [512, 3, 1]], 57 | [-2, 1, Conv, [320, 3, 2]], 58 | [[-1, 12], 1, Concat, [1]], # cat 59 | [-1, 3, BottleneckCSPB, [320]], # 39 60 | [-1, 1, Conv, [640, 3, 1]], 61 | 62 | [[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 63 | ] -------------------------------------------------------------------------------- /cfg/baseline/yolor-w6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # expand model depth 4 | width_multiple: 1.0 # expand layer channels 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # CSP-Darknet backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | [-1, 1, Conv, [128, 3, 2]], # 2-P2/4 19 | [-1, 3, BottleneckCSPA, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 4-P3/8 21 | [-1, 7, BottleneckCSPA, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 6-P4/16 23 | [-1, 7, BottleneckCSPA, [512]], 24 | [-1, 1, Conv, [768, 3, 2]], # 8-P5/32 25 | [-1, 3, BottleneckCSPA, [768]], 26 | [-1, 1, Conv, [1024, 3, 2]], # 10-P6/64 27 | [-1, 3, BottleneckCSPA, [1024]], # 11 28 | ] 29 | 30 | # CSP-Dark-PAN head 31 | head: 32 | [[-1, 1, SPPCSPC, [512]], # 12 33 | [-1, 1, Conv, [384, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [-6, 1, Conv, [384, 1, 1]], # route backbone P5 36 | [[-1, -2], 1, Concat, [1]], 37 | [-1, 3, BottleneckCSPB, [384]], # 17 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [-13, 1, Conv, [256, 1, 1]], # route backbone P4 41 | [[-1, -2], 1, Concat, [1]], 42 | [-1, 3, BottleneckCSPB, [256]], # 22 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 45 | [-20, 1, Conv, [128, 1, 1]], # route backbone P3 46 | [[-1, -2], 1, Concat, [1]], 47 | [-1, 3, BottleneckCSPB, [128]], # 27 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-2, 1, Conv, [256, 3, 2]], 50 | [[-1, 22], 1, Concat, [1]], # cat 51 | [-1, 3, BottleneckCSPB, [256]], # 31 52 | [-1, 1, Conv, [512, 3, 1]], 53 | [-2, 1, Conv, [384, 3, 2]], 54 | [[-1, 17], 1, Concat, [1]], # cat 55 | [-1, 3, BottleneckCSPB, [384]], # 35 56 | [-1, 1, Conv, [768, 3, 1]], 57 | [-2, 1, Conv, [512, 3, 2]], 58 | [[-1, 12], 1, Concat, [1]], # cat 59 | [-1, 3, BottleneckCSPB, [512]], # 39 60 | [-1, 1, Conv, [1024, 3, 1]], 61 | 62 | [[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 63 | ] -------------------------------------------------------------------------------- /cfg/baseline/yolov3-spp.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # darknet53 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, Bottleneck, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, Bottleneck, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, Bottleneck, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, Bottleneck, [1024]], # 10 26 | ] 27 | 28 | # YOLOv3-SPP head 29 | head: 30 | [[-1, 1, Bottleneck, [1024, False]], 31 | [-1, 1, SPP, [512, [5, 9, 13]]], 32 | [-1, 1, Conv, [1024, 3, 1]], 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 35 | 36 | [-2, 1, Conv, [256, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 39 | [-1, 1, Bottleneck, [512, False]], 40 | [-1, 1, Bottleneck, [512, False]], 41 | [-1, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 43 | 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 46 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 47 | [-1, 1, Bottleneck, [256, False]], 48 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 49 | 50 | [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 51 | ] 52 | -------------------------------------------------------------------------------- /cfg/baseline/yolov3.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # darknet53 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, Bottleneck, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, Bottleneck, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, Bottleneck, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, Bottleneck, [1024]], # 10 26 | ] 27 | 28 | # YOLOv3 head 29 | head: 30 | [[-1, 1, Bottleneck, [1024, False]], 31 | [-1, 1, Conv, [512, [1, 1]]], 32 | [-1, 1, Conv, [1024, 3, 1]], 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 35 | 36 | [-2, 1, Conv, [256, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 39 | [-1, 1, Bottleneck, [512, False]], 40 | [-1, 1, Bottleneck, [512, False]], 41 | [-1, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 43 | 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 46 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 47 | [-1, 1, Bottleneck, [256, False]], 48 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 49 | 50 | [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 51 | ] 52 | -------------------------------------------------------------------------------- /cfg/baseline/yolov4-csp.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # CSP-Darknet backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, BottleneckCSPC, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, BottleneckCSPC, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, BottleneckCSPC, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, BottleneckCSPC, [1024]], # 10 26 | ] 27 | 28 | # CSP-Dark-PAN head 29 | head: 30 | [[-1, 1, SPPCSPC, [512]], # 11 31 | [-1, 1, Conv, [256, 1, 1]], 32 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 33 | [8, 1, Conv, [256, 1, 1]], # route backbone P4 34 | [[-1, -2], 1, Concat, [1]], 35 | [-1, 2, BottleneckCSPB, [256]], # 16 36 | [-1, 1, Conv, [128, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [6, 1, Conv, [128, 1, 1]], # route backbone P3 39 | [[-1, -2], 1, Concat, [1]], 40 | [-1, 2, BottleneckCSPB, [128]], # 21 41 | [-1, 1, Conv, [256, 3, 1]], 42 | [-2, 1, Conv, [256, 3, 2]], 43 | [[-1, 16], 1, Concat, [1]], # cat 44 | [-1, 2, BottleneckCSPB, [256]], # 25 45 | [-1, 1, Conv, [512, 3, 1]], 46 | [-2, 1, Conv, [512, 3, 2]], 47 | [[-1, 11], 1, Concat, [1]], # cat 48 | [-1, 2, BottleneckCSPB, [512]], # 29 49 | [-1, 1, Conv, [1024, 3, 1]], 50 | 51 | [[22,26,30], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 52 | ] 53 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-d6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7-d6 backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [96, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [192]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [-1, 1, Conv, [64, 3, 1]], 29 | [-1, 1, Conv, [64, 3, 1]], 30 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 31 | [-1, 1, Conv, [192, 1, 1]], # 14 32 | 33 | [-1, 1, DownC, [384]], # 15-P3/8 34 | [-1, 1, Conv, [128, 1, 1]], 35 | [-2, 1, Conv, [128, 1, 1]], 36 | [-1, 1, Conv, [128, 3, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [-1, 1, Conv, [128, 3, 1]], 42 | [-1, 1, Conv, [128, 3, 1]], 43 | [-1, 1, Conv, [128, 3, 1]], 44 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 45 | [-1, 1, Conv, [384, 1, 1]], # 27 46 | 47 | [-1, 1, DownC, [768]], # 28-P4/16 48 | [-1, 1, Conv, [256, 1, 1]], 49 | [-2, 1, Conv, [256, 1, 1]], 50 | [-1, 1, Conv, [256, 3, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [-1, 1, Conv, [256, 3, 1]], 53 | [-1, 1, Conv, [256, 3, 1]], 54 | [-1, 1, Conv, [256, 3, 1]], 55 | [-1, 1, Conv, [256, 3, 1]], 56 | [-1, 1, Conv, [256, 3, 1]], 57 | [-1, 1, Conv, [256, 3, 1]], 58 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 59 | [-1, 1, Conv, [768, 1, 1]], # 40 60 | 61 | [-1, 1, DownC, [1152]], # 41-P5/32 62 | [-1, 1, Conv, [384, 1, 1]], 63 | [-2, 1, Conv, [384, 1, 1]], 64 | [-1, 1, Conv, [384, 3, 1]], 65 | [-1, 1, Conv, [384, 3, 1]], 66 | [-1, 1, Conv, [384, 3, 1]], 67 | [-1, 1, Conv, [384, 3, 1]], 68 | [-1, 1, Conv, [384, 3, 1]], 69 | [-1, 1, Conv, [384, 3, 1]], 70 | [-1, 1, Conv, [384, 3, 1]], 71 | [-1, 1, Conv, [384, 3, 1]], 72 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 73 | [-1, 1, Conv, [1152, 1, 1]], # 53 74 | 75 | [-1, 1, DownC, [1536]], # 54-P6/64 76 | [-1, 1, Conv, [512, 1, 1]], 77 | [-2, 1, Conv, [512, 1, 1]], 78 | [-1, 1, Conv, [512, 3, 1]], 79 | [-1, 1, Conv, [512, 3, 1]], 80 | [-1, 1, Conv, [512, 3, 1]], 81 | [-1, 1, Conv, [512, 3, 1]], 82 | [-1, 1, Conv, [512, 3, 1]], 83 | [-1, 1, Conv, [512, 3, 1]], 84 | [-1, 1, Conv, [512, 3, 1]], 85 | [-1, 1, Conv, [512, 3, 1]], 86 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 87 | [-1, 1, Conv, [1536, 1, 1]], # 66 88 | ] 89 | 90 | # yolov7-d6 head 91 | head: 92 | [[-1, 1, SPPCSPC, [768]], # 67 93 | 94 | [-1, 1, Conv, [576, 1, 1]], 95 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 96 | [53, 1, Conv, [576, 1, 1]], # route backbone P5 97 | [[-1, -2], 1, Concat, [1]], 98 | 99 | [-1, 1, Conv, [384, 1, 1]], 100 | [-2, 1, Conv, [384, 1, 1]], 101 | [-1, 1, Conv, [192, 3, 1]], 102 | [-1, 1, Conv, [192, 3, 1]], 103 | [-1, 1, Conv, [192, 3, 1]], 104 | [-1, 1, Conv, [192, 3, 1]], 105 | [-1, 1, Conv, [192, 3, 1]], 106 | [-1, 1, Conv, [192, 3, 1]], 107 | [-1, 1, Conv, [192, 3, 1]], 108 | [-1, 1, Conv, [192, 3, 1]], 109 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 110 | [-1, 1, Conv, [576, 1, 1]], # 83 111 | 112 | [-1, 1, Conv, [384, 1, 1]], 113 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 114 | [40, 1, Conv, [384, 1, 1]], # route backbone P4 115 | [[-1, -2], 1, Concat, [1]], 116 | 117 | [-1, 1, Conv, [256, 1, 1]], 118 | [-2, 1, Conv, [256, 1, 1]], 119 | [-1, 1, Conv, [128, 3, 1]], 120 | [-1, 1, Conv, [128, 3, 1]], 121 | [-1, 1, Conv, [128, 3, 1]], 122 | [-1, 1, Conv, [128, 3, 1]], 123 | [-1, 1, Conv, [128, 3, 1]], 124 | [-1, 1, Conv, [128, 3, 1]], 125 | [-1, 1, Conv, [128, 3, 1]], 126 | [-1, 1, Conv, [128, 3, 1]], 127 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 128 | [-1, 1, Conv, [384, 1, 1]], # 99 129 | 130 | [-1, 1, Conv, [192, 1, 1]], 131 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 132 | [27, 1, Conv, [192, 1, 1]], # route backbone P3 133 | [[-1, -2], 1, Concat, [1]], 134 | 135 | [-1, 1, Conv, [128, 1, 1]], 136 | [-2, 1, Conv, [128, 1, 1]], 137 | [-1, 1, Conv, [64, 3, 1]], 138 | [-1, 1, Conv, [64, 3, 1]], 139 | [-1, 1, Conv, [64, 3, 1]], 140 | [-1, 1, Conv, [64, 3, 1]], 141 | [-1, 1, Conv, [64, 3, 1]], 142 | [-1, 1, Conv, [64, 3, 1]], 143 | [-1, 1, Conv, [64, 3, 1]], 144 | [-1, 1, Conv, [64, 3, 1]], 145 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 146 | [-1, 1, Conv, [192, 1, 1]], # 115 147 | 148 | [-1, 1, DownC, [384]], 149 | [[-1, 99], 1, Concat, [1]], 150 | 151 | [-1, 1, Conv, [256, 1, 1]], 152 | [-2, 1, Conv, [256, 1, 1]], 153 | [-1, 1, Conv, [128, 3, 1]], 154 | [-1, 1, Conv, [128, 3, 1]], 155 | [-1, 1, Conv, [128, 3, 1]], 156 | [-1, 1, Conv, [128, 3, 1]], 157 | [-1, 1, Conv, [128, 3, 1]], 158 | [-1, 1, Conv, [128, 3, 1]], 159 | [-1, 1, Conv, [128, 3, 1]], 160 | [-1, 1, Conv, [128, 3, 1]], 161 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 162 | [-1, 1, Conv, [384, 1, 1]], # 129 163 | 164 | [-1, 1, DownC, [576]], 165 | [[-1, 83], 1, Concat, [1]], 166 | 167 | [-1, 1, Conv, [384, 1, 1]], 168 | [-2, 1, Conv, [384, 1, 1]], 169 | [-1, 1, Conv, [192, 3, 1]], 170 | [-1, 1, Conv, [192, 3, 1]], 171 | [-1, 1, Conv, [192, 3, 1]], 172 | [-1, 1, Conv, [192, 3, 1]], 173 | [-1, 1, Conv, [192, 3, 1]], 174 | [-1, 1, Conv, [192, 3, 1]], 175 | [-1, 1, Conv, [192, 3, 1]], 176 | [-1, 1, Conv, [192, 3, 1]], 177 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 178 | [-1, 1, Conv, [576, 1, 1]], # 143 179 | 180 | [-1, 1, DownC, [768]], 181 | [[-1, 67], 1, Concat, [1]], 182 | 183 | [-1, 1, Conv, [512, 1, 1]], 184 | [-2, 1, Conv, [512, 1, 1]], 185 | [-1, 1, Conv, [256, 3, 1]], 186 | [-1, 1, Conv, [256, 3, 1]], 187 | [-1, 1, Conv, [256, 3, 1]], 188 | [-1, 1, Conv, [256, 3, 1]], 189 | [-1, 1, Conv, [256, 3, 1]], 190 | [-1, 1, Conv, [256, 3, 1]], 191 | [-1, 1, Conv, [256, 3, 1]], 192 | [-1, 1, Conv, [256, 3, 1]], 193 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 194 | [-1, 1, Conv, [768, 1, 1]], # 157 195 | 196 | [115, 1, Conv, [384, 3, 1]], 197 | [129, 1, Conv, [768, 3, 1]], 198 | [143, 1, Conv, [1152, 3, 1]], 199 | [157, 1, Conv, [1536, 3, 1]], 200 | 201 | [[158,159,160,161], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 202 | ] 203 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-e6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7-e6 backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [80, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [160]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 29 | [-1, 1, Conv, [160, 1, 1]], # 12 30 | 31 | [-1, 1, DownC, [320]], # 13-P3/8 32 | [-1, 1, Conv, [128, 1, 1]], 33 | [-2, 1, Conv, [128, 1, 1]], 34 | [-1, 1, Conv, [128, 3, 1]], 35 | [-1, 1, Conv, [128, 3, 1]], 36 | [-1, 1, Conv, [128, 3, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 41 | [-1, 1, Conv, [320, 1, 1]], # 23 42 | 43 | [-1, 1, DownC, [640]], # 24-P4/16 44 | [-1, 1, Conv, [256, 1, 1]], 45 | [-2, 1, Conv, [256, 1, 1]], 46 | [-1, 1, Conv, [256, 3, 1]], 47 | [-1, 1, Conv, [256, 3, 1]], 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-1, 1, Conv, [256, 3, 1]], 50 | [-1, 1, Conv, [256, 3, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 53 | [-1, 1, Conv, [640, 1, 1]], # 34 54 | 55 | [-1, 1, DownC, [960]], # 35-P5/32 56 | [-1, 1, Conv, [384, 1, 1]], 57 | [-2, 1, Conv, [384, 1, 1]], 58 | [-1, 1, Conv, [384, 3, 1]], 59 | [-1, 1, Conv, [384, 3, 1]], 60 | [-1, 1, Conv, [384, 3, 1]], 61 | [-1, 1, Conv, [384, 3, 1]], 62 | [-1, 1, Conv, [384, 3, 1]], 63 | [-1, 1, Conv, [384, 3, 1]], 64 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 65 | [-1, 1, Conv, [960, 1, 1]], # 45 66 | 67 | [-1, 1, DownC, [1280]], # 46-P6/64 68 | [-1, 1, Conv, [512, 1, 1]], 69 | [-2, 1, Conv, [512, 1, 1]], 70 | [-1, 1, Conv, [512, 3, 1]], 71 | [-1, 1, Conv, [512, 3, 1]], 72 | [-1, 1, Conv, [512, 3, 1]], 73 | [-1, 1, Conv, [512, 3, 1]], 74 | [-1, 1, Conv, [512, 3, 1]], 75 | [-1, 1, Conv, [512, 3, 1]], 76 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 77 | [-1, 1, Conv, [1280, 1, 1]], # 56 78 | ] 79 | 80 | # yolov7-e6 head 81 | head: 82 | [[-1, 1, SPPCSPC, [640]], # 57 83 | 84 | [-1, 1, Conv, [480, 1, 1]], 85 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 86 | [45, 1, Conv, [480, 1, 1]], # route backbone P5 87 | [[-1, -2], 1, Concat, [1]], 88 | 89 | [-1, 1, Conv, [384, 1, 1]], 90 | [-2, 1, Conv, [384, 1, 1]], 91 | [-1, 1, Conv, [192, 3, 1]], 92 | [-1, 1, Conv, [192, 3, 1]], 93 | [-1, 1, Conv, [192, 3, 1]], 94 | [-1, 1, Conv, [192, 3, 1]], 95 | [-1, 1, Conv, [192, 3, 1]], 96 | [-1, 1, Conv, [192, 3, 1]], 97 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 98 | [-1, 1, Conv, [480, 1, 1]], # 71 99 | 100 | [-1, 1, Conv, [320, 1, 1]], 101 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 102 | [34, 1, Conv, [320, 1, 1]], # route backbone P4 103 | [[-1, -2], 1, Concat, [1]], 104 | 105 | [-1, 1, Conv, [256, 1, 1]], 106 | [-2, 1, Conv, [256, 1, 1]], 107 | [-1, 1, Conv, [128, 3, 1]], 108 | [-1, 1, Conv, [128, 3, 1]], 109 | [-1, 1, Conv, [128, 3, 1]], 110 | [-1, 1, Conv, [128, 3, 1]], 111 | [-1, 1, Conv, [128, 3, 1]], 112 | [-1, 1, Conv, [128, 3, 1]], 113 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 114 | [-1, 1, Conv, [320, 1, 1]], # 85 115 | 116 | [-1, 1, Conv, [160, 1, 1]], 117 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 118 | [23, 1, Conv, [160, 1, 1]], # route backbone P3 119 | [[-1, -2], 1, Concat, [1]], 120 | 121 | [-1, 1, Conv, [128, 1, 1]], 122 | [-2, 1, Conv, [128, 1, 1]], 123 | [-1, 1, Conv, [64, 3, 1]], 124 | [-1, 1, Conv, [64, 3, 1]], 125 | [-1, 1, Conv, [64, 3, 1]], 126 | [-1, 1, Conv, [64, 3, 1]], 127 | [-1, 1, Conv, [64, 3, 1]], 128 | [-1, 1, Conv, [64, 3, 1]], 129 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 130 | [-1, 1, Conv, [160, 1, 1]], # 99 131 | 132 | [-1, 1, DownC, [320]], 133 | [[-1, 85], 1, Concat, [1]], 134 | 135 | [-1, 1, Conv, [256, 1, 1]], 136 | [-2, 1, Conv, [256, 1, 1]], 137 | [-1, 1, Conv, [128, 3, 1]], 138 | [-1, 1, Conv, [128, 3, 1]], 139 | [-1, 1, Conv, [128, 3, 1]], 140 | [-1, 1, Conv, [128, 3, 1]], 141 | [-1, 1, Conv, [128, 3, 1]], 142 | [-1, 1, Conv, [128, 3, 1]], 143 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 144 | [-1, 1, Conv, [320, 1, 1]], # 111 145 | 146 | [-1, 1, DownC, [480]], 147 | [[-1, 71], 1, Concat, [1]], 148 | 149 | [-1, 1, Conv, [384, 1, 1]], 150 | [-2, 1, Conv, [384, 1, 1]], 151 | [-1, 1, Conv, [192, 3, 1]], 152 | [-1, 1, Conv, [192, 3, 1]], 153 | [-1, 1, Conv, [192, 3, 1]], 154 | [-1, 1, Conv, [192, 3, 1]], 155 | [-1, 1, Conv, [192, 3, 1]], 156 | [-1, 1, Conv, [192, 3, 1]], 157 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 158 | [-1, 1, Conv, [480, 1, 1]], # 123 159 | 160 | [-1, 1, DownC, [640]], 161 | [[-1, 57], 1, Concat, [1]], 162 | 163 | [-1, 1, Conv, [512, 1, 1]], 164 | [-2, 1, Conv, [512, 1, 1]], 165 | [-1, 1, Conv, [256, 3, 1]], 166 | [-1, 1, Conv, [256, 3, 1]], 167 | [-1, 1, Conv, [256, 3, 1]], 168 | [-1, 1, Conv, [256, 3, 1]], 169 | [-1, 1, Conv, [256, 3, 1]], 170 | [-1, 1, Conv, [256, 3, 1]], 171 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 172 | [-1, 1, Conv, [640, 1, 1]], # 135 173 | 174 | [99, 1, Conv, [320, 3, 1]], 175 | [111, 1, Conv, [640, 3, 1]], 176 | [123, 1, Conv, [960, 3, 1]], 177 | [135, 1, Conv, [1280, 3, 1]], 178 | 179 | [[136,137,138,139], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 180 | ] 181 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-e6e.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7-e6e backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [80, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [160]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 29 | [-1, 1, Conv, [160, 1, 1]], # 12 30 | [-11, 1, Conv, [64, 1, 1]], 31 | [-12, 1, Conv, [64, 1, 1]], 32 | [-1, 1, Conv, [64, 3, 1]], 33 | [-1, 1, Conv, [64, 3, 1]], 34 | [-1, 1, Conv, [64, 3, 1]], 35 | [-1, 1, Conv, [64, 3, 1]], 36 | [-1, 1, Conv, [64, 3, 1]], 37 | [-1, 1, Conv, [64, 3, 1]], 38 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 39 | [-1, 1, Conv, [160, 1, 1]], # 22 40 | [[-1, -11], 1, Shortcut, [1]], # 23 41 | 42 | [-1, 1, DownC, [320]], # 24-P3/8 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, Conv, [128, 3, 1]], 46 | [-1, 1, Conv, [128, 3, 1]], 47 | [-1, 1, Conv, [128, 3, 1]], 48 | [-1, 1, Conv, [128, 3, 1]], 49 | [-1, 1, Conv, [128, 3, 1]], 50 | [-1, 1, Conv, [128, 3, 1]], 51 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 52 | [-1, 1, Conv, [320, 1, 1]], # 34 53 | [-11, 1, Conv, [128, 1, 1]], 54 | [-12, 1, Conv, [128, 1, 1]], 55 | [-1, 1, Conv, [128, 3, 1]], 56 | [-1, 1, Conv, [128, 3, 1]], 57 | [-1, 1, Conv, [128, 3, 1]], 58 | [-1, 1, Conv, [128, 3, 1]], 59 | [-1, 1, Conv, [128, 3, 1]], 60 | [-1, 1, Conv, [128, 3, 1]], 61 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 62 | [-1, 1, Conv, [320, 1, 1]], # 44 63 | [[-1, -11], 1, Shortcut, [1]], # 45 64 | 65 | [-1, 1, DownC, [640]], # 46-P4/16 66 | [-1, 1, Conv, [256, 1, 1]], 67 | [-2, 1, Conv, [256, 1, 1]], 68 | [-1, 1, Conv, [256, 3, 1]], 69 | [-1, 1, Conv, [256, 3, 1]], 70 | [-1, 1, Conv, [256, 3, 1]], 71 | [-1, 1, Conv, [256, 3, 1]], 72 | [-1, 1, Conv, [256, 3, 1]], 73 | [-1, 1, Conv, [256, 3, 1]], 74 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 75 | [-1, 1, Conv, [640, 1, 1]], # 56 76 | [-11, 1, Conv, [256, 1, 1]], 77 | [-12, 1, Conv, [256, 1, 1]], 78 | [-1, 1, Conv, [256, 3, 1]], 79 | [-1, 1, Conv, [256, 3, 1]], 80 | [-1, 1, Conv, [256, 3, 1]], 81 | [-1, 1, Conv, [256, 3, 1]], 82 | [-1, 1, Conv, [256, 3, 1]], 83 | [-1, 1, Conv, [256, 3, 1]], 84 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 85 | [-1, 1, Conv, [640, 1, 1]], # 66 86 | [[-1, -11], 1, Shortcut, [1]], # 67 87 | 88 | [-1, 1, DownC, [960]], # 68-P5/32 89 | [-1, 1, Conv, [384, 1, 1]], 90 | [-2, 1, Conv, [384, 1, 1]], 91 | [-1, 1, Conv, [384, 3, 1]], 92 | [-1, 1, Conv, [384, 3, 1]], 93 | [-1, 1, Conv, [384, 3, 1]], 94 | [-1, 1, Conv, [384, 3, 1]], 95 | [-1, 1, Conv, [384, 3, 1]], 96 | [-1, 1, Conv, [384, 3, 1]], 97 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 98 | [-1, 1, Conv, [960, 1, 1]], # 78 99 | [-11, 1, Conv, [384, 1, 1]], 100 | [-12, 1, Conv, [384, 1, 1]], 101 | [-1, 1, Conv, [384, 3, 1]], 102 | [-1, 1, Conv, [384, 3, 1]], 103 | [-1, 1, Conv, [384, 3, 1]], 104 | [-1, 1, Conv, [384, 3, 1]], 105 | [-1, 1, Conv, [384, 3, 1]], 106 | [-1, 1, Conv, [384, 3, 1]], 107 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 108 | [-1, 1, Conv, [960, 1, 1]], # 88 109 | [[-1, -11], 1, Shortcut, [1]], # 89 110 | 111 | [-1, 1, DownC, [1280]], # 90-P6/64 112 | [-1, 1, Conv, [512, 1, 1]], 113 | [-2, 1, Conv, [512, 1, 1]], 114 | [-1, 1, Conv, [512, 3, 1]], 115 | [-1, 1, Conv, [512, 3, 1]], 116 | [-1, 1, Conv, [512, 3, 1]], 117 | [-1, 1, Conv, [512, 3, 1]], 118 | [-1, 1, Conv, [512, 3, 1]], 119 | [-1, 1, Conv, [512, 3, 1]], 120 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 121 | [-1, 1, Conv, [1280, 1, 1]], # 100 122 | [-11, 1, Conv, [512, 1, 1]], 123 | [-12, 1, Conv, [512, 1, 1]], 124 | [-1, 1, Conv, [512, 3, 1]], 125 | [-1, 1, Conv, [512, 3, 1]], 126 | [-1, 1, Conv, [512, 3, 1]], 127 | [-1, 1, Conv, [512, 3, 1]], 128 | [-1, 1, Conv, [512, 3, 1]], 129 | [-1, 1, Conv, [512, 3, 1]], 130 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 131 | [-1, 1, Conv, [1280, 1, 1]], # 110 132 | [[-1, -11], 1, Shortcut, [1]], # 111 133 | ] 134 | 135 | # yolov7-e6e head 136 | head: 137 | [[-1, 1, SPPCSPC, [640]], # 112 138 | 139 | [-1, 1, Conv, [480, 1, 1]], 140 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 141 | [89, 1, Conv, [480, 1, 1]], # route backbone P5 142 | [[-1, -2], 1, Concat, [1]], 143 | 144 | [-1, 1, Conv, [384, 1, 1]], 145 | [-2, 1, Conv, [384, 1, 1]], 146 | [-1, 1, Conv, [192, 3, 1]], 147 | [-1, 1, Conv, [192, 3, 1]], 148 | [-1, 1, Conv, [192, 3, 1]], 149 | [-1, 1, Conv, [192, 3, 1]], 150 | [-1, 1, Conv, [192, 3, 1]], 151 | [-1, 1, Conv, [192, 3, 1]], 152 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 153 | [-1, 1, Conv, [480, 1, 1]], # 126 154 | [-11, 1, Conv, [384, 1, 1]], 155 | [-12, 1, Conv, [384, 1, 1]], 156 | [-1, 1, Conv, [192, 3, 1]], 157 | [-1, 1, Conv, [192, 3, 1]], 158 | [-1, 1, Conv, [192, 3, 1]], 159 | [-1, 1, Conv, [192, 3, 1]], 160 | [-1, 1, Conv, [192, 3, 1]], 161 | [-1, 1, Conv, [192, 3, 1]], 162 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 163 | [-1, 1, Conv, [480, 1, 1]], # 136 164 | [[-1, -11], 1, Shortcut, [1]], # 137 165 | 166 | [-1, 1, Conv, [320, 1, 1]], 167 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 168 | [67, 1, Conv, [320, 1, 1]], # route backbone P4 169 | [[-1, -2], 1, Concat, [1]], 170 | 171 | [-1, 1, Conv, [256, 1, 1]], 172 | [-2, 1, Conv, [256, 1, 1]], 173 | [-1, 1, Conv, [128, 3, 1]], 174 | [-1, 1, Conv, [128, 3, 1]], 175 | [-1, 1, Conv, [128, 3, 1]], 176 | [-1, 1, Conv, [128, 3, 1]], 177 | [-1, 1, Conv, [128, 3, 1]], 178 | [-1, 1, Conv, [128, 3, 1]], 179 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 180 | [-1, 1, Conv, [320, 1, 1]], # 151 181 | [-11, 1, Conv, [256, 1, 1]], 182 | [-12, 1, Conv, [256, 1, 1]], 183 | [-1, 1, Conv, [128, 3, 1]], 184 | [-1, 1, Conv, [128, 3, 1]], 185 | [-1, 1, Conv, [128, 3, 1]], 186 | [-1, 1, Conv, [128, 3, 1]], 187 | [-1, 1, Conv, [128, 3, 1]], 188 | [-1, 1, Conv, [128, 3, 1]], 189 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 190 | [-1, 1, Conv, [320, 1, 1]], # 161 191 | [[-1, -11], 1, Shortcut, [1]], # 162 192 | 193 | [-1, 1, Conv, [160, 1, 1]], 194 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 195 | [45, 1, Conv, [160, 1, 1]], # route backbone P3 196 | [[-1, -2], 1, Concat, [1]], 197 | 198 | [-1, 1, Conv, [128, 1, 1]], 199 | [-2, 1, Conv, [128, 1, 1]], 200 | [-1, 1, Conv, [64, 3, 1]], 201 | [-1, 1, Conv, [64, 3, 1]], 202 | [-1, 1, Conv, [64, 3, 1]], 203 | [-1, 1, Conv, [64, 3, 1]], 204 | [-1, 1, Conv, [64, 3, 1]], 205 | [-1, 1, Conv, [64, 3, 1]], 206 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 207 | [-1, 1, Conv, [160, 1, 1]], # 176 208 | [-11, 1, Conv, [128, 1, 1]], 209 | [-12, 1, Conv, [128, 1, 1]], 210 | [-1, 1, Conv, [64, 3, 1]], 211 | [-1, 1, Conv, [64, 3, 1]], 212 | [-1, 1, Conv, [64, 3, 1]], 213 | [-1, 1, Conv, [64, 3, 1]], 214 | [-1, 1, Conv, [64, 3, 1]], 215 | [-1, 1, Conv, [64, 3, 1]], 216 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 217 | [-1, 1, Conv, [160, 1, 1]], # 186 218 | [[-1, -11], 1, Shortcut, [1]], # 187 219 | 220 | [-1, 1, DownC, [320]], 221 | [[-1, 162], 1, Concat, [1]], 222 | 223 | [-1, 1, Conv, [256, 1, 1]], 224 | [-2, 1, Conv, [256, 1, 1]], 225 | [-1, 1, Conv, [128, 3, 1]], 226 | [-1, 1, Conv, [128, 3, 1]], 227 | [-1, 1, Conv, [128, 3, 1]], 228 | [-1, 1, Conv, [128, 3, 1]], 229 | [-1, 1, Conv, [128, 3, 1]], 230 | [-1, 1, Conv, [128, 3, 1]], 231 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 232 | [-1, 1, Conv, [320, 1, 1]], # 199 233 | [-11, 1, Conv, [256, 1, 1]], 234 | [-12, 1, Conv, [256, 1, 1]], 235 | [-1, 1, Conv, [128, 3, 1]], 236 | [-1, 1, Conv, [128, 3, 1]], 237 | [-1, 1, Conv, [128, 3, 1]], 238 | [-1, 1, Conv, [128, 3, 1]], 239 | [-1, 1, Conv, [128, 3, 1]], 240 | [-1, 1, Conv, [128, 3, 1]], 241 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 242 | [-1, 1, Conv, [320, 1, 1]], # 209 243 | [[-1, -11], 1, Shortcut, [1]], # 210 244 | 245 | [-1, 1, DownC, [480]], 246 | [[-1, 137], 1, Concat, [1]], 247 | 248 | [-1, 1, Conv, [384, 1, 1]], 249 | [-2, 1, Conv, [384, 1, 1]], 250 | [-1, 1, Conv, [192, 3, 1]], 251 | [-1, 1, Conv, [192, 3, 1]], 252 | [-1, 1, Conv, [192, 3, 1]], 253 | [-1, 1, Conv, [192, 3, 1]], 254 | [-1, 1, Conv, [192, 3, 1]], 255 | [-1, 1, Conv, [192, 3, 1]], 256 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 257 | [-1, 1, Conv, [480, 1, 1]], # 222 258 | [-11, 1, Conv, [384, 1, 1]], 259 | [-12, 1, Conv, [384, 1, 1]], 260 | [-1, 1, Conv, [192, 3, 1]], 261 | [-1, 1, Conv, [192, 3, 1]], 262 | [-1, 1, Conv, [192, 3, 1]], 263 | [-1, 1, Conv, [192, 3, 1]], 264 | [-1, 1, Conv, [192, 3, 1]], 265 | [-1, 1, Conv, [192, 3, 1]], 266 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 267 | [-1, 1, Conv, [480, 1, 1]], # 232 268 | [[-1, -11], 1, Shortcut, [1]], # 233 269 | 270 | [-1, 1, DownC, [640]], 271 | [[-1, 112], 1, Concat, [1]], 272 | 273 | [-1, 1, Conv, [512, 1, 1]], 274 | [-2, 1, Conv, [512, 1, 1]], 275 | [-1, 1, Conv, [256, 3, 1]], 276 | [-1, 1, Conv, [256, 3, 1]], 277 | [-1, 1, Conv, [256, 3, 1]], 278 | [-1, 1, Conv, [256, 3, 1]], 279 | [-1, 1, Conv, [256, 3, 1]], 280 | [-1, 1, Conv, [256, 3, 1]], 281 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 282 | [-1, 1, Conv, [640, 1, 1]], # 245 283 | [-11, 1, Conv, [512, 1, 1]], 284 | [-12, 1, Conv, [512, 1, 1]], 285 | [-1, 1, Conv, [256, 3, 1]], 286 | [-1, 1, Conv, [256, 3, 1]], 287 | [-1, 1, Conv, [256, 3, 1]], 288 | [-1, 1, Conv, [256, 3, 1]], 289 | [-1, 1, Conv, [256, 3, 1]], 290 | [-1, 1, Conv, [256, 3, 1]], 291 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 292 | [-1, 1, Conv, [640, 1, 1]], # 255 293 | [[-1, -11], 1, Shortcut, [1]], # 256 294 | 295 | [187, 1, Conv, [320, 3, 1]], 296 | [210, 1, Conv, [640, 3, 1]], 297 | [233, 1, Conv, [960, 3, 1]], 298 | [256, 1, Conv, [1280, 3, 1]], 299 | 300 | [[257,258,259,260], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 301 | ] 302 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-tiny-silu.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv7-tiny backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 2]], # 0-P1/2 16 | 17 | [-1, 1, Conv, [64, 3, 2]], # 1-P2/4 18 | 19 | [-1, 1, Conv, [32, 1, 1]], 20 | [-2, 1, Conv, [32, 1, 1]], 21 | [-1, 1, Conv, [32, 3, 1]], 22 | [-1, 1, Conv, [32, 3, 1]], 23 | [[-1, -2, -3, -4], 1, Concat, [1]], 24 | [-1, 1, Conv, [64, 1, 1]], # 7 25 | 26 | [-1, 1, MP, []], # 8-P3/8 27 | [-1, 1, Conv, [64, 1, 1]], 28 | [-2, 1, Conv, [64, 1, 1]], 29 | [-1, 1, Conv, [64, 3, 1]], 30 | [-1, 1, Conv, [64, 3, 1]], 31 | [[-1, -2, -3, -4], 1, Concat, [1]], 32 | [-1, 1, Conv, [128, 1, 1]], # 14 33 | 34 | [-1, 1, MP, []], # 15-P4/16 35 | [-1, 1, Conv, [128, 1, 1]], 36 | [-2, 1, Conv, [128, 1, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [[-1, -2, -3, -4], 1, Concat, [1]], 40 | [-1, 1, Conv, [256, 1, 1]], # 21 41 | 42 | [-1, 1, MP, []], # 22-P5/32 43 | [-1, 1, Conv, [256, 1, 1]], 44 | [-2, 1, Conv, [256, 1, 1]], 45 | [-1, 1, Conv, [256, 3, 1]], 46 | [-1, 1, Conv, [256, 3, 1]], 47 | [[-1, -2, -3, -4], 1, Concat, [1]], 48 | [-1, 1, Conv, [512, 1, 1]], # 28 49 | ] 50 | 51 | # YOLOv7-tiny head 52 | head: 53 | [[-1, 1, Conv, [256, 1, 1]], 54 | [-2, 1, Conv, [256, 1, 1]], 55 | [-1, 1, SP, [5]], 56 | [-2, 1, SP, [9]], 57 | [-3, 1, SP, [13]], 58 | [[-1, -2, -3, -4], 1, Concat, [1]], 59 | [-1, 1, Conv, [256, 1, 1]], 60 | [[-1, -7], 1, Concat, [1]], 61 | [-1, 1, Conv, [256, 1, 1]], # 37 62 | 63 | [-1, 1, Conv, [128, 1, 1]], 64 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 65 | [21, 1, Conv, [128, 1, 1]], # route backbone P4 66 | [[-1, -2], 1, Concat, [1]], 67 | 68 | [-1, 1, Conv, [64, 1, 1]], 69 | [-2, 1, Conv, [64, 1, 1]], 70 | [-1, 1, Conv, [64, 3, 1]], 71 | [-1, 1, Conv, [64, 3, 1]], 72 | [[-1, -2, -3, -4], 1, Concat, [1]], 73 | [-1, 1, Conv, [128, 1, 1]], # 47 74 | 75 | [-1, 1, Conv, [64, 1, 1]], 76 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 77 | [14, 1, Conv, [64, 1, 1]], # route backbone P3 78 | [[-1, -2], 1, Concat, [1]], 79 | 80 | [-1, 1, Conv, [32, 1, 1]], 81 | [-2, 1, Conv, [32, 1, 1]], 82 | [-1, 1, Conv, [32, 3, 1]], 83 | [-1, 1, Conv, [32, 3, 1]], 84 | [[-1, -2, -3, -4], 1, Concat, [1]], 85 | [-1, 1, Conv, [64, 1, 1]], # 57 86 | 87 | [-1, 1, Conv, [128, 3, 2]], 88 | [[-1, 47], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [64, 1, 1]], 91 | [-2, 1, Conv, [64, 1, 1]], 92 | [-1, 1, Conv, [64, 3, 1]], 93 | [-1, 1, Conv, [64, 3, 1]], 94 | [[-1, -2, -3, -4], 1, Concat, [1]], 95 | [-1, 1, Conv, [128, 1, 1]], # 65 96 | 97 | [-1, 1, Conv, [256, 3, 2]], 98 | [[-1, 37], 1, Concat, [1]], 99 | 100 | [-1, 1, Conv, [128, 1, 1]], 101 | [-2, 1, Conv, [128, 1, 1]], 102 | [-1, 1, Conv, [128, 3, 1]], 103 | [-1, 1, Conv, [128, 3, 1]], 104 | [[-1, -2, -3, -4], 1, Concat, [1]], 105 | [-1, 1, Conv, [256, 1, 1]], # 73 106 | 107 | [57, 1, Conv, [128, 3, 1]], 108 | [65, 1, Conv, [256, 3, 1]], 109 | [73, 1, Conv, [512, 3, 1]], 110 | 111 | [[74,75,76], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 112 | ] 113 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-tiny.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # yolov7-tiny backbone 13 | backbone: 14 | # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True 15 | [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 0-P1/2 16 | 17 | [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 1-P2/4 18 | 19 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 20 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 21 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 22 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 23 | [[-1, -2, -3, -4], 1, Concat, [1]], 24 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 7 25 | 26 | [-1, 1, MP, []], # 8-P3/8 27 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 28 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 29 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 30 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 31 | [[-1, -2, -3, -4], 1, Concat, [1]], 32 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 14 33 | 34 | [-1, 1, MP, []], # 15-P4/16 35 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 36 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 37 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 38 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 39 | [[-1, -2, -3, -4], 1, Concat, [1]], 40 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 21 41 | 42 | [-1, 1, MP, []], # 22-P5/32 43 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 44 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 45 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 46 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 47 | [[-1, -2, -3, -4], 1, Concat, [1]], 48 | [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 28 49 | ] 50 | 51 | # yolov7-tiny head 52 | head: 53 | [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 54 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 55 | [-1, 1, SP, [5]], 56 | [-2, 1, SP, [9]], 57 | [-3, 1, SP, [13]], 58 | [[-1, -2, -3, -4], 1, Concat, [1]], 59 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 60 | [[-1, -7], 1, Concat, [1]], 61 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 37 62 | 63 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 64 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 65 | [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4 66 | [[-1, -2], 1, Concat, [1]], 67 | 68 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 69 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 70 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 71 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 72 | [[-1, -2, -3, -4], 1, Concat, [1]], 73 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 47 74 | 75 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 76 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 77 | [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3 78 | [[-1, -2], 1, Concat, [1]], 79 | 80 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 81 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 82 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 83 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 84 | [[-1, -2, -3, -4], 1, Concat, [1]], 85 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 57 86 | 87 | [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]], 88 | [[-1, 47], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 91 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 92 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 93 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 94 | [[-1, -2, -3, -4], 1, Concat, [1]], 95 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 65 96 | 97 | [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]], 98 | [[-1, 37], 1, Concat, [1]], 99 | 100 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 101 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 102 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 103 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 104 | [[-1, -2, -3, -4], 1, Concat, [1]], 105 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 73 106 | 107 | [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 108 | [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 109 | [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 110 | 111 | [[74,75,76], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 112 | ] 113 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7-w6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7-w6 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, Conv, [128, 3, 2]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [[-1, -3, -5, -6], 1, Concat, [1]], 27 | [-1, 1, Conv, [128, 1, 1]], # 10 28 | 29 | [-1, 1, Conv, [256, 3, 2]], # 11-P3/8 30 | [-1, 1, Conv, [128, 1, 1]], 31 | [-2, 1, Conv, [128, 1, 1]], 32 | [-1, 1, Conv, [128, 3, 1]], 33 | [-1, 1, Conv, [128, 3, 1]], 34 | [-1, 1, Conv, [128, 3, 1]], 35 | [-1, 1, Conv, [128, 3, 1]], 36 | [[-1, -3, -5, -6], 1, Concat, [1]], 37 | [-1, 1, Conv, [256, 1, 1]], # 19 38 | 39 | [-1, 1, Conv, [512, 3, 2]], # 20-P4/16 40 | [-1, 1, Conv, [256, 1, 1]], 41 | [-2, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [256, 3, 1]], 43 | [-1, 1, Conv, [256, 3, 1]], 44 | [-1, 1, Conv, [256, 3, 1]], 45 | [-1, 1, Conv, [256, 3, 1]], 46 | [[-1, -3, -5, -6], 1, Concat, [1]], 47 | [-1, 1, Conv, [512, 1, 1]], # 28 48 | 49 | [-1, 1, Conv, [768, 3, 2]], # 29-P5/32 50 | [-1, 1, Conv, [384, 1, 1]], 51 | [-2, 1, Conv, [384, 1, 1]], 52 | [-1, 1, Conv, [384, 3, 1]], 53 | [-1, 1, Conv, [384, 3, 1]], 54 | [-1, 1, Conv, [384, 3, 1]], 55 | [-1, 1, Conv, [384, 3, 1]], 56 | [[-1, -3, -5, -6], 1, Concat, [1]], 57 | [-1, 1, Conv, [768, 1, 1]], # 37 58 | 59 | [-1, 1, Conv, [1024, 3, 2]], # 38-P6/64 60 | [-1, 1, Conv, [512, 1, 1]], 61 | [-2, 1, Conv, [512, 1, 1]], 62 | [-1, 1, Conv, [512, 3, 1]], 63 | [-1, 1, Conv, [512, 3, 1]], 64 | [-1, 1, Conv, [512, 3, 1]], 65 | [-1, 1, Conv, [512, 3, 1]], 66 | [[-1, -3, -5, -6], 1, Concat, [1]], 67 | [-1, 1, Conv, [1024, 1, 1]], # 46 68 | ] 69 | 70 | # yolov7-w6 head 71 | head: 72 | [[-1, 1, SPPCSPC, [512]], # 47 73 | 74 | [-1, 1, Conv, [384, 1, 1]], 75 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 76 | [37, 1, Conv, [384, 1, 1]], # route backbone P5 77 | [[-1, -2], 1, Concat, [1]], 78 | 79 | [-1, 1, Conv, [384, 1, 1]], 80 | [-2, 1, Conv, [384, 1, 1]], 81 | [-1, 1, Conv, [192, 3, 1]], 82 | [-1, 1, Conv, [192, 3, 1]], 83 | [-1, 1, Conv, [192, 3, 1]], 84 | [-1, 1, Conv, [192, 3, 1]], 85 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 86 | [-1, 1, Conv, [384, 1, 1]], # 59 87 | 88 | [-1, 1, Conv, [256, 1, 1]], 89 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 90 | [28, 1, Conv, [256, 1, 1]], # route backbone P4 91 | [[-1, -2], 1, Concat, [1]], 92 | 93 | [-1, 1, Conv, [256, 1, 1]], 94 | [-2, 1, Conv, [256, 1, 1]], 95 | [-1, 1, Conv, [128, 3, 1]], 96 | [-1, 1, Conv, [128, 3, 1]], 97 | [-1, 1, Conv, [128, 3, 1]], 98 | [-1, 1, Conv, [128, 3, 1]], 99 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 100 | [-1, 1, Conv, [256, 1, 1]], # 71 101 | 102 | [-1, 1, Conv, [128, 1, 1]], 103 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 104 | [19, 1, Conv, [128, 1, 1]], # route backbone P3 105 | [[-1, -2], 1, Concat, [1]], 106 | 107 | [-1, 1, Conv, [128, 1, 1]], 108 | [-2, 1, Conv, [128, 1, 1]], 109 | [-1, 1, Conv, [64, 3, 1]], 110 | [-1, 1, Conv, [64, 3, 1]], 111 | [-1, 1, Conv, [64, 3, 1]], 112 | [-1, 1, Conv, [64, 3, 1]], 113 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 114 | [-1, 1, Conv, [128, 1, 1]], # 83 115 | 116 | [-1, 1, Conv, [256, 3, 2]], 117 | [[-1, 71], 1, Concat, [1]], # cat 118 | 119 | [-1, 1, Conv, [256, 1, 1]], 120 | [-2, 1, Conv, [256, 1, 1]], 121 | [-1, 1, Conv, [128, 3, 1]], 122 | [-1, 1, Conv, [128, 3, 1]], 123 | [-1, 1, Conv, [128, 3, 1]], 124 | [-1, 1, Conv, [128, 3, 1]], 125 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 126 | [-1, 1, Conv, [256, 1, 1]], # 93 127 | 128 | [-1, 1, Conv, [384, 3, 2]], 129 | [[-1, 59], 1, Concat, [1]], # cat 130 | 131 | [-1, 1, Conv, [384, 1, 1]], 132 | [-2, 1, Conv, [384, 1, 1]], 133 | [-1, 1, Conv, [192, 3, 1]], 134 | [-1, 1, Conv, [192, 3, 1]], 135 | [-1, 1, Conv, [192, 3, 1]], 136 | [-1, 1, Conv, [192, 3, 1]], 137 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 138 | [-1, 1, Conv, [384, 1, 1]], # 103 139 | 140 | [-1, 1, Conv, [512, 3, 2]], 141 | [[-1, 47], 1, Concat, [1]], # cat 142 | 143 | [-1, 1, Conv, [512, 1, 1]], 144 | [-2, 1, Conv, [512, 1, 1]], 145 | [-1, 1, Conv, [256, 3, 1]], 146 | [-1, 1, Conv, [256, 3, 1]], 147 | [-1, 1, Conv, [256, 3, 1]], 148 | [-1, 1, Conv, [256, 3, 1]], 149 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 150 | [-1, 1, Conv, [512, 1, 1]], # 113 151 | 152 | [83, 1, Conv, [256, 3, 1]], 153 | [93, 1, Conv, [512, 3, 1]], 154 | [103, 1, Conv, [768, 3, 1]], 155 | [113, 1, Conv, [1024, 3, 1]], 156 | 157 | [[114,115,116,117], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 158 | ] 159 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # yolov7 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | 17 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 18 | [-1, 1, Conv, [64, 3, 1]], 19 | 20 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 21 | [-1, 1, Conv, [64, 1, 1]], 22 | [-2, 1, Conv, [64, 1, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [[-1, -3, -5, -6], 1, Concat, [1]], 28 | [-1, 1, Conv, [256, 1, 1]], # 11 29 | 30 | [-1, 1, MP, []], 31 | [-1, 1, Conv, [128, 1, 1]], 32 | [-3, 1, Conv, [128, 1, 1]], 33 | [-1, 1, Conv, [128, 3, 2]], 34 | [[-1, -3], 1, Concat, [1]], # 16-P3/8 35 | [-1, 1, Conv, [128, 1, 1]], 36 | [-2, 1, Conv, [128, 1, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [[-1, -3, -5, -6], 1, Concat, [1]], 42 | [-1, 1, Conv, [512, 1, 1]], # 24 43 | 44 | [-1, 1, MP, []], 45 | [-1, 1, Conv, [256, 1, 1]], 46 | [-3, 1, Conv, [256, 1, 1]], 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, -3], 1, Concat, [1]], # 29-P4/16 49 | [-1, 1, Conv, [256, 1, 1]], 50 | [-2, 1, Conv, [256, 1, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [-1, 1, Conv, [256, 3, 1]], 53 | [-1, 1, Conv, [256, 3, 1]], 54 | [-1, 1, Conv, [256, 3, 1]], 55 | [[-1, -3, -5, -6], 1, Concat, [1]], 56 | [-1, 1, Conv, [1024, 1, 1]], # 37 57 | 58 | [-1, 1, MP, []], 59 | [-1, 1, Conv, [512, 1, 1]], 60 | [-3, 1, Conv, [512, 1, 1]], 61 | [-1, 1, Conv, [512, 3, 2]], 62 | [[-1, -3], 1, Concat, [1]], # 42-P5/32 63 | [-1, 1, Conv, [256, 1, 1]], 64 | [-2, 1, Conv, [256, 1, 1]], 65 | [-1, 1, Conv, [256, 3, 1]], 66 | [-1, 1, Conv, [256, 3, 1]], 67 | [-1, 1, Conv, [256, 3, 1]], 68 | [-1, 1, Conv, [256, 3, 1]], 69 | [[-1, -3, -5, -6], 1, Concat, [1]], 70 | [-1, 1, Conv, [1024, 1, 1]], # 50 71 | ] 72 | 73 | # yolov7 head 74 | head: 75 | [[-1, 1, SPPCSPC, [512]], # 51 76 | 77 | [-1, 1, Conv, [256, 1, 1]], 78 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 79 | [37, 1, Conv, [256, 1, 1]], # route backbone P4 80 | [[-1, -2], 1, Concat, [1]], 81 | 82 | [-1, 1, Conv, [256, 1, 1]], 83 | [-2, 1, Conv, [256, 1, 1]], 84 | [-1, 1, Conv, [128, 3, 1]], 85 | [-1, 1, Conv, [128, 3, 1]], 86 | [-1, 1, Conv, [128, 3, 1]], 87 | [-1, 1, Conv, [128, 3, 1]], 88 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 89 | [-1, 1, Conv, [256, 1, 1]], # 63 90 | 91 | [-1, 1, Conv, [128, 1, 1]], 92 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 93 | [24, 1, Conv, [128, 1, 1]], # route backbone P3 94 | [[-1, -2], 1, Concat, [1]], 95 | 96 | [-1, 1, Conv, [128, 1, 1]], 97 | [-2, 1, Conv, [128, 1, 1]], 98 | [-1, 1, Conv, [64, 3, 1]], 99 | [-1, 1, Conv, [64, 3, 1]], 100 | [-1, 1, Conv, [64, 3, 1]], 101 | [-1, 1, Conv, [64, 3, 1]], 102 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 103 | [-1, 1, Conv, [128, 1, 1]], # 75 104 | 105 | [-1, 1, MP, []], 106 | [-1, 1, Conv, [128, 1, 1]], 107 | [-3, 1, Conv, [128, 1, 1]], 108 | [-1, 1, Conv, [128, 3, 2]], 109 | [[-1, -3, 63], 1, Concat, [1]], 110 | 111 | [-1, 1, Conv, [256, 1, 1]], 112 | [-2, 1, Conv, [256, 1, 1]], 113 | [-1, 1, Conv, [128, 3, 1]], 114 | [-1, 1, Conv, [128, 3, 1]], 115 | [-1, 1, Conv, [128, 3, 1]], 116 | [-1, 1, Conv, [128, 3, 1]], 117 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 118 | [-1, 1, Conv, [256, 1, 1]], # 88 119 | 120 | [-1, 1, MP, []], 121 | [-1, 1, Conv, [256, 1, 1]], 122 | [-3, 1, Conv, [256, 1, 1]], 123 | [-1, 1, Conv, [256, 3, 2]], 124 | [[-1, -3, 51], 1, Concat, [1]], 125 | 126 | [-1, 1, Conv, [512, 1, 1]], 127 | [-2, 1, Conv, [512, 1, 1]], 128 | [-1, 1, Conv, [256, 3, 1]], 129 | [-1, 1, Conv, [256, 3, 1]], 130 | [-1, 1, Conv, [256, 3, 1]], 131 | [-1, 1, Conv, [256, 3, 1]], 132 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 133 | [-1, 1, Conv, [512, 1, 1]], # 101 134 | 135 | [75, 1, RepConv, [256, 3, 1]], 136 | [88, 1, RepConv, [512, 3, 1]], 137 | [101, 1, RepConv, [1024, 3, 1]], 138 | 139 | [[102,103,104], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 140 | ] 141 | -------------------------------------------------------------------------------- /cfg/deploy/yolov7x.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # yolov7x backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [40, 3, 1]], # 0 16 | 17 | [-1, 1, Conv, [80, 3, 2]], # 1-P1/2 18 | [-1, 1, Conv, [80, 3, 1]], 19 | 20 | [-1, 1, Conv, [160, 3, 2]], # 3-P2/4 21 | [-1, 1, Conv, [64, 1, 1]], 22 | [-2, 1, Conv, [64, 1, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [-1, 1, Conv, [64, 3, 1]], 29 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 30 | [-1, 1, Conv, [320, 1, 1]], # 13 31 | 32 | [-1, 1, MP, []], 33 | [-1, 1, Conv, [160, 1, 1]], 34 | [-3, 1, Conv, [160, 1, 1]], 35 | [-1, 1, Conv, [160, 3, 2]], 36 | [[-1, -3], 1, Concat, [1]], # 18-P3/8 37 | [-1, 1, Conv, [128, 1, 1]], 38 | [-2, 1, Conv, [128, 1, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [-1, 1, Conv, [128, 3, 1]], 42 | [-1, 1, Conv, [128, 3, 1]], 43 | [-1, 1, Conv, [128, 3, 1]], 44 | [-1, 1, Conv, [128, 3, 1]], 45 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 46 | [-1, 1, Conv, [640, 1, 1]], # 28 47 | 48 | [-1, 1, MP, []], 49 | [-1, 1, Conv, [320, 1, 1]], 50 | [-3, 1, Conv, [320, 1, 1]], 51 | [-1, 1, Conv, [320, 3, 2]], 52 | [[-1, -3], 1, Concat, [1]], # 33-P4/16 53 | [-1, 1, Conv, [256, 1, 1]], 54 | [-2, 1, Conv, [256, 1, 1]], 55 | [-1, 1, Conv, [256, 3, 1]], 56 | [-1, 1, Conv, [256, 3, 1]], 57 | [-1, 1, Conv, [256, 3, 1]], 58 | [-1, 1, Conv, [256, 3, 1]], 59 | [-1, 1, Conv, [256, 3, 1]], 60 | [-1, 1, Conv, [256, 3, 1]], 61 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 62 | [-1, 1, Conv, [1280, 1, 1]], # 43 63 | 64 | [-1, 1, MP, []], 65 | [-1, 1, Conv, [640, 1, 1]], 66 | [-3, 1, Conv, [640, 1, 1]], 67 | [-1, 1, Conv, [640, 3, 2]], 68 | [[-1, -3], 1, Concat, [1]], # 48-P5/32 69 | [-1, 1, Conv, [256, 1, 1]], 70 | [-2, 1, Conv, [256, 1, 1]], 71 | [-1, 1, Conv, [256, 3, 1]], 72 | [-1, 1, Conv, [256, 3, 1]], 73 | [-1, 1, Conv, [256, 3, 1]], 74 | [-1, 1, Conv, [256, 3, 1]], 75 | [-1, 1, Conv, [256, 3, 1]], 76 | [-1, 1, Conv, [256, 3, 1]], 77 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 78 | [-1, 1, Conv, [1280, 1, 1]], # 58 79 | ] 80 | 81 | # yolov7x head 82 | head: 83 | [[-1, 1, SPPCSPC, [640]], # 59 84 | 85 | [-1, 1, Conv, [320, 1, 1]], 86 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 87 | [43, 1, Conv, [320, 1, 1]], # route backbone P4 88 | [[-1, -2], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [256, 1, 1]], 91 | [-2, 1, Conv, [256, 1, 1]], 92 | [-1, 1, Conv, [256, 3, 1]], 93 | [-1, 1, Conv, [256, 3, 1]], 94 | [-1, 1, Conv, [256, 3, 1]], 95 | [-1, 1, Conv, [256, 3, 1]], 96 | [-1, 1, Conv, [256, 3, 1]], 97 | [-1, 1, Conv, [256, 3, 1]], 98 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 99 | [-1, 1, Conv, [320, 1, 1]], # 73 100 | 101 | [-1, 1, Conv, [160, 1, 1]], 102 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 103 | [28, 1, Conv, [160, 1, 1]], # route backbone P3 104 | [[-1, -2], 1, Concat, [1]], 105 | 106 | [-1, 1, Conv, [128, 1, 1]], 107 | [-2, 1, Conv, [128, 1, 1]], 108 | [-1, 1, Conv, [128, 3, 1]], 109 | [-1, 1, Conv, [128, 3, 1]], 110 | [-1, 1, Conv, [128, 3, 1]], 111 | [-1, 1, Conv, [128, 3, 1]], 112 | [-1, 1, Conv, [128, 3, 1]], 113 | [-1, 1, Conv, [128, 3, 1]], 114 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 115 | [-1, 1, Conv, [160, 1, 1]], # 87 116 | 117 | [-1, 1, MP, []], 118 | [-1, 1, Conv, [160, 1, 1]], 119 | [-3, 1, Conv, [160, 1, 1]], 120 | [-1, 1, Conv, [160, 3, 2]], 121 | [[-1, -3, 73], 1, Concat, [1]], 122 | 123 | [-1, 1, Conv, [256, 1, 1]], 124 | [-2, 1, Conv, [256, 1, 1]], 125 | [-1, 1, Conv, [256, 3, 1]], 126 | [-1, 1, Conv, [256, 3, 1]], 127 | [-1, 1, Conv, [256, 3, 1]], 128 | [-1, 1, Conv, [256, 3, 1]], 129 | [-1, 1, Conv, [256, 3, 1]], 130 | [-1, 1, Conv, [256, 3, 1]], 131 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 132 | [-1, 1, Conv, [320, 1, 1]], # 102 133 | 134 | [-1, 1, MP, []], 135 | [-1, 1, Conv, [320, 1, 1]], 136 | [-3, 1, Conv, [320, 1, 1]], 137 | [-1, 1, Conv, [320, 3, 2]], 138 | [[-1, -3, 59], 1, Concat, [1]], 139 | 140 | [-1, 1, Conv, [512, 1, 1]], 141 | [-2, 1, Conv, [512, 1, 1]], 142 | [-1, 1, Conv, [512, 3, 1]], 143 | [-1, 1, Conv, [512, 3, 1]], 144 | [-1, 1, Conv, [512, 3, 1]], 145 | [-1, 1, Conv, [512, 3, 1]], 146 | [-1, 1, Conv, [512, 3, 1]], 147 | [-1, 1, Conv, [512, 3, 1]], 148 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 149 | [-1, 1, Conv, [640, 1, 1]], # 117 150 | 151 | [87, 1, Conv, [320, 3, 1]], 152 | [102, 1, Conv, [640, 3, 1]], 153 | [117, 1, Conv, [1280, 3, 1]], 154 | 155 | [[118,119,120], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 156 | ] 157 | -------------------------------------------------------------------------------- /cfg/training/yolov7-d6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7 backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [96, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [192]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [-1, 1, Conv, [64, 3, 1]], 29 | [-1, 1, Conv, [64, 3, 1]], 30 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 31 | [-1, 1, Conv, [192, 1, 1]], # 14 32 | 33 | [-1, 1, DownC, [384]], # 15-P3/8 34 | [-1, 1, Conv, [128, 1, 1]], 35 | [-2, 1, Conv, [128, 1, 1]], 36 | [-1, 1, Conv, [128, 3, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [-1, 1, Conv, [128, 3, 1]], 42 | [-1, 1, Conv, [128, 3, 1]], 43 | [-1, 1, Conv, [128, 3, 1]], 44 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 45 | [-1, 1, Conv, [384, 1, 1]], # 27 46 | 47 | [-1, 1, DownC, [768]], # 28-P4/16 48 | [-1, 1, Conv, [256, 1, 1]], 49 | [-2, 1, Conv, [256, 1, 1]], 50 | [-1, 1, Conv, [256, 3, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [-1, 1, Conv, [256, 3, 1]], 53 | [-1, 1, Conv, [256, 3, 1]], 54 | [-1, 1, Conv, [256, 3, 1]], 55 | [-1, 1, Conv, [256, 3, 1]], 56 | [-1, 1, Conv, [256, 3, 1]], 57 | [-1, 1, Conv, [256, 3, 1]], 58 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 59 | [-1, 1, Conv, [768, 1, 1]], # 40 60 | 61 | [-1, 1, DownC, [1152]], # 41-P5/32 62 | [-1, 1, Conv, [384, 1, 1]], 63 | [-2, 1, Conv, [384, 1, 1]], 64 | [-1, 1, Conv, [384, 3, 1]], 65 | [-1, 1, Conv, [384, 3, 1]], 66 | [-1, 1, Conv, [384, 3, 1]], 67 | [-1, 1, Conv, [384, 3, 1]], 68 | [-1, 1, Conv, [384, 3, 1]], 69 | [-1, 1, Conv, [384, 3, 1]], 70 | [-1, 1, Conv, [384, 3, 1]], 71 | [-1, 1, Conv, [384, 3, 1]], 72 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 73 | [-1, 1, Conv, [1152, 1, 1]], # 53 74 | 75 | [-1, 1, DownC, [1536]], # 54-P6/64 76 | [-1, 1, Conv, [512, 1, 1]], 77 | [-2, 1, Conv, [512, 1, 1]], 78 | [-1, 1, Conv, [512, 3, 1]], 79 | [-1, 1, Conv, [512, 3, 1]], 80 | [-1, 1, Conv, [512, 3, 1]], 81 | [-1, 1, Conv, [512, 3, 1]], 82 | [-1, 1, Conv, [512, 3, 1]], 83 | [-1, 1, Conv, [512, 3, 1]], 84 | [-1, 1, Conv, [512, 3, 1]], 85 | [-1, 1, Conv, [512, 3, 1]], 86 | [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]], 87 | [-1, 1, Conv, [1536, 1, 1]], # 66 88 | ] 89 | 90 | # yolov7 head 91 | head: 92 | [[-1, 1, SPPCSPC, [768]], # 67 93 | 94 | [-1, 1, Conv, [576, 1, 1]], 95 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 96 | [53, 1, Conv, [576, 1, 1]], # route backbone P5 97 | [[-1, -2], 1, Concat, [1]], 98 | 99 | [-1, 1, Conv, [384, 1, 1]], 100 | [-2, 1, Conv, [384, 1, 1]], 101 | [-1, 1, Conv, [192, 3, 1]], 102 | [-1, 1, Conv, [192, 3, 1]], 103 | [-1, 1, Conv, [192, 3, 1]], 104 | [-1, 1, Conv, [192, 3, 1]], 105 | [-1, 1, Conv, [192, 3, 1]], 106 | [-1, 1, Conv, [192, 3, 1]], 107 | [-1, 1, Conv, [192, 3, 1]], 108 | [-1, 1, Conv, [192, 3, 1]], 109 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 110 | [-1, 1, Conv, [576, 1, 1]], # 83 111 | 112 | [-1, 1, Conv, [384, 1, 1]], 113 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 114 | [40, 1, Conv, [384, 1, 1]], # route backbone P4 115 | [[-1, -2], 1, Concat, [1]], 116 | 117 | [-1, 1, Conv, [256, 1, 1]], 118 | [-2, 1, Conv, [256, 1, 1]], 119 | [-1, 1, Conv, [128, 3, 1]], 120 | [-1, 1, Conv, [128, 3, 1]], 121 | [-1, 1, Conv, [128, 3, 1]], 122 | [-1, 1, Conv, [128, 3, 1]], 123 | [-1, 1, Conv, [128, 3, 1]], 124 | [-1, 1, Conv, [128, 3, 1]], 125 | [-1, 1, Conv, [128, 3, 1]], 126 | [-1, 1, Conv, [128, 3, 1]], 127 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 128 | [-1, 1, Conv, [384, 1, 1]], # 99 129 | 130 | [-1, 1, Conv, [192, 1, 1]], 131 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 132 | [27, 1, Conv, [192, 1, 1]], # route backbone P3 133 | [[-1, -2], 1, Concat, [1]], 134 | 135 | [-1, 1, Conv, [128, 1, 1]], 136 | [-2, 1, Conv, [128, 1, 1]], 137 | [-1, 1, Conv, [64, 3, 1]], 138 | [-1, 1, Conv, [64, 3, 1]], 139 | [-1, 1, Conv, [64, 3, 1]], 140 | [-1, 1, Conv, [64, 3, 1]], 141 | [-1, 1, Conv, [64, 3, 1]], 142 | [-1, 1, Conv, [64, 3, 1]], 143 | [-1, 1, Conv, [64, 3, 1]], 144 | [-1, 1, Conv, [64, 3, 1]], 145 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 146 | [-1, 1, Conv, [192, 1, 1]], # 115 147 | 148 | [-1, 1, DownC, [384]], 149 | [[-1, 99], 1, Concat, [1]], 150 | 151 | [-1, 1, Conv, [256, 1, 1]], 152 | [-2, 1, Conv, [256, 1, 1]], 153 | [-1, 1, Conv, [128, 3, 1]], 154 | [-1, 1, Conv, [128, 3, 1]], 155 | [-1, 1, Conv, [128, 3, 1]], 156 | [-1, 1, Conv, [128, 3, 1]], 157 | [-1, 1, Conv, [128, 3, 1]], 158 | [-1, 1, Conv, [128, 3, 1]], 159 | [-1, 1, Conv, [128, 3, 1]], 160 | [-1, 1, Conv, [128, 3, 1]], 161 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 162 | [-1, 1, Conv, [384, 1, 1]], # 129 163 | 164 | [-1, 1, DownC, [576]], 165 | [[-1, 83], 1, Concat, [1]], 166 | 167 | [-1, 1, Conv, [384, 1, 1]], 168 | [-2, 1, Conv, [384, 1, 1]], 169 | [-1, 1, Conv, [192, 3, 1]], 170 | [-1, 1, Conv, [192, 3, 1]], 171 | [-1, 1, Conv, [192, 3, 1]], 172 | [-1, 1, Conv, [192, 3, 1]], 173 | [-1, 1, Conv, [192, 3, 1]], 174 | [-1, 1, Conv, [192, 3, 1]], 175 | [-1, 1, Conv, [192, 3, 1]], 176 | [-1, 1, Conv, [192, 3, 1]], 177 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 178 | [-1, 1, Conv, [576, 1, 1]], # 143 179 | 180 | [-1, 1, DownC, [768]], 181 | [[-1, 67], 1, Concat, [1]], 182 | 183 | [-1, 1, Conv, [512, 1, 1]], 184 | [-2, 1, Conv, [512, 1, 1]], 185 | [-1, 1, Conv, [256, 3, 1]], 186 | [-1, 1, Conv, [256, 3, 1]], 187 | [-1, 1, Conv, [256, 3, 1]], 188 | [-1, 1, Conv, [256, 3, 1]], 189 | [-1, 1, Conv, [256, 3, 1]], 190 | [-1, 1, Conv, [256, 3, 1]], 191 | [-1, 1, Conv, [256, 3, 1]], 192 | [-1, 1, Conv, [256, 3, 1]], 193 | [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]], 194 | [-1, 1, Conv, [768, 1, 1]], # 157 195 | 196 | [115, 1, Conv, [384, 3, 1]], 197 | [129, 1, Conv, [768, 3, 1]], 198 | [143, 1, Conv, [1152, 3, 1]], 199 | [157, 1, Conv, [1536, 3, 1]], 200 | 201 | [115, 1, Conv, [384, 3, 1]], 202 | [99, 1, Conv, [768, 3, 1]], 203 | [83, 1, Conv, [1152, 3, 1]], 204 | [67, 1, Conv, [1536, 3, 1]], 205 | 206 | [[158,159,160,161,162,163,164,165], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 207 | ] 208 | -------------------------------------------------------------------------------- /cfg/training/yolov7-e6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7 backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [80, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [160]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 29 | [-1, 1, Conv, [160, 1, 1]], # 12 30 | 31 | [-1, 1, DownC, [320]], # 13-P3/8 32 | [-1, 1, Conv, [128, 1, 1]], 33 | [-2, 1, Conv, [128, 1, 1]], 34 | [-1, 1, Conv, [128, 3, 1]], 35 | [-1, 1, Conv, [128, 3, 1]], 36 | [-1, 1, Conv, [128, 3, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 41 | [-1, 1, Conv, [320, 1, 1]], # 23 42 | 43 | [-1, 1, DownC, [640]], # 24-P4/16 44 | [-1, 1, Conv, [256, 1, 1]], 45 | [-2, 1, Conv, [256, 1, 1]], 46 | [-1, 1, Conv, [256, 3, 1]], 47 | [-1, 1, Conv, [256, 3, 1]], 48 | [-1, 1, Conv, [256, 3, 1]], 49 | [-1, 1, Conv, [256, 3, 1]], 50 | [-1, 1, Conv, [256, 3, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 53 | [-1, 1, Conv, [640, 1, 1]], # 34 54 | 55 | [-1, 1, DownC, [960]], # 35-P5/32 56 | [-1, 1, Conv, [384, 1, 1]], 57 | [-2, 1, Conv, [384, 1, 1]], 58 | [-1, 1, Conv, [384, 3, 1]], 59 | [-1, 1, Conv, [384, 3, 1]], 60 | [-1, 1, Conv, [384, 3, 1]], 61 | [-1, 1, Conv, [384, 3, 1]], 62 | [-1, 1, Conv, [384, 3, 1]], 63 | [-1, 1, Conv, [384, 3, 1]], 64 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 65 | [-1, 1, Conv, [960, 1, 1]], # 45 66 | 67 | [-1, 1, DownC, [1280]], # 46-P6/64 68 | [-1, 1, Conv, [512, 1, 1]], 69 | [-2, 1, Conv, [512, 1, 1]], 70 | [-1, 1, Conv, [512, 3, 1]], 71 | [-1, 1, Conv, [512, 3, 1]], 72 | [-1, 1, Conv, [512, 3, 1]], 73 | [-1, 1, Conv, [512, 3, 1]], 74 | [-1, 1, Conv, [512, 3, 1]], 75 | [-1, 1, Conv, [512, 3, 1]], 76 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 77 | [-1, 1, Conv, [1280, 1, 1]], # 56 78 | ] 79 | 80 | # yolov7 head 81 | head: 82 | [[-1, 1, SPPCSPC, [640]], # 57 83 | 84 | [-1, 1, Conv, [480, 1, 1]], 85 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 86 | [45, 1, Conv, [480, 1, 1]], # route backbone P5 87 | [[-1, -2], 1, Concat, [1]], 88 | 89 | [-1, 1, Conv, [384, 1, 1]], 90 | [-2, 1, Conv, [384, 1, 1]], 91 | [-1, 1, Conv, [192, 3, 1]], 92 | [-1, 1, Conv, [192, 3, 1]], 93 | [-1, 1, Conv, [192, 3, 1]], 94 | [-1, 1, Conv, [192, 3, 1]], 95 | [-1, 1, Conv, [192, 3, 1]], 96 | [-1, 1, Conv, [192, 3, 1]], 97 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 98 | [-1, 1, Conv, [480, 1, 1]], # 71 99 | 100 | [-1, 1, Conv, [320, 1, 1]], 101 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 102 | [34, 1, Conv, [320, 1, 1]], # route backbone P4 103 | [[-1, -2], 1, Concat, [1]], 104 | 105 | [-1, 1, Conv, [256, 1, 1]], 106 | [-2, 1, Conv, [256, 1, 1]], 107 | [-1, 1, Conv, [128, 3, 1]], 108 | [-1, 1, Conv, [128, 3, 1]], 109 | [-1, 1, Conv, [128, 3, 1]], 110 | [-1, 1, Conv, [128, 3, 1]], 111 | [-1, 1, Conv, [128, 3, 1]], 112 | [-1, 1, Conv, [128, 3, 1]], 113 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 114 | [-1, 1, Conv, [320, 1, 1]], # 85 115 | 116 | [-1, 1, Conv, [160, 1, 1]], 117 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 118 | [23, 1, Conv, [160, 1, 1]], # route backbone P3 119 | [[-1, -2], 1, Concat, [1]], 120 | 121 | [-1, 1, Conv, [128, 1, 1]], 122 | [-2, 1, Conv, [128, 1, 1]], 123 | [-1, 1, Conv, [64, 3, 1]], 124 | [-1, 1, Conv, [64, 3, 1]], 125 | [-1, 1, Conv, [64, 3, 1]], 126 | [-1, 1, Conv, [64, 3, 1]], 127 | [-1, 1, Conv, [64, 3, 1]], 128 | [-1, 1, Conv, [64, 3, 1]], 129 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 130 | [-1, 1, Conv, [160, 1, 1]], # 99 131 | 132 | [-1, 1, DownC, [320]], 133 | [[-1, 85], 1, Concat, [1]], 134 | 135 | [-1, 1, Conv, [256, 1, 1]], 136 | [-2, 1, Conv, [256, 1, 1]], 137 | [-1, 1, Conv, [128, 3, 1]], 138 | [-1, 1, Conv, [128, 3, 1]], 139 | [-1, 1, Conv, [128, 3, 1]], 140 | [-1, 1, Conv, [128, 3, 1]], 141 | [-1, 1, Conv, [128, 3, 1]], 142 | [-1, 1, Conv, [128, 3, 1]], 143 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 144 | [-1, 1, Conv, [320, 1, 1]], # 111 145 | 146 | [-1, 1, DownC, [480]], 147 | [[-1, 71], 1, Concat, [1]], 148 | 149 | [-1, 1, Conv, [384, 1, 1]], 150 | [-2, 1, Conv, [384, 1, 1]], 151 | [-1, 1, Conv, [192, 3, 1]], 152 | [-1, 1, Conv, [192, 3, 1]], 153 | [-1, 1, Conv, [192, 3, 1]], 154 | [-1, 1, Conv, [192, 3, 1]], 155 | [-1, 1, Conv, [192, 3, 1]], 156 | [-1, 1, Conv, [192, 3, 1]], 157 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 158 | [-1, 1, Conv, [480, 1, 1]], # 123 159 | 160 | [-1, 1, DownC, [640]], 161 | [[-1, 57], 1, Concat, [1]], 162 | 163 | [-1, 1, Conv, [512, 1, 1]], 164 | [-2, 1, Conv, [512, 1, 1]], 165 | [-1, 1, Conv, [256, 3, 1]], 166 | [-1, 1, Conv, [256, 3, 1]], 167 | [-1, 1, Conv, [256, 3, 1]], 168 | [-1, 1, Conv, [256, 3, 1]], 169 | [-1, 1, Conv, [256, 3, 1]], 170 | [-1, 1, Conv, [256, 3, 1]], 171 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 172 | [-1, 1, Conv, [640, 1, 1]], # 135 173 | 174 | [99, 1, Conv, [320, 3, 1]], 175 | [111, 1, Conv, [640, 3, 1]], 176 | [123, 1, Conv, [960, 3, 1]], 177 | [135, 1, Conv, [1280, 3, 1]], 178 | 179 | [99, 1, Conv, [320, 3, 1]], 180 | [85, 1, Conv, [640, 3, 1]], 181 | [71, 1, Conv, [960, 3, 1]], 182 | [57, 1, Conv, [1280, 3, 1]], 183 | 184 | [[136,137,138,139,140,141,142,143], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 185 | ] 186 | -------------------------------------------------------------------------------- /cfg/training/yolov7-e6e.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7 backbone 14 | backbone: 15 | # [from, number, module, args], 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [80, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, DownC, [160]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 29 | [-1, 1, Conv, [160, 1, 1]], # 12 30 | [-11, 1, Conv, [64, 1, 1]], 31 | [-12, 1, Conv, [64, 1, 1]], 32 | [-1, 1, Conv, [64, 3, 1]], 33 | [-1, 1, Conv, [64, 3, 1]], 34 | [-1, 1, Conv, [64, 3, 1]], 35 | [-1, 1, Conv, [64, 3, 1]], 36 | [-1, 1, Conv, [64, 3, 1]], 37 | [-1, 1, Conv, [64, 3, 1]], 38 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 39 | [-1, 1, Conv, [160, 1, 1]], # 22 40 | [[-1, -11], 1, Shortcut, [1]], # 23 41 | 42 | [-1, 1, DownC, [320]], # 24-P3/8 43 | [-1, 1, Conv, [128, 1, 1]], 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, Conv, [128, 3, 1]], 46 | [-1, 1, Conv, [128, 3, 1]], 47 | [-1, 1, Conv, [128, 3, 1]], 48 | [-1, 1, Conv, [128, 3, 1]], 49 | [-1, 1, Conv, [128, 3, 1]], 50 | [-1, 1, Conv, [128, 3, 1]], 51 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 52 | [-1, 1, Conv, [320, 1, 1]], # 34 53 | [-11, 1, Conv, [128, 1, 1]], 54 | [-12, 1, Conv, [128, 1, 1]], 55 | [-1, 1, Conv, [128, 3, 1]], 56 | [-1, 1, Conv, [128, 3, 1]], 57 | [-1, 1, Conv, [128, 3, 1]], 58 | [-1, 1, Conv, [128, 3, 1]], 59 | [-1, 1, Conv, [128, 3, 1]], 60 | [-1, 1, Conv, [128, 3, 1]], 61 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 62 | [-1, 1, Conv, [320, 1, 1]], # 44 63 | [[-1, -11], 1, Shortcut, [1]], # 45 64 | 65 | [-1, 1, DownC, [640]], # 46-P4/16 66 | [-1, 1, Conv, [256, 1, 1]], 67 | [-2, 1, Conv, [256, 1, 1]], 68 | [-1, 1, Conv, [256, 3, 1]], 69 | [-1, 1, Conv, [256, 3, 1]], 70 | [-1, 1, Conv, [256, 3, 1]], 71 | [-1, 1, Conv, [256, 3, 1]], 72 | [-1, 1, Conv, [256, 3, 1]], 73 | [-1, 1, Conv, [256, 3, 1]], 74 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 75 | [-1, 1, Conv, [640, 1, 1]], # 56 76 | [-11, 1, Conv, [256, 1, 1]], 77 | [-12, 1, Conv, [256, 1, 1]], 78 | [-1, 1, Conv, [256, 3, 1]], 79 | [-1, 1, Conv, [256, 3, 1]], 80 | [-1, 1, Conv, [256, 3, 1]], 81 | [-1, 1, Conv, [256, 3, 1]], 82 | [-1, 1, Conv, [256, 3, 1]], 83 | [-1, 1, Conv, [256, 3, 1]], 84 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 85 | [-1, 1, Conv, [640, 1, 1]], # 66 86 | [[-1, -11], 1, Shortcut, [1]], # 67 87 | 88 | [-1, 1, DownC, [960]], # 68-P5/32 89 | [-1, 1, Conv, [384, 1, 1]], 90 | [-2, 1, Conv, [384, 1, 1]], 91 | [-1, 1, Conv, [384, 3, 1]], 92 | [-1, 1, Conv, [384, 3, 1]], 93 | [-1, 1, Conv, [384, 3, 1]], 94 | [-1, 1, Conv, [384, 3, 1]], 95 | [-1, 1, Conv, [384, 3, 1]], 96 | [-1, 1, Conv, [384, 3, 1]], 97 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 98 | [-1, 1, Conv, [960, 1, 1]], # 78 99 | [-11, 1, Conv, [384, 1, 1]], 100 | [-12, 1, Conv, [384, 1, 1]], 101 | [-1, 1, Conv, [384, 3, 1]], 102 | [-1, 1, Conv, [384, 3, 1]], 103 | [-1, 1, Conv, [384, 3, 1]], 104 | [-1, 1, Conv, [384, 3, 1]], 105 | [-1, 1, Conv, [384, 3, 1]], 106 | [-1, 1, Conv, [384, 3, 1]], 107 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 108 | [-1, 1, Conv, [960, 1, 1]], # 88 109 | [[-1, -11], 1, Shortcut, [1]], # 89 110 | 111 | [-1, 1, DownC, [1280]], # 90-P6/64 112 | [-1, 1, Conv, [512, 1, 1]], 113 | [-2, 1, Conv, [512, 1, 1]], 114 | [-1, 1, Conv, [512, 3, 1]], 115 | [-1, 1, Conv, [512, 3, 1]], 116 | [-1, 1, Conv, [512, 3, 1]], 117 | [-1, 1, Conv, [512, 3, 1]], 118 | [-1, 1, Conv, [512, 3, 1]], 119 | [-1, 1, Conv, [512, 3, 1]], 120 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 121 | [-1, 1, Conv, [1280, 1, 1]], # 100 122 | [-11, 1, Conv, [512, 1, 1]], 123 | [-12, 1, Conv, [512, 1, 1]], 124 | [-1, 1, Conv, [512, 3, 1]], 125 | [-1, 1, Conv, [512, 3, 1]], 126 | [-1, 1, Conv, [512, 3, 1]], 127 | [-1, 1, Conv, [512, 3, 1]], 128 | [-1, 1, Conv, [512, 3, 1]], 129 | [-1, 1, Conv, [512, 3, 1]], 130 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 131 | [-1, 1, Conv, [1280, 1, 1]], # 110 132 | [[-1, -11], 1, Shortcut, [1]], # 111 133 | ] 134 | 135 | # yolov7 head 136 | head: 137 | [[-1, 1, SPPCSPC, [640]], # 112 138 | 139 | [-1, 1, Conv, [480, 1, 1]], 140 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 141 | [89, 1, Conv, [480, 1, 1]], # route backbone P5 142 | [[-1, -2], 1, Concat, [1]], 143 | 144 | [-1, 1, Conv, [384, 1, 1]], 145 | [-2, 1, Conv, [384, 1, 1]], 146 | [-1, 1, Conv, [192, 3, 1]], 147 | [-1, 1, Conv, [192, 3, 1]], 148 | [-1, 1, Conv, [192, 3, 1]], 149 | [-1, 1, Conv, [192, 3, 1]], 150 | [-1, 1, Conv, [192, 3, 1]], 151 | [-1, 1, Conv, [192, 3, 1]], 152 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 153 | [-1, 1, Conv, [480, 1, 1]], # 126 154 | [-11, 1, Conv, [384, 1, 1]], 155 | [-12, 1, Conv, [384, 1, 1]], 156 | [-1, 1, Conv, [192, 3, 1]], 157 | [-1, 1, Conv, [192, 3, 1]], 158 | [-1, 1, Conv, [192, 3, 1]], 159 | [-1, 1, Conv, [192, 3, 1]], 160 | [-1, 1, Conv, [192, 3, 1]], 161 | [-1, 1, Conv, [192, 3, 1]], 162 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 163 | [-1, 1, Conv, [480, 1, 1]], # 136 164 | [[-1, -11], 1, Shortcut, [1]], # 137 165 | 166 | [-1, 1, Conv, [320, 1, 1]], 167 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 168 | [67, 1, Conv, [320, 1, 1]], # route backbone P4 169 | [[-1, -2], 1, Concat, [1]], 170 | 171 | [-1, 1, Conv, [256, 1, 1]], 172 | [-2, 1, Conv, [256, 1, 1]], 173 | [-1, 1, Conv, [128, 3, 1]], 174 | [-1, 1, Conv, [128, 3, 1]], 175 | [-1, 1, Conv, [128, 3, 1]], 176 | [-1, 1, Conv, [128, 3, 1]], 177 | [-1, 1, Conv, [128, 3, 1]], 178 | [-1, 1, Conv, [128, 3, 1]], 179 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 180 | [-1, 1, Conv, [320, 1, 1]], # 151 181 | [-11, 1, Conv, [256, 1, 1]], 182 | [-12, 1, Conv, [256, 1, 1]], 183 | [-1, 1, Conv, [128, 3, 1]], 184 | [-1, 1, Conv, [128, 3, 1]], 185 | [-1, 1, Conv, [128, 3, 1]], 186 | [-1, 1, Conv, [128, 3, 1]], 187 | [-1, 1, Conv, [128, 3, 1]], 188 | [-1, 1, Conv, [128, 3, 1]], 189 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 190 | [-1, 1, Conv, [320, 1, 1]], # 161 191 | [[-1, -11], 1, Shortcut, [1]], # 162 192 | 193 | [-1, 1, Conv, [160, 1, 1]], 194 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 195 | [45, 1, Conv, [160, 1, 1]], # route backbone P3 196 | [[-1, -2], 1, Concat, [1]], 197 | 198 | [-1, 1, Conv, [128, 1, 1]], 199 | [-2, 1, Conv, [128, 1, 1]], 200 | [-1, 1, Conv, [64, 3, 1]], 201 | [-1, 1, Conv, [64, 3, 1]], 202 | [-1, 1, Conv, [64, 3, 1]], 203 | [-1, 1, Conv, [64, 3, 1]], 204 | [-1, 1, Conv, [64, 3, 1]], 205 | [-1, 1, Conv, [64, 3, 1]], 206 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 207 | [-1, 1, Conv, [160, 1, 1]], # 176 208 | [-11, 1, Conv, [128, 1, 1]], 209 | [-12, 1, Conv, [128, 1, 1]], 210 | [-1, 1, Conv, [64, 3, 1]], 211 | [-1, 1, Conv, [64, 3, 1]], 212 | [-1, 1, Conv, [64, 3, 1]], 213 | [-1, 1, Conv, [64, 3, 1]], 214 | [-1, 1, Conv, [64, 3, 1]], 215 | [-1, 1, Conv, [64, 3, 1]], 216 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 217 | [-1, 1, Conv, [160, 1, 1]], # 186 218 | [[-1, -11], 1, Shortcut, [1]], # 187 219 | 220 | [-1, 1, DownC, [320]], 221 | [[-1, 162], 1, Concat, [1]], 222 | 223 | [-1, 1, Conv, [256, 1, 1]], 224 | [-2, 1, Conv, [256, 1, 1]], 225 | [-1, 1, Conv, [128, 3, 1]], 226 | [-1, 1, Conv, [128, 3, 1]], 227 | [-1, 1, Conv, [128, 3, 1]], 228 | [-1, 1, Conv, [128, 3, 1]], 229 | [-1, 1, Conv, [128, 3, 1]], 230 | [-1, 1, Conv, [128, 3, 1]], 231 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 232 | [-1, 1, Conv, [320, 1, 1]], # 199 233 | [-11, 1, Conv, [256, 1, 1]], 234 | [-12, 1, Conv, [256, 1, 1]], 235 | [-1, 1, Conv, [128, 3, 1]], 236 | [-1, 1, Conv, [128, 3, 1]], 237 | [-1, 1, Conv, [128, 3, 1]], 238 | [-1, 1, Conv, [128, 3, 1]], 239 | [-1, 1, Conv, [128, 3, 1]], 240 | [-1, 1, Conv, [128, 3, 1]], 241 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 242 | [-1, 1, Conv, [320, 1, 1]], # 209 243 | [[-1, -11], 1, Shortcut, [1]], # 210 244 | 245 | [-1, 1, DownC, [480]], 246 | [[-1, 137], 1, Concat, [1]], 247 | 248 | [-1, 1, Conv, [384, 1, 1]], 249 | [-2, 1, Conv, [384, 1, 1]], 250 | [-1, 1, Conv, [192, 3, 1]], 251 | [-1, 1, Conv, [192, 3, 1]], 252 | [-1, 1, Conv, [192, 3, 1]], 253 | [-1, 1, Conv, [192, 3, 1]], 254 | [-1, 1, Conv, [192, 3, 1]], 255 | [-1, 1, Conv, [192, 3, 1]], 256 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 257 | [-1, 1, Conv, [480, 1, 1]], # 222 258 | [-11, 1, Conv, [384, 1, 1]], 259 | [-12, 1, Conv, [384, 1, 1]], 260 | [-1, 1, Conv, [192, 3, 1]], 261 | [-1, 1, Conv, [192, 3, 1]], 262 | [-1, 1, Conv, [192, 3, 1]], 263 | [-1, 1, Conv, [192, 3, 1]], 264 | [-1, 1, Conv, [192, 3, 1]], 265 | [-1, 1, Conv, [192, 3, 1]], 266 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 267 | [-1, 1, Conv, [480, 1, 1]], # 232 268 | [[-1, -11], 1, Shortcut, [1]], # 233 269 | 270 | [-1, 1, DownC, [640]], 271 | [[-1, 112], 1, Concat, [1]], 272 | 273 | [-1, 1, Conv, [512, 1, 1]], 274 | [-2, 1, Conv, [512, 1, 1]], 275 | [-1, 1, Conv, [256, 3, 1]], 276 | [-1, 1, Conv, [256, 3, 1]], 277 | [-1, 1, Conv, [256, 3, 1]], 278 | [-1, 1, Conv, [256, 3, 1]], 279 | [-1, 1, Conv, [256, 3, 1]], 280 | [-1, 1, Conv, [256, 3, 1]], 281 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 282 | [-1, 1, Conv, [640, 1, 1]], # 245 283 | [-11, 1, Conv, [512, 1, 1]], 284 | [-12, 1, Conv, [512, 1, 1]], 285 | [-1, 1, Conv, [256, 3, 1]], 286 | [-1, 1, Conv, [256, 3, 1]], 287 | [-1, 1, Conv, [256, 3, 1]], 288 | [-1, 1, Conv, [256, 3, 1]], 289 | [-1, 1, Conv, [256, 3, 1]], 290 | [-1, 1, Conv, [256, 3, 1]], 291 | [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]], 292 | [-1, 1, Conv, [640, 1, 1]], # 255 293 | [[-1, -11], 1, Shortcut, [1]], # 256 294 | 295 | [187, 1, Conv, [320, 3, 1]], 296 | [210, 1, Conv, [640, 3, 1]], 297 | [233, 1, Conv, [960, 3, 1]], 298 | [256, 1, Conv, [1280, 3, 1]], 299 | 300 | [186, 1, Conv, [320, 3, 1]], 301 | [161, 1, Conv, [640, 3, 1]], 302 | [136, 1, Conv, [960, 3, 1]], 303 | [112, 1, Conv, [1280, 3, 1]], 304 | 305 | [[257,258,259,260,261,262,263,264], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 306 | ] 307 | -------------------------------------------------------------------------------- /cfg/training/yolov7-tiny-relu.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # yolov7-tiny backbone 13 | backbone: 14 | # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True 15 | [[-1, 1, Conv, [32, 3, 2, None, 1, nn.ReLU]], # 0-P1/2 16 | 17 | [-1, 1, Conv, [64, 3, 2, None, 1, nn.ReLU]], # 1-P2/4 18 | 19 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.ReLU]], 20 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.ReLU]], 21 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.ReLU]], 22 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.ReLU]], 23 | [[-1, -2, -3, -4], 1, Concat, [1]], 24 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], # 7 25 | 26 | [-1, 1, MP, []], # 8-P3/8 27 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 28 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 29 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 30 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 31 | [[-1, -2, -3, -4], 1, Concat, [1]], 32 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], # 14 33 | 34 | [-1, 1, MP, []], # 15-P4/16 35 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], 36 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], 37 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.ReLU]], 38 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.ReLU]], 39 | [[-1, -2, -3, -4], 1, Concat, [1]], 40 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], # 21 41 | 42 | [-1, 1, MP, []], # 22-P5/32 43 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], 44 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], 45 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.ReLU]], 46 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.ReLU]], 47 | [[-1, -2, -3, -4], 1, Concat, [1]], 48 | [-1, 1, Conv, [512, 1, 1, None, 1, nn.ReLU]], # 28 49 | ] 50 | 51 | # yolov7-tiny head 52 | head: 53 | [[-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], 54 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], 55 | [-1, 1, SP, [5]], 56 | [-2, 1, SP, [9]], 57 | [-3, 1, SP, [13]], 58 | [[-1, -2, -3, -4], 1, Concat, [1]], 59 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], 60 | [[-1, -7], 1, Concat, [1]], 61 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], # 37 62 | 63 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], 64 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 65 | [21, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], # route backbone P4 66 | [[-1, -2], 1, Concat, [1]], 67 | 68 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 69 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 70 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 71 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 72 | [[-1, -2, -3, -4], 1, Concat, [1]], 73 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], # 47 74 | 75 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 76 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 77 | [14, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], # route backbone P3 78 | [[-1, -2], 1, Concat, [1]], 79 | 80 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.ReLU]], 81 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.ReLU]], 82 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.ReLU]], 83 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.ReLU]], 84 | [[-1, -2, -3, -4], 1, Concat, [1]], 85 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], # 57 86 | 87 | [-1, 1, Conv, [128, 3, 2, None, 1, nn.ReLU]], 88 | [[-1, 47], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 91 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.ReLU]], 92 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 93 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.ReLU]], 94 | [[-1, -2, -3, -4], 1, Concat, [1]], 95 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], # 65 96 | 97 | [-1, 1, Conv, [256, 3, 2, None, 1, nn.ReLU]], 98 | [[-1, 37], 1, Concat, [1]], 99 | 100 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], 101 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.ReLU]], 102 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.ReLU]], 103 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.ReLU]], 104 | [[-1, -2, -3, -4], 1, Concat, [1]], 105 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.ReLU]], # 73 106 | 107 | [57, 1, Conv, [128, 3, 1, None, 1, nn.ReLU]], 108 | [65, 1, Conv, [256, 3, 1, None, 1, nn.ReLU]], 109 | [73, 1, Conv, [512, 3, 1, None, 1, nn.ReLU]], 110 | 111 | [[74,75,76], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 112 | ] 113 | -------------------------------------------------------------------------------- /cfg/training/yolov7-tiny.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # yolov7-tiny backbone 13 | backbone: 14 | # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True 15 | [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 0-P1/2 16 | 17 | [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 1-P2/4 18 | 19 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 20 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 21 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 22 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 23 | [[-1, -2, -3, -4], 1, Concat, [1]], 24 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 7 25 | 26 | [-1, 1, MP, []], # 8-P3/8 27 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 28 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 29 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 30 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 31 | [[-1, -2, -3, -4], 1, Concat, [1]], 32 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 14 33 | 34 | [-1, 1, MP, []], # 15-P4/16 35 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 36 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 37 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 38 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 39 | [[-1, -2, -3, -4], 1, Concat, [1]], 40 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 21 41 | 42 | [-1, 1, MP, []], # 22-P5/32 43 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 44 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 45 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 46 | [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 47 | [[-1, -2, -3, -4], 1, Concat, [1]], 48 | [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 28 49 | ] 50 | 51 | # yolov7-tiny head 52 | head: 53 | [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 54 | [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 55 | [-1, 1, SP, [5]], 56 | [-2, 1, SP, [9]], 57 | [-3, 1, SP, [13]], 58 | [[-1, -2, -3, -4], 1, Concat, [1]], 59 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 60 | [[-1, -7], 1, Concat, [1]], 61 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 37 62 | 63 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 64 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 65 | [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4 66 | [[-1, -2], 1, Concat, [1]], 67 | 68 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 69 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 70 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 71 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 72 | [[-1, -2, -3, -4], 1, Concat, [1]], 73 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 47 74 | 75 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 76 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 77 | [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3 78 | [[-1, -2], 1, Concat, [1]], 79 | 80 | [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 81 | [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 82 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 83 | [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 84 | [[-1, -2, -3, -4], 1, Concat, [1]], 85 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 57 86 | 87 | [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]], 88 | [[-1, 47], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 91 | [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 92 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 93 | [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 94 | [[-1, -2, -3, -4], 1, Concat, [1]], 95 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 65 96 | 97 | [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]], 98 | [[-1, 37], 1, Concat, [1]], 99 | 100 | [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 101 | [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], 102 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 103 | [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 104 | [[-1, -2, -3, -4], 1, Concat, [1]], 105 | [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 73 106 | 107 | [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 108 | [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 109 | [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]], 110 | 111 | [[74,75,76], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 112 | ] 113 | -------------------------------------------------------------------------------- /cfg/training/yolov7-w6.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [ 19,27, 44,40, 38,94 ] # P3/8 9 | - [ 96,68, 86,152, 180,137 ] # P4/16 10 | - [ 140,301, 303,264, 238,542 ] # P5/32 11 | - [ 436,615, 739,380, 925,792 ] # P6/64 12 | 13 | # yolov7 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, ReOrg, []], # 0 17 | [-1, 1, Conv, [64, 3, 1]], # 1-P1/2 18 | 19 | [-1, 1, Conv, [128, 3, 2]], # 2-P2/4 20 | [-1, 1, Conv, [64, 1, 1]], 21 | [-2, 1, Conv, [64, 1, 1]], 22 | [-1, 1, Conv, [64, 3, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [[-1, -3, -5, -6], 1, Concat, [1]], 27 | [-1, 1, Conv, [128, 1, 1]], # 10 28 | 29 | [-1, 1, Conv, [256, 3, 2]], # 11-P3/8 30 | [-1, 1, Conv, [128, 1, 1]], 31 | [-2, 1, Conv, [128, 1, 1]], 32 | [-1, 1, Conv, [128, 3, 1]], 33 | [-1, 1, Conv, [128, 3, 1]], 34 | [-1, 1, Conv, [128, 3, 1]], 35 | [-1, 1, Conv, [128, 3, 1]], 36 | [[-1, -3, -5, -6], 1, Concat, [1]], 37 | [-1, 1, Conv, [256, 1, 1]], # 19 38 | 39 | [-1, 1, Conv, [512, 3, 2]], # 20-P4/16 40 | [-1, 1, Conv, [256, 1, 1]], 41 | [-2, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [256, 3, 1]], 43 | [-1, 1, Conv, [256, 3, 1]], 44 | [-1, 1, Conv, [256, 3, 1]], 45 | [-1, 1, Conv, [256, 3, 1]], 46 | [[-1, -3, -5, -6], 1, Concat, [1]], 47 | [-1, 1, Conv, [512, 1, 1]], # 28 48 | 49 | [-1, 1, Conv, [768, 3, 2]], # 29-P5/32 50 | [-1, 1, Conv, [384, 1, 1]], 51 | [-2, 1, Conv, [384, 1, 1]], 52 | [-1, 1, Conv, [384, 3, 1]], 53 | [-1, 1, Conv, [384, 3, 1]], 54 | [-1, 1, Conv, [384, 3, 1]], 55 | [-1, 1, Conv, [384, 3, 1]], 56 | [[-1, -3, -5, -6], 1, Concat, [1]], 57 | [-1, 1, Conv, [768, 1, 1]], # 37 58 | 59 | [-1, 1, Conv, [1024, 3, 2]], # 38-P6/64 60 | [-1, 1, Conv, [512, 1, 1]], 61 | [-2, 1, Conv, [512, 1, 1]], 62 | [-1, 1, Conv, [512, 3, 1]], 63 | [-1, 1, Conv, [512, 3, 1]], 64 | [-1, 1, Conv, [512, 3, 1]], 65 | [-1, 1, Conv, [512, 3, 1]], 66 | [[-1, -3, -5, -6], 1, Concat, [1]], 67 | [-1, 1, Conv, [1024, 1, 1]], # 46 68 | ] 69 | 70 | # yolov7 head 71 | head: 72 | [[-1, 1, SPPCSPC, [512]], # 47 73 | 74 | [-1, 1, Conv, [384, 1, 1]], 75 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 76 | [37, 1, Conv, [384, 1, 1]], # route backbone P5 77 | [[-1, -2], 1, Concat, [1]], 78 | 79 | [-1, 1, Conv, [384, 1, 1]], 80 | [-2, 1, Conv, [384, 1, 1]], 81 | [-1, 1, Conv, [192, 3, 1]], 82 | [-1, 1, Conv, [192, 3, 1]], 83 | [-1, 1, Conv, [192, 3, 1]], 84 | [-1, 1, Conv, [192, 3, 1]], 85 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 86 | [-1, 1, Conv, [384, 1, 1]], # 59 87 | 88 | [-1, 1, Conv, [256, 1, 1]], 89 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 90 | [28, 1, Conv, [256, 1, 1]], # route backbone P4 91 | [[-1, -2], 1, Concat, [1]], 92 | 93 | [-1, 1, Conv, [256, 1, 1]], 94 | [-2, 1, Conv, [256, 1, 1]], 95 | [-1, 1, Conv, [128, 3, 1]], 96 | [-1, 1, Conv, [128, 3, 1]], 97 | [-1, 1, Conv, [128, 3, 1]], 98 | [-1, 1, Conv, [128, 3, 1]], 99 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 100 | [-1, 1, Conv, [256, 1, 1]], # 71 101 | 102 | [-1, 1, Conv, [128, 1, 1]], 103 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 104 | [19, 1, Conv, [128, 1, 1]], # route backbone P3 105 | [[-1, -2], 1, Concat, [1]], 106 | 107 | [-1, 1, Conv, [128, 1, 1]], 108 | [-2, 1, Conv, [128, 1, 1]], 109 | [-1, 1, Conv, [64, 3, 1]], 110 | [-1, 1, Conv, [64, 3, 1]], 111 | [-1, 1, Conv, [64, 3, 1]], 112 | [-1, 1, Conv, [64, 3, 1]], 113 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 114 | [-1, 1, Conv, [128, 1, 1]], # 83 115 | 116 | [-1, 1, Conv, [256, 3, 2]], 117 | [[-1, 71], 1, Concat, [1]], # cat 118 | 119 | [-1, 1, Conv, [256, 1, 1]], 120 | [-2, 1, Conv, [256, 1, 1]], 121 | [-1, 1, Conv, [128, 3, 1]], 122 | [-1, 1, Conv, [128, 3, 1]], 123 | [-1, 1, Conv, [128, 3, 1]], 124 | [-1, 1, Conv, [128, 3, 1]], 125 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 126 | [-1, 1, Conv, [256, 1, 1]], # 93 127 | 128 | [-1, 1, Conv, [384, 3, 2]], 129 | [[-1, 59], 1, Concat, [1]], # cat 130 | 131 | [-1, 1, Conv, [384, 1, 1]], 132 | [-2, 1, Conv, [384, 1, 1]], 133 | [-1, 1, Conv, [192, 3, 1]], 134 | [-1, 1, Conv, [192, 3, 1]], 135 | [-1, 1, Conv, [192, 3, 1]], 136 | [-1, 1, Conv, [192, 3, 1]], 137 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 138 | [-1, 1, Conv, [384, 1, 1]], # 103 139 | 140 | [-1, 1, Conv, [512, 3, 2]], 141 | [[-1, 47], 1, Concat, [1]], # cat 142 | 143 | [-1, 1, Conv, [512, 1, 1]], 144 | [-2, 1, Conv, [512, 1, 1]], 145 | [-1, 1, Conv, [256, 3, 1]], 146 | [-1, 1, Conv, [256, 3, 1]], 147 | [-1, 1, Conv, [256, 3, 1]], 148 | [-1, 1, Conv, [256, 3, 1]], 149 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 150 | [-1, 1, Conv, [512, 1, 1]], # 113 151 | 152 | [83, 1, Conv, [256, 3, 1]], 153 | [93, 1, Conv, [512, 3, 1]], 154 | [103, 1, Conv, [768, 3, 1]], 155 | [113, 1, Conv, [1024, 3, 1]], 156 | 157 | [83, 1, Conv, [320, 3, 1]], 158 | [71, 1, Conv, [640, 3, 1]], 159 | [59, 1, Conv, [960, 3, 1]], 160 | [47, 1, Conv, [1280, 3, 1]], 161 | 162 | [[114,115,116,117,118,119,120,121], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6) 163 | ] 164 | -------------------------------------------------------------------------------- /cfg/training/yolov7.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # yolov7 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | 17 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 18 | [-1, 1, Conv, [64, 3, 1]], 19 | 20 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 21 | [-1, 1, Conv, [64, 1, 1]], 22 | [-2, 1, Conv, [64, 1, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [[-1, -3, -5, -6], 1, Concat, [1]], 28 | [-1, 1, Conv, [256, 1, 1]], # 11 29 | 30 | [-1, 1, MP, []], 31 | [-1, 1, Conv, [128, 1, 1]], 32 | [-3, 1, Conv, [128, 1, 1]], 33 | [-1, 1, Conv, [128, 3, 2]], 34 | [[-1, -3], 1, Concat, [1]], # 16-P3/8 35 | [-1, 1, Conv, [128, 1, 1]], 36 | [-2, 1, Conv, [128, 1, 1]], 37 | [-1, 1, Conv, [128, 3, 1]], 38 | [-1, 1, Conv, [128, 3, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [[-1, -3, -5, -6], 1, Concat, [1]], 42 | [-1, 1, Conv, [512, 1, 1]], # 24 43 | 44 | [-1, 1, MP, []], 45 | [-1, 1, Conv, [256, 1, 1]], 46 | [-3, 1, Conv, [256, 1, 1]], 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, -3], 1, Concat, [1]], # 29-P4/16 49 | [-1, 1, Conv, [256, 1, 1]], 50 | [-2, 1, Conv, [256, 1, 1]], 51 | [-1, 1, Conv, [256, 3, 1]], 52 | [-1, 1, Conv, [256, 3, 1]], 53 | [-1, 1, Conv, [256, 3, 1]], 54 | [-1, 1, Conv, [256, 3, 1]], 55 | [[-1, -3, -5, -6], 1, Concat, [1]], 56 | [-1, 1, Conv, [1024, 1, 1]], # 37 57 | 58 | [-1, 1, MP, []], 59 | [-1, 1, Conv, [512, 1, 1]], 60 | [-3, 1, Conv, [512, 1, 1]], 61 | [-1, 1, Conv, [512, 3, 2]], 62 | [[-1, -3], 1, Concat, [1]], # 42-P5/32 63 | [-1, 1, Conv, [256, 1, 1]], 64 | [-2, 1, Conv, [256, 1, 1]], 65 | [-1, 1, Conv, [256, 3, 1]], 66 | [-1, 1, Conv, [256, 3, 1]], 67 | [-1, 1, Conv, [256, 3, 1]], 68 | [-1, 1, Conv, [256, 3, 1]], 69 | [[-1, -3, -5, -6], 1, Concat, [1]], 70 | [-1, 1, Conv, [1024, 1, 1]], # 50 71 | ] 72 | 73 | # yolov7 head 74 | head: 75 | [[-1, 1, SPPCSPC, [512]], # 51 76 | 77 | [-1, 1, Conv, [256, 1, 1]], 78 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 79 | [37, 1, Conv, [256, 1, 1]], # route backbone P4 80 | [[-1, -2], 1, Concat, [1]], 81 | 82 | [-1, 1, Conv, [256, 1, 1]], 83 | [-2, 1, Conv, [256, 1, 1]], 84 | [-1, 1, Conv, [128, 3, 1]], 85 | [-1, 1, Conv, [128, 3, 1]], 86 | [-1, 1, Conv, [128, 3, 1]], 87 | [-1, 1, Conv, [128, 3, 1]], 88 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 89 | [-1, 1, Conv, [256, 1, 1]], # 63 90 | 91 | [-1, 1, Conv, [128, 1, 1]], 92 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 93 | [24, 1, Conv, [128, 1, 1]], # route backbone P3 94 | [[-1, -2], 1, Concat, [1]], 95 | 96 | [-1, 1, Conv, [128, 1, 1]], 97 | [-2, 1, Conv, [128, 1, 1]], 98 | [-1, 1, Conv, [64, 3, 1]], 99 | [-1, 1, Conv, [64, 3, 1]], 100 | [-1, 1, Conv, [64, 3, 1]], 101 | [-1, 1, Conv, [64, 3, 1]], 102 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 103 | [-1, 1, Conv, [128, 1, 1]], # 75 104 | 105 | [-1, 1, MP, []], 106 | [-1, 1, Conv, [128, 1, 1]], 107 | [-3, 1, Conv, [128, 1, 1]], 108 | [-1, 1, Conv, [128, 3, 2]], 109 | [[-1, -3, 63], 1, Concat, [1]], 110 | 111 | [-1, 1, Conv, [256, 1, 1]], 112 | [-2, 1, Conv, [256, 1, 1]], 113 | [-1, 1, Conv, [128, 3, 1]], 114 | [-1, 1, Conv, [128, 3, 1]], 115 | [-1, 1, Conv, [128, 3, 1]], 116 | [-1, 1, Conv, [128, 3, 1]], 117 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 118 | [-1, 1, Conv, [256, 1, 1]], # 88 119 | 120 | [-1, 1, MP, []], 121 | [-1, 1, Conv, [256, 1, 1]], 122 | [-3, 1, Conv, [256, 1, 1]], 123 | [-1, 1, Conv, [256, 3, 2]], 124 | [[-1, -3, 51], 1, Concat, [1]], 125 | 126 | [-1, 1, Conv, [512, 1, 1]], 127 | [-2, 1, Conv, [512, 1, 1]], 128 | [-1, 1, Conv, [256, 3, 1]], 129 | [-1, 1, Conv, [256, 3, 1]], 130 | [-1, 1, Conv, [256, 3, 1]], 131 | [-1, 1, Conv, [256, 3, 1]], 132 | [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], 133 | [-1, 1, Conv, [512, 1, 1]], # 101 134 | 135 | [75, 1, RepConv, [256, 3, 1]], 136 | [88, 1, RepConv, [512, 3, 1]], 137 | [101, 1, RepConv, [1024, 3, 1]], 138 | 139 | [[102,103,104], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 140 | ] 141 | -------------------------------------------------------------------------------- /cfg/training/yolov7x.yaml: -------------------------------------------------------------------------------- 1 | # parameters 2 | nc: 80 # number of classes 3 | depth_multiple: 1.0 # model depth multiple 4 | width_multiple: 1.0 # layer channel multiple 5 | 6 | # anchors 7 | anchors: 8 | - [12,16, 19,36, 40,28] # P3/8 9 | - [36,75, 76,55, 72,146] # P4/16 10 | - [142,110, 192,243, 459,401] # P5/32 11 | 12 | # yolov7 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [40, 3, 1]], # 0 16 | 17 | [-1, 1, Conv, [80, 3, 2]], # 1-P1/2 18 | [-1, 1, Conv, [80, 3, 1]], 19 | 20 | [-1, 1, Conv, [160, 3, 2]], # 3-P2/4 21 | [-1, 1, Conv, [64, 1, 1]], 22 | [-2, 1, Conv, [64, 1, 1]], 23 | [-1, 1, Conv, [64, 3, 1]], 24 | [-1, 1, Conv, [64, 3, 1]], 25 | [-1, 1, Conv, [64, 3, 1]], 26 | [-1, 1, Conv, [64, 3, 1]], 27 | [-1, 1, Conv, [64, 3, 1]], 28 | [-1, 1, Conv, [64, 3, 1]], 29 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 30 | [-1, 1, Conv, [320, 1, 1]], # 13 31 | 32 | [-1, 1, MP, []], 33 | [-1, 1, Conv, [160, 1, 1]], 34 | [-3, 1, Conv, [160, 1, 1]], 35 | [-1, 1, Conv, [160, 3, 2]], 36 | [[-1, -3], 1, Concat, [1]], # 18-P3/8 37 | [-1, 1, Conv, [128, 1, 1]], 38 | [-2, 1, Conv, [128, 1, 1]], 39 | [-1, 1, Conv, [128, 3, 1]], 40 | [-1, 1, Conv, [128, 3, 1]], 41 | [-1, 1, Conv, [128, 3, 1]], 42 | [-1, 1, Conv, [128, 3, 1]], 43 | [-1, 1, Conv, [128, 3, 1]], 44 | [-1, 1, Conv, [128, 3, 1]], 45 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 46 | [-1, 1, Conv, [640, 1, 1]], # 28 47 | 48 | [-1, 1, MP, []], 49 | [-1, 1, Conv, [320, 1, 1]], 50 | [-3, 1, Conv, [320, 1, 1]], 51 | [-1, 1, Conv, [320, 3, 2]], 52 | [[-1, -3], 1, Concat, [1]], # 33-P4/16 53 | [-1, 1, Conv, [256, 1, 1]], 54 | [-2, 1, Conv, [256, 1, 1]], 55 | [-1, 1, Conv, [256, 3, 1]], 56 | [-1, 1, Conv, [256, 3, 1]], 57 | [-1, 1, Conv, [256, 3, 1]], 58 | [-1, 1, Conv, [256, 3, 1]], 59 | [-1, 1, Conv, [256, 3, 1]], 60 | [-1, 1, Conv, [256, 3, 1]], 61 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 62 | [-1, 1, Conv, [1280, 1, 1]], # 43 63 | 64 | [-1, 1, MP, []], 65 | [-1, 1, Conv, [640, 1, 1]], 66 | [-3, 1, Conv, [640, 1, 1]], 67 | [-1, 1, Conv, [640, 3, 2]], 68 | [[-1, -3], 1, Concat, [1]], # 48-P5/32 69 | [-1, 1, Conv, [256, 1, 1]], 70 | [-2, 1, Conv, [256, 1, 1]], 71 | [-1, 1, Conv, [256, 3, 1]], 72 | [-1, 1, Conv, [256, 3, 1]], 73 | [-1, 1, Conv, [256, 3, 1]], 74 | [-1, 1, Conv, [256, 3, 1]], 75 | [-1, 1, Conv, [256, 3, 1]], 76 | [-1, 1, Conv, [256, 3, 1]], 77 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 78 | [-1, 1, Conv, [1280, 1, 1]], # 58 79 | ] 80 | 81 | # yolov7 head 82 | head: 83 | [[-1, 1, SPPCSPC, [640]], # 59 84 | 85 | [-1, 1, Conv, [320, 1, 1]], 86 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 87 | [43, 1, Conv, [320, 1, 1]], # route backbone P4 88 | [[-1, -2], 1, Concat, [1]], 89 | 90 | [-1, 1, Conv, [256, 1, 1]], 91 | [-2, 1, Conv, [256, 1, 1]], 92 | [-1, 1, Conv, [256, 3, 1]], 93 | [-1, 1, Conv, [256, 3, 1]], 94 | [-1, 1, Conv, [256, 3, 1]], 95 | [-1, 1, Conv, [256, 3, 1]], 96 | [-1, 1, Conv, [256, 3, 1]], 97 | [-1, 1, Conv, [256, 3, 1]], 98 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 99 | [-1, 1, Conv, [320, 1, 1]], # 73 100 | 101 | [-1, 1, Conv, [160, 1, 1]], 102 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 103 | [28, 1, Conv, [160, 1, 1]], # route backbone P3 104 | [[-1, -2], 1, Concat, [1]], 105 | 106 | [-1, 1, Conv, [128, 1, 1]], 107 | [-2, 1, Conv, [128, 1, 1]], 108 | [-1, 1, Conv, [128, 3, 1]], 109 | [-1, 1, Conv, [128, 3, 1]], 110 | [-1, 1, Conv, [128, 3, 1]], 111 | [-1, 1, Conv, [128, 3, 1]], 112 | [-1, 1, Conv, [128, 3, 1]], 113 | [-1, 1, Conv, [128, 3, 1]], 114 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 115 | [-1, 1, Conv, [160, 1, 1]], # 87 116 | 117 | [-1, 1, MP, []], 118 | [-1, 1, Conv, [160, 1, 1]], 119 | [-3, 1, Conv, [160, 1, 1]], 120 | [-1, 1, Conv, [160, 3, 2]], 121 | [[-1, -3, 73], 1, Concat, [1]], 122 | 123 | [-1, 1, Conv, [256, 1, 1]], 124 | [-2, 1, Conv, [256, 1, 1]], 125 | [-1, 1, Conv, [256, 3, 1]], 126 | [-1, 1, Conv, [256, 3, 1]], 127 | [-1, 1, Conv, [256, 3, 1]], 128 | [-1, 1, Conv, [256, 3, 1]], 129 | [-1, 1, Conv, [256, 3, 1]], 130 | [-1, 1, Conv, [256, 3, 1]], 131 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 132 | [-1, 1, Conv, [320, 1, 1]], # 102 133 | 134 | [-1, 1, MP, []], 135 | [-1, 1, Conv, [320, 1, 1]], 136 | [-3, 1, Conv, [320, 1, 1]], 137 | [-1, 1, Conv, [320, 3, 2]], 138 | [[-1, -3, 59], 1, Concat, [1]], 139 | 140 | [-1, 1, Conv, [512, 1, 1]], 141 | [-2, 1, Conv, [512, 1, 1]], 142 | [-1, 1, Conv, [512, 3, 1]], 143 | [-1, 1, Conv, [512, 3, 1]], 144 | [-1, 1, Conv, [512, 3, 1]], 145 | [-1, 1, Conv, [512, 3, 1]], 146 | [-1, 1, Conv, [512, 3, 1]], 147 | [-1, 1, Conv, [512, 3, 1]], 148 | [[-1, -3, -5, -7, -8], 1, Concat, [1]], 149 | [-1, 1, Conv, [640, 1, 1]], # 117 150 | 151 | [87, 1, Conv, [320, 3, 1]], 152 | [102, 1, Conv, [640, 3, 1]], 153 | [117, 1, Conv, [1280, 3, 1]], 154 | 155 | [[118,119,120], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) 156 | ] 157 | -------------------------------------------------------------------------------- /data/coco.yaml: -------------------------------------------------------------------------------- 1 | # COCO 2017 dataset http://cocodataset.org 2 | 3 | # download command/URL (optional) 4 | download: bash ./scripts/get_coco.sh 5 | 6 | # train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] 7 | train: ./coco/train2017.txt # 118287 images 8 | val: ./coco/val2017.txt # 5000 images 9 | test: ./coco/test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 10 | 11 | # number of classes 12 | nc: 80 13 | 14 | # class names 15 | names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 16 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 17 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 18 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 19 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 20 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 21 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 22 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 23 | 'hair drier', 'toothbrush' ] 24 | -------------------------------------------------------------------------------- /data/hyp.scratch.custom.yaml: -------------------------------------------------------------------------------- 1 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 2 | lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) 3 | momentum: 0.937 # SGD momentum/Adam beta1 4 | weight_decay: 0.0005 # optimizer weight decay 5e-4 5 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 6 | warmup_momentum: 0.8 # warmup initial momentum 7 | warmup_bias_lr: 0.1 # warmup initial bias lr 8 | box: 0.05 # box loss gain 9 | cls: 0.3 # cls loss gain 10 | cls_pw: 1.0 # cls BCELoss positive_weight 11 | obj: 0.7 # obj loss gain (scale with pixels) 12 | obj_pw: 1.0 # obj BCELoss positive_weight 13 | iou_t: 0.20 # IoU training threshold 14 | anchor_t: 4.0 # anchor-multiple threshold 15 | # anchors: 3 # anchors per output layer (0 to ignore) 16 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 17 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 18 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 19 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 20 | degrees: 0.0 # image rotation (+/- deg) 21 | translate: 0.2 # image translation (+/- fraction) 22 | scale: 0.5 # image scale (+/- gain) 23 | shear: 0.0 # image shear (+/- deg) 24 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 25 | flipud: 0.0 # image flip up-down (probability) 26 | fliplr: 0.5 # image flip left-right (probability) 27 | mosaic: 1.0 # image mosaic (probability) 28 | mixup: 0.0 # image mixup (probability) 29 | copy_paste: 0.0 # image copy paste (probability) 30 | paste_in: 0.0 # image copy paste (probability), use 0 for faster training 31 | loss_ota: 1 # use ComputeLossOTA, use 0 for faster training -------------------------------------------------------------------------------- /data/hyp.scratch.p5.yaml: -------------------------------------------------------------------------------- 1 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 2 | lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) 3 | momentum: 0.937 # SGD momentum/Adam beta1 4 | weight_decay: 0.0005 # optimizer weight decay 5e-4 5 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 6 | warmup_momentum: 0.8 # warmup initial momentum 7 | warmup_bias_lr: 0.1 # warmup initial bias lr 8 | box: 0.05 # box loss gain 9 | cls: 0.3 # cls loss gain 10 | cls_pw: 1.0 # cls BCELoss positive_weight 11 | obj: 0.7 # obj loss gain (scale with pixels) 12 | obj_pw: 1.0 # obj BCELoss positive_weight 13 | iou_t: 0.20 # IoU training threshold 14 | anchor_t: 4.0 # anchor-multiple threshold 15 | # anchors: 3 # anchors per output layer (0 to ignore) 16 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 17 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 18 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 19 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 20 | degrees: 0.0 # image rotation (+/- deg) 21 | translate: 0.2 # image translation (+/- fraction) 22 | scale: 0.9 # image scale (+/- gain) 23 | shear: 0.0 # image shear (+/- deg) 24 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 25 | flipud: 0.0 # image flip up-down (probability) 26 | fliplr: 0.5 # image flip left-right (probability) 27 | mosaic: 1.0 # image mosaic (probability) 28 | mixup: 0.15 # image mixup (probability) 29 | copy_paste: 0.0 # image copy paste (probability) 30 | paste_in: 0.15 # image copy paste (probability), use 0 for faster training 31 | loss_ota: 1 # use ComputeLossOTA, use 0 for faster training -------------------------------------------------------------------------------- /data/hyp.scratch.p6.yaml: -------------------------------------------------------------------------------- 1 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 2 | lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) 3 | momentum: 0.937 # SGD momentum/Adam beta1 4 | weight_decay: 0.0005 # optimizer weight decay 5e-4 5 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 6 | warmup_momentum: 0.8 # warmup initial momentum 7 | warmup_bias_lr: 0.1 # warmup initial bias lr 8 | box: 0.05 # box loss gain 9 | cls: 0.3 # cls loss gain 10 | cls_pw: 1.0 # cls BCELoss positive_weight 11 | obj: 0.7 # obj loss gain (scale with pixels) 12 | obj_pw: 1.0 # obj BCELoss positive_weight 13 | iou_t: 0.20 # IoU training threshold 14 | anchor_t: 4.0 # anchor-multiple threshold 15 | # anchors: 3 # anchors per output layer (0 to ignore) 16 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 17 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 18 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 19 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 20 | degrees: 0.0 # image rotation (+/- deg) 21 | translate: 0.2 # image translation (+/- fraction) 22 | scale: 0.9 # image scale (+/- gain) 23 | shear: 0.0 # image shear (+/- deg) 24 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 25 | flipud: 0.0 # image flip up-down (probability) 26 | fliplr: 0.5 # image flip left-right (probability) 27 | mosaic: 1.0 # image mosaic (probability) 28 | mixup: 0.15 # image mixup (probability) 29 | copy_paste: 0.0 # image copy paste (probability) 30 | paste_in: 0.15 # image copy paste (probability), use 0 for faster training 31 | loss_ota: 1 # use ComputeLossOTA, use 0 for faster training -------------------------------------------------------------------------------- /data/hyp.scratch.tiny.yaml: -------------------------------------------------------------------------------- 1 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 2 | lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf) 3 | momentum: 0.937 # SGD momentum/Adam beta1 4 | weight_decay: 0.0005 # optimizer weight decay 5e-4 5 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 6 | warmup_momentum: 0.8 # warmup initial momentum 7 | warmup_bias_lr: 0.1 # warmup initial bias lr 8 | box: 0.05 # box loss gain 9 | cls: 0.5 # cls loss gain 10 | cls_pw: 1.0 # cls BCELoss positive_weight 11 | obj: 1.0 # obj loss gain (scale with pixels) 12 | obj_pw: 1.0 # obj BCELoss positive_weight 13 | iou_t: 0.20 # IoU training threshold 14 | anchor_t: 4.0 # anchor-multiple threshold 15 | # anchors: 3 # anchors per output layer (0 to ignore) 16 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 17 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 18 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 19 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 20 | degrees: 0.0 # image rotation (+/- deg) 21 | translate: 0.1 # image translation (+/- fraction) 22 | scale: 0.5 # image scale (+/- gain) 23 | shear: 0.0 # image shear (+/- deg) 24 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 25 | flipud: 0.0 # image flip up-down (probability) 26 | fliplr: 0.5 # image flip left-right (probability) 27 | mosaic: 1.0 # image mosaic (probability) 28 | mixup: 0.05 # image mixup (probability) 29 | copy_paste: 0.0 # image copy paste (probability) 30 | paste_in: 0.05 # image copy paste (probability), use 0 for faster training 31 | loss_ota: 1 # use ComputeLossOTA, use 0 for faster training 32 | -------------------------------------------------------------------------------- /deploy/triton-inference-server/README.md: -------------------------------------------------------------------------------- 1 | # YOLOv7 on Triton Inference Server 2 | 3 | Instructions to deploy YOLOv7 as TensorRT engine to [Triton Inference Server](https://github.com/NVIDIA/triton-inference-server). 4 | 5 | Triton Inference Server takes care of model deployment with many out-of-the-box benefits, like a GRPC and HTTP interface, automatic scheduling on multiple GPUs, shared memory (even on GPU), dynamic server-side batching, health metrics and memory resource management. 6 | 7 | There are no additional dependencies needed to run this deployment, except a working docker daemon with GPU support. 8 | 9 | ## Export TensorRT 10 | 11 | See https://github.com/WongKinYiu/yolov7#export for more info. 12 | 13 | ```bash 14 | # Pytorch Yolov7 -> ONNX with grid, EfficientNMS plugin and dynamic batch size 15 | python export.py --weights ./yolov7.pt --grid --end2end --dynamic-batch --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 16 | # ONNX -> TensorRT with trtexec and docker 17 | docker run -it --rm --gpus=all nvcr.io/nvidia/tensorrt:22.06-py3 18 | # Copy onnx -> container: docker cp yolov7.onnx :/workspace/ 19 | # Export with FP16 precision, min batch 1, opt batch 8 and max batch 8 20 | ./tensorrt/bin/trtexec --onnx=yolov7.onnx --minShapes=images:1x3x640x640 --optShapes=images:8x3x640x640 --maxShapes=images:8x3x640x640 --fp16 --workspace=4096 --saveEngine=yolov7-fp16-1x8x8.engine --timingCacheFile=timing.cache 21 | # Test engine 22 | ./tensorrt/bin/trtexec --loadEngine=yolov7-fp16-1x8x8.engine 23 | # Copy engine -> host: docker cp :/workspace/yolov7-fp16-1x8x8.engine . 24 | ``` 25 | 26 | Example output of test with RTX 3090. 27 | 28 | ``` 29 | [I] === Performance summary === 30 | [I] Throughput: 73.4985 qps 31 | [I] Latency: min = 14.8578 ms, max = 15.8344 ms, mean = 15.07 ms, median = 15.0422 ms, percentile(99%) = 15.7443 ms 32 | [I] End-to-End Host Latency: min = 25.8715 ms, max = 28.4102 ms, mean = 26.672 ms, median = 26.6082 ms, percentile(99%) = 27.8314 ms 33 | [I] Enqueue Time: min = 0.793701 ms, max = 1.47144 ms, mean = 1.2008 ms, median = 1.28644 ms, percentile(99%) = 1.38965 ms 34 | [I] H2D Latency: min = 1.50073 ms, max = 1.52454 ms, mean = 1.51225 ms, median = 1.51404 ms, percentile(99%) = 1.51941 ms 35 | [I] GPU Compute Time: min = 13.3386 ms, max = 14.3186 ms, mean = 13.5448 ms, median = 13.5178 ms, percentile(99%) = 14.2151 ms 36 | [I] D2H Latency: min = 0.00878906 ms, max = 0.0172729 ms, mean = 0.0128844 ms, median = 0.0125732 ms, percentile(99%) = 0.0166016 ms 37 | [I] Total Host Walltime: 3.04768 s 38 | [I] Total GPU Compute Time: 3.03404 s 39 | [I] Explanations of the performance metrics are printed in the verbose logs. 40 | ``` 41 | Note: 73.5 qps x batch 8 = 588 fps @ ~15ms latency. 42 | 43 | ## Model Repository 44 | 45 | See [Triton Model Repository Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_repository.md#model-repository) for more info. 46 | 47 | ```bash 48 | # Create folder structure 49 | mkdir -p triton-deploy/models/yolov7/1/ 50 | touch triton-deploy/models/yolov7/config.pbtxt 51 | # Place model 52 | mv yolov7-fp16-1x8x8.engine triton-deploy/models/yolov7/1/model.plan 53 | ``` 54 | 55 | ## Model Configuration 56 | 57 | See [Triton Model Configuration Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#model-configuration) for more info. 58 | 59 | Minimal configuration for `triton-deploy/models/yolov7/config.pbtxt`: 60 | 61 | ``` 62 | name: "yolov7" 63 | platform: "tensorrt_plan" 64 | max_batch_size: 8 65 | dynamic_batching { } 66 | ``` 67 | 68 | Example repository: 69 | 70 | ```bash 71 | $ tree triton-deploy/ 72 | triton-deploy/ 73 | └── models 74 | └── yolov7 75 | ├── 1 76 | │   └── model.plan 77 | └── config.pbtxt 78 | 79 | 3 directories, 2 files 80 | ``` 81 | 82 | ## Start Triton Inference Server 83 | 84 | ``` 85 | docker run --gpus all --rm --ipc=host --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 -p8000:8000 -p8001:8001 -p8002:8002 -v$(pwd)/triton-deploy/models:/models nvcr.io/nvidia/tritonserver:22.06-py3 tritonserver --model-repository=/models --strict-model-config=false --log-verbose 1 86 | ``` 87 | 88 | In the log you should see: 89 | 90 | ``` 91 | +--------+---------+--------+ 92 | | Model | Version | Status | 93 | +--------+---------+--------+ 94 | | yolov7 | 1 | READY | 95 | +--------+---------+--------+ 96 | ``` 97 | 98 | ## Performance with Model Analyzer 99 | 100 | See [Triton Model Analyzer Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_analyzer.md#model-analyzer) for more info. 101 | 102 | Performance numbers @ RTX 3090 + AMD Ryzen 9 5950X 103 | 104 | Example test for 16 concurrent clients using shared memory, each with batch size 1 requests: 105 | 106 | ```bash 107 | docker run -it --ipc=host --net=host nvcr.io/nvidia/tritonserver:22.06-py3-sdk /bin/bash 108 | 109 | ./install/bin/perf_analyzer -m yolov7 -u 127.0.0.1:8001 -i grpc --shared-memory system --concurrency-range 16 110 | 111 | # Result (truncated) 112 | Concurrency: 16, throughput: 590.119 infer/sec, latency 27080 usec 113 | ``` 114 | 115 | Throughput for 16 clients with batch size 1 is the same as for a single thread running the engine at 16 batch size locally thanks to Triton [Dynamic Batching Strategy](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#dynamic-batcher). Result without dynamic batching (disable in model configuration) considerably worse: 116 | 117 | ```bash 118 | # Result (truncated) 119 | Concurrency: 16, throughput: 335.587 infer/sec, latency 47616 usec 120 | ``` 121 | 122 | ## How to run model in your code 123 | 124 | Example client can be found in client.py. It can run dummy input, images and videos. 125 | 126 | ```bash 127 | pip3 install tritonclient[all] opencv-python 128 | python3 client.py image data/dog.jpg 129 | ``` 130 | 131 | ![exemplary output result](data/dog_result.jpg) 132 | 133 | ``` 134 | $ python3 client.py --help 135 | usage: client.py [-h] [-m MODEL] [--width WIDTH] [--height HEIGHT] [-u URL] [-o OUT] [-f FPS] [-i] [-v] [-t CLIENT_TIMEOUT] [-s] [-r ROOT_CERTIFICATES] [-p PRIVATE_KEY] [-x CERTIFICATE_CHAIN] {dummy,image,video} [input] 136 | 137 | positional arguments: 138 | {dummy,image,video} Run mode. 'dummy' will send an emtpy buffer to the server to test if inference works. 'image' will process an image. 'video' will process a video. 139 | input Input file to load from in image or video mode 140 | 141 | optional arguments: 142 | -h, --help show this help message and exit 143 | -m MODEL, --model MODEL 144 | Inference model name, default yolov7 145 | --width WIDTH Inference model input width, default 640 146 | --height HEIGHT Inference model input height, default 640 147 | -u URL, --url URL Inference server URL, default localhost:8001 148 | -o OUT, --out OUT Write output into file instead of displaying it 149 | -f FPS, --fps FPS Video output fps, default 24.0 FPS 150 | -i, --model-info Print model status, configuration and statistics 151 | -v, --verbose Enable verbose client output 152 | -t CLIENT_TIMEOUT, --client-timeout CLIENT_TIMEOUT 153 | Client timeout in seconds, default no timeout 154 | -s, --ssl Enable SSL encrypted channel to the server 155 | -r ROOT_CERTIFICATES, --root-certificates ROOT_CERTIFICATES 156 | File holding PEM-encoded root certificates, default none 157 | -p PRIVATE_KEY, --private-key PRIVATE_KEY 158 | File holding PEM-encoded private key, default is none 159 | -x CERTIFICATE_CHAIN, --certificate-chain CERTIFICATE_CHAIN 160 | File holding PEM-encoded certicate chain default is none 161 | ``` 162 | -------------------------------------------------------------------------------- /deploy/triton-inference-server/boundingbox.py: -------------------------------------------------------------------------------- 1 | class BoundingBox: 2 | def __init__(self, classID, confidence, x1, x2, y1, y2, image_width, image_height): 3 | self.classID = classID 4 | self.confidence = confidence 5 | self.x1 = x1 6 | self.x2 = x2 7 | self.y1 = y1 8 | self.y2 = y2 9 | self.u1 = x1 / image_width 10 | self.u2 = x2 / image_width 11 | self.v1 = y1 / image_height 12 | self.v2 = y2 / image_height 13 | 14 | def box(self): 15 | return (self.x1, self.y1, self.x2, self.y2) 16 | 17 | def width(self): 18 | return self.x2 - self.x1 19 | 20 | def height(self): 21 | return self.y2 - self.y1 22 | 23 | def center_absolute(self): 24 | return (0.5 * (self.x1 + self.x2), 0.5 * (self.y1 + self.y2)) 25 | 26 | def center_normalized(self): 27 | return (0.5 * (self.u1 + self.u2), 0.5 * (self.v1 + self.v2)) 28 | 29 | def size_absolute(self): 30 | return (self.x2 - self.x1, self.y2 - self.y1) 31 | 32 | def size_normalized(self): 33 | return (self.u2 - self.u1, self.v2 - self.v1) 34 | -------------------------------------------------------------------------------- /deploy/triton-inference-server/data/dog.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/deploy/triton-inference-server/data/dog.jpg -------------------------------------------------------------------------------- /deploy/triton-inference-server/data/dog_result.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/deploy/triton-inference-server/data/dog_result.jpg -------------------------------------------------------------------------------- /deploy/triton-inference-server/labels.py: -------------------------------------------------------------------------------- 1 | from enum import Enum 2 | 3 | class COCOLabels(Enum): 4 | PERSON = 0 5 | BICYCLE = 1 6 | CAR = 2 7 | MOTORBIKE = 3 8 | AEROPLANE = 4 9 | BUS = 5 10 | TRAIN = 6 11 | TRUCK = 7 12 | BOAT = 8 13 | TRAFFIC_LIGHT = 9 14 | FIRE_HYDRANT = 10 15 | STOP_SIGN = 11 16 | PARKING_METER = 12 17 | BENCH = 13 18 | BIRD = 14 19 | CAT = 15 20 | DOG = 16 21 | HORSE = 17 22 | SHEEP = 18 23 | COW = 19 24 | ELEPHANT = 20 25 | BEAR = 21 26 | ZEBRA = 22 27 | GIRAFFE = 23 28 | BACKPACK = 24 29 | UMBRELLA = 25 30 | HANDBAG = 26 31 | TIE = 27 32 | SUITCASE = 28 33 | FRISBEE = 29 34 | SKIS = 30 35 | SNOWBOARD = 31 36 | SPORTS_BALL = 32 37 | KITE = 33 38 | BASEBALL_BAT = 34 39 | BASEBALL_GLOVE = 35 40 | SKATEBOARD = 36 41 | SURFBOARD = 37 42 | TENNIS_RACKET = 38 43 | BOTTLE = 39 44 | WINE_GLASS = 40 45 | CUP = 41 46 | FORK = 42 47 | KNIFE = 43 48 | SPOON = 44 49 | BOWL = 45 50 | BANANA = 46 51 | APPLE = 47 52 | SANDWICH = 48 53 | ORANGE = 49 54 | BROCCOLI = 50 55 | CARROT = 51 56 | HOT_DOG = 52 57 | PIZZA = 53 58 | DONUT = 54 59 | CAKE = 55 60 | CHAIR = 56 61 | SOFA = 57 62 | POTTEDPLANT = 58 63 | BED = 59 64 | DININGTABLE = 60 65 | TOILET = 61 66 | TVMONITOR = 62 67 | LAPTOP = 63 68 | MOUSE = 64 69 | REMOTE = 65 70 | KEYBOARD = 66 71 | CELL_PHONE = 67 72 | MICROWAVE = 68 73 | OVEN = 69 74 | TOASTER = 70 75 | SINK = 71 76 | REFRIGERATOR = 72 77 | BOOK = 73 78 | CLOCK = 74 79 | VASE = 75 80 | SCISSORS = 76 81 | TEDDY_BEAR = 77 82 | HAIR_DRIER = 78 83 | TOOTHBRUSH = 79 84 | -------------------------------------------------------------------------------- /deploy/triton-inference-server/processing.py: -------------------------------------------------------------------------------- 1 | from boundingbox import BoundingBox 2 | 3 | import cv2 4 | import numpy as np 5 | 6 | def preprocess(img, input_shape, letter_box=True): 7 | if letter_box: 8 | img_h, img_w, _ = img.shape 9 | new_h, new_w = input_shape[0], input_shape[1] 10 | offset_h, offset_w = 0, 0 11 | if (new_w / img_w) <= (new_h / img_h): 12 | new_h = int(img_h * new_w / img_w) 13 | offset_h = (input_shape[0] - new_h) // 2 14 | else: 15 | new_w = int(img_w * new_h / img_h) 16 | offset_w = (input_shape[1] - new_w) // 2 17 | resized = cv2.resize(img, (new_w, new_h)) 18 | img = np.full((input_shape[0], input_shape[1], 3), 127, dtype=np.uint8) 19 | img[offset_h:(offset_h + new_h), offset_w:(offset_w + new_w), :] = resized 20 | else: 21 | img = cv2.resize(img, (input_shape[1], input_shape[0])) 22 | 23 | img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) 24 | img = img.transpose((2, 0, 1)).astype(np.float32) 25 | img /= 255.0 26 | return img 27 | 28 | def postprocess(num_dets, det_boxes, det_scores, det_classes, img_w, img_h, input_shape, letter_box=True): 29 | boxes = det_boxes[0, :num_dets[0][0]] / np.array([input_shape[0], input_shape[1], input_shape[0], input_shape[1]], dtype=np.float32) 30 | scores = det_scores[0, :num_dets[0][0]] 31 | classes = det_classes[0, :num_dets[0][0]].astype(np.int) 32 | 33 | old_h, old_w = img_h, img_w 34 | offset_h, offset_w = 0, 0 35 | if letter_box: 36 | if (img_w / input_shape[1]) >= (img_h / input_shape[0]): 37 | old_h = int(input_shape[0] * img_w / input_shape[1]) 38 | offset_h = (old_h - img_h) // 2 39 | else: 40 | old_w = int(input_shape[1] * img_h / input_shape[0]) 41 | offset_w = (old_w - img_w) // 2 42 | 43 | boxes = boxes * np.array([old_w, old_h, old_w, old_h], dtype=np.float32) 44 | if letter_box: 45 | boxes -= np.array([offset_w, offset_h, offset_w, offset_h], dtype=np.float32) 46 | boxes = boxes.astype(np.int) 47 | 48 | detected_objects = [] 49 | for box, score, label in zip(boxes, scores, classes): 50 | detected_objects.append(BoundingBox(label, score, box[0], box[2], box[1], box[3], img_w, img_h)) 51 | return detected_objects 52 | -------------------------------------------------------------------------------- /deploy/triton-inference-server/render.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | import cv2 4 | 5 | from math import sqrt 6 | 7 | _LINE_THICKNESS_SCALING = 500.0 8 | 9 | np.random.seed(0) 10 | RAND_COLORS = np.random.randint(50, 255, (64, 3), "int") # used for class visu 11 | RAND_COLORS[0] = [220, 220, 220] 12 | 13 | def render_box(img, box, color=(200, 200, 200)): 14 | """ 15 | Render a box. Calculates scaling and thickness automatically. 16 | :param img: image to render into 17 | :param box: (x1, y1, x2, y2) - box coordinates 18 | :param color: (b, g, r) - box color 19 | :return: updated image 20 | """ 21 | x1, y1, x2, y2 = box 22 | thickness = int( 23 | round( 24 | (img.shape[0] * img.shape[1]) 25 | / (_LINE_THICKNESS_SCALING * _LINE_THICKNESS_SCALING) 26 | ) 27 | ) 28 | thickness = max(1, thickness) 29 | img = cv2.rectangle( 30 | img, 31 | (int(x1), int(y1)), 32 | (int(x2), int(y2)), 33 | color, 34 | thickness=thickness 35 | ) 36 | return img 37 | 38 | def render_filled_box(img, box, color=(200, 200, 200)): 39 | """ 40 | Render a box. Calculates scaling and thickness automatically. 41 | :param img: image to render into 42 | :param box: (x1, y1, x2, y2) - box coordinates 43 | :param color: (b, g, r) - box color 44 | :return: updated image 45 | """ 46 | x1, y1, x2, y2 = box 47 | img = cv2.rectangle( 48 | img, 49 | (int(x1), int(y1)), 50 | (int(x2), int(y2)), 51 | color, 52 | thickness=cv2.FILLED 53 | ) 54 | return img 55 | 56 | _TEXT_THICKNESS_SCALING = 700.0 57 | _TEXT_SCALING = 520.0 58 | 59 | 60 | def get_text_size(img, text, normalised_scaling=1.0): 61 | """ 62 | Get calculated text size (as box width and height) 63 | :param img: image reference, used to determine appropriate text scaling 64 | :param text: text to display 65 | :param normalised_scaling: additional normalised scaling. Default 1.0. 66 | :return: (width, height) - width and height of text box 67 | """ 68 | thickness = int( 69 | round( 70 | (img.shape[0] * img.shape[1]) 71 | / (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING) 72 | ) 73 | * normalised_scaling 74 | ) 75 | thickness = max(1, thickness) 76 | scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling 77 | return cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, scaling, thickness)[0] 78 | 79 | 80 | def render_text(img, text, pos, color=(200, 200, 200), normalised_scaling=1.0): 81 | """ 82 | Render a text into the image. Calculates scaling and thickness automatically. 83 | :param img: image to render into 84 | :param text: text to display 85 | :param pos: (x, y) - upper left coordinates of render position 86 | :param color: (b, g, r) - text color 87 | :param normalised_scaling: additional normalised scaling. Default 1.0. 88 | :return: updated image 89 | """ 90 | x, y = pos 91 | thickness = int( 92 | round( 93 | (img.shape[0] * img.shape[1]) 94 | / (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING) 95 | ) 96 | * normalised_scaling 97 | ) 98 | thickness = max(1, thickness) 99 | scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling 100 | size = get_text_size(img, text, normalised_scaling) 101 | cv2.putText( 102 | img, 103 | text, 104 | (int(x), int(y + size[1])), 105 | cv2.FONT_HERSHEY_SIMPLEX, 106 | scaling, 107 | color, 108 | thickness=thickness, 109 | ) 110 | return img 111 | -------------------------------------------------------------------------------- /detect.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import time 3 | from pathlib import Path 4 | 5 | import cv2 6 | import torch 7 | import torch.backends.cudnn as cudnn 8 | from numpy import random 9 | 10 | from models.experimental import attempt_load 11 | from utils.datasets import LoadStreams, LoadImages 12 | from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \ 13 | scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path 14 | from utils.plots import plot_one_box 15 | from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel 16 | 17 | 18 | def detect(save_img=False): 19 | source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace 20 | save_img = not opt.nosave and not source.endswith('.txt') # save inference images 21 | webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( 22 | ('rtsp://', 'rtmp://', 'http://', 'https://')) 23 | 24 | # Directories 25 | save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run 26 | (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir 27 | 28 | # Initialize 29 | set_logging() 30 | device = select_device(opt.device) 31 | half = device.type != 'cpu' # half precision only supported on CUDA 32 | 33 | # Load model 34 | model = attempt_load(weights, map_location=device) # load FP32 model 35 | stride = int(model.stride.max()) # model stride 36 | imgsz = check_img_size(imgsz, s=stride) # check img_size 37 | 38 | if trace: 39 | model = TracedModel(model, device, opt.img_size) 40 | 41 | if half: 42 | model.half() # to FP16 43 | 44 | # Second-stage classifier 45 | classify = False 46 | if classify: 47 | modelc = load_classifier(name='resnet101', n=2) # initialize 48 | modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval() 49 | 50 | # Set Dataloader 51 | vid_path, vid_writer = None, None 52 | if webcam: 53 | view_img = check_imshow() 54 | cudnn.benchmark = True # set True to speed up constant image size inference 55 | dataset = LoadStreams(source, img_size=imgsz, stride=stride) 56 | else: 57 | dataset = LoadImages(source, img_size=imgsz, stride=stride) 58 | 59 | # Get names and colors 60 | names = model.module.names if hasattr(model, 'module') else model.names 61 | colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] 62 | 63 | # Run inference 64 | if device.type != 'cpu': 65 | model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once 66 | old_img_w = old_img_h = imgsz 67 | old_img_b = 1 68 | 69 | t0 = time.time() 70 | for path, img, im0s, vid_cap in dataset: 71 | img = torch.from_numpy(img).to(device) 72 | img = img.half() if half else img.float() # uint8 to fp16/32 73 | img /= 255.0 # 0 - 255 to 0.0 - 1.0 74 | if img.ndimension() == 3: 75 | img = img.unsqueeze(0) 76 | 77 | # Warmup 78 | if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]): 79 | old_img_b = img.shape[0] 80 | old_img_h = img.shape[2] 81 | old_img_w = img.shape[3] 82 | for i in range(3): 83 | model(img, augment=opt.augment)[0] 84 | 85 | # Inference 86 | t1 = time_synchronized() 87 | pred = model(img, augment=opt.augment)[0] 88 | t2 = time_synchronized() 89 | 90 | # Apply NMS 91 | pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) 92 | t3 = time_synchronized() 93 | 94 | # Apply Classifier 95 | if classify: 96 | pred = apply_classifier(pred, modelc, img, im0s) 97 | 98 | # Process detections 99 | for i, det in enumerate(pred): # detections per image 100 | if webcam: # batch_size >= 1 101 | p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count 102 | else: 103 | p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0) 104 | 105 | p = Path(p) # to Path 106 | save_path = str(save_dir / p.name) # img.jpg 107 | txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt 108 | gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh 109 | if len(det): 110 | # Rescale boxes from img_size to im0 size 111 | det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() 112 | 113 | # Print results 114 | for c in det[:, -1].unique(): 115 | n = (det[:, -1] == c).sum() # detections per class 116 | s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string 117 | 118 | # Write results 119 | for *xyxy, conf, cls in reversed(det): 120 | if save_txt: # Write to file 121 | xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh 122 | line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format 123 | with open(txt_path + '.txt', 'a') as f: 124 | f.write(('%g ' * len(line)).rstrip() % line + '\n') 125 | 126 | if save_img or view_img: # Add bbox to image 127 | label = f'{names[int(cls)]} {conf:.2f}' 128 | plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1) 129 | 130 | # Print time (inference + NMS) 131 | print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS') 132 | 133 | # Stream results 134 | if view_img: 135 | cv2.imshow(str(p), im0) 136 | cv2.waitKey(1) # 1 millisecond 137 | 138 | # Save results (image with detections) 139 | if save_img: 140 | if dataset.mode == 'image': 141 | cv2.imwrite(save_path, im0) 142 | print(f" The image with the result is saved in: {save_path}") 143 | else: # 'video' or 'stream' 144 | if vid_path != save_path: # new video 145 | vid_path = save_path 146 | if isinstance(vid_writer, cv2.VideoWriter): 147 | vid_writer.release() # release previous video writer 148 | if vid_cap: # video 149 | fps = vid_cap.get(cv2.CAP_PROP_FPS) 150 | w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) 151 | h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) 152 | else: # stream 153 | fps, w, h = 30, im0.shape[1], im0.shape[0] 154 | save_path += '.mp4' 155 | vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) 156 | vid_writer.write(im0) 157 | 158 | if save_txt or save_img: 159 | s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' 160 | #print(f"Results saved to {save_dir}{s}") 161 | 162 | print(f'Done. ({time.time() - t0:.3f}s)') 163 | 164 | 165 | if __name__ == '__main__': 166 | parser = argparse.ArgumentParser() 167 | parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)') 168 | parser.add_argument('--source', type=str, default='inference/images', help='source') # file/folder, 0 for webcam 169 | parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)') 170 | parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold') 171 | parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS') 172 | parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') 173 | parser.add_argument('--view-img', action='store_true', help='display results') 174 | parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') 175 | parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') 176 | parser.add_argument('--nosave', action='store_true', help='do not save images/videos') 177 | parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3') 178 | parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS') 179 | parser.add_argument('--augment', action='store_true', help='augmented inference') 180 | parser.add_argument('--update', action='store_true', help='update all models') 181 | parser.add_argument('--project', default='runs/detect', help='save results to project/name') 182 | parser.add_argument('--name', default='exp', help='save results to project/name') 183 | parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') 184 | parser.add_argument('--no-trace', action='store_true', help='don`t trace model') 185 | opt = parser.parse_args() 186 | print(opt) 187 | #check_requirements(exclude=('pycocotools', 'thop')) 188 | 189 | with torch.no_grad(): 190 | if opt.update: # update all models (to fix SourceChangeWarning) 191 | for opt.weights in ['yolov7.pt']: 192 | detect() 193 | strip_optimizer(opt.weights) 194 | else: 195 | detect() 196 | -------------------------------------------------------------------------------- /export.py: -------------------------------------------------------------------------------- 1 | import os 2 | import argparse 3 | import sys 4 | import time 5 | import warnings 6 | 7 | sys.path.append('./') # to run '$ python *.py' files in subdirectories 8 | 9 | # activate rknn hack 10 | if '--rknpu' in sys.argv: 11 | os.environ['RKNN_model_hack']='1' 12 | 13 | import torch 14 | import torch.nn as nn 15 | from torch.utils.mobile_optimizer import optimize_for_mobile 16 | 17 | import models 18 | from models.experimental import attempt_load, End2End 19 | from utils.activations import Hardswish, SiLU 20 | from utils.general import set_logging, check_img_size 21 | from utils.torch_utils import select_device 22 | from utils.add_nms import RegisterNMS 23 | 24 | if __name__ == '__main__': 25 | parser = argparse.ArgumentParser() 26 | parser.add_argument('--weights', type=str, default='./yolov7-tiny.pt', help='weights path') 27 | parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width 28 | parser.add_argument('--batch-size', type=int, default=1, help='batch size') 29 | parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') 30 | parser.add_argument('--dynamic-batch', action='store_true', help='dynamic batch onnx for tensorrt and onnx-runtime') 31 | parser.add_argument('--grid', action='store_true', help='export Detect() layer grid') 32 | parser.add_argument('--end2end', action='store_true', help='export end2end onnx') 33 | parser.add_argument('--max-wh', type=int, default=None, help='None for tensorrt nms, int value for onnx-runtime nms') 34 | parser.add_argument('--topk-all', type=int, default=100, help='topk objects for every images') 35 | parser.add_argument('--iou-thres', type=float, default=0.45, help='iou threshold for NMS') 36 | parser.add_argument('--conf-thres', type=float, default=0.25, help='conf threshold for NMS') 37 | parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') 38 | parser.add_argument('--simplify', action='store_true', help='simplify onnx model') 39 | parser.add_argument('--include-nms', action='store_true', help='export end2end onnx') 40 | parser.add_argument('--fp16', action='store_true', help='CoreML FP16 half-precision export') 41 | parser.add_argument('--int8', action='store_true', help='CoreML INT8 quantization') 42 | parser.add_argument('--rknpu', action='store_true', help='RKNN npu platform') 43 | opt = parser.parse_args() 44 | del opt.rknpu 45 | opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand 46 | opt.dynamic = opt.dynamic and not opt.end2end 47 | opt.dynamic = False if opt.dynamic_batch else opt.dynamic 48 | print(opt) 49 | set_logging() 50 | t = time.time() 51 | 52 | # Load PyTorch model 53 | device = select_device(opt.device) 54 | model = attempt_load(opt.weights, map_location=device) # load FP32 model 55 | labels = model.names 56 | 57 | # Checks 58 | gs = int(max(model.stride)) # grid size (max stride) 59 | opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples 60 | 61 | # Input 62 | img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection 63 | 64 | # Update model 65 | for k, m in model.named_modules(): 66 | m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility 67 | # if isinstance(m, models.common.Conv): # assign export-friendly activations 68 | # if isinstance(m.act, nn.Hardswish): 69 | # m.act = Hardswish() 70 | # elif isinstance(m.act, nn.SiLU): 71 | # m.act = SiLU() 72 | # elif isinstance(m, models.yolo.Detect): 73 | # m.forward = m.forward_export # assign forward (optional) 74 | model.model[-1].export = not opt.grid # set Detect() layer grid export 75 | if os.getenv('RKNN_model_hack', '0') in ['1']: 76 | from models.common import SP 77 | for k, m in model.named_modules(): 78 | if isinstance(m, SP) and m.m.kernel_size%2==1 and m.m.stride==1: 79 | new_sp = nn.Sequential(*[nn.MaxPool2d(3,1,1) for i in range(m.m.kernel_size//2)]) 80 | m.m = new_sp 81 | 82 | from models.yolo import Detect, IDetect 83 | if isinstance(model.model[-1], Detect) or isinstance(model.model[-1], IDetect): 84 | # save anchors 85 | print('---> save anchors for RKNN') 86 | RK_anchors = model.model[-1].stride.reshape(3,1).repeat(1,3).reshape(-1,1)* model.model[-1].anchors.reshape(9,2) 87 | with open('RK_anchors.txt', 'w') as anf: 88 | # anf.write(str(model.model[-1].na)+'\n') 89 | for _v in RK_anchors.numpy().flatten(): 90 | anf.write(str(_v)+'\n') 91 | RK_anchors = RK_anchors.tolist() 92 | print(RK_anchors) 93 | 94 | y = model(img) # dry run 95 | if opt.include_nms: 96 | model.model[-1].include_nms = True 97 | y = None 98 | 99 | # TorchScript export 100 | # try: 101 | # print('\nStarting TorchScript export with torch %s...' % torch.__version__) 102 | # f = opt.weights.replace('.pt', '.torchscript.pt') # filename 103 | # ts = torch.jit.trace(model, img, strict=False) 104 | # ts.save(f) 105 | # print('TorchScript export success, saved as %s' % f) 106 | # except Exception as e: 107 | # print('TorchScript export failure: %s' % e) 108 | 109 | # ONNX export 110 | try: 111 | print('\nStarting onnx export with torch %s...' % torch.__version__) 112 | f = opt.weights.replace('.pt', '.onnx') # filename 113 | torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],) 114 | print('ONNX export success, saved as %s' % f) 115 | except Exception as e: 116 | print('ONNX export failure: %s' % e) 117 | 118 | # # CoreML export 119 | # try: 120 | # import coremltools as ct 121 | 122 | # print('\nStarting CoreML export with coremltools %s...' % ct.__version__) 123 | # # convert model from torchscript and apply pixel scaling as per detect.py 124 | # ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])]) 125 | # bits, mode = (8, 'kmeans_lut') if opt.int8 else (16, 'linear') if opt.fp16 else (32, None) 126 | # if bits < 32: 127 | # if sys.platform.lower() == 'darwin': # quantization only supported on macOS 128 | # with warnings.catch_warnings(): 129 | # warnings.filterwarnings("ignore", category=DeprecationWarning) # suppress numpy==1.20 float warning 130 | # ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode) 131 | # else: 132 | # print('quantization only supported on macOS, skipping...') 133 | 134 | # f = opt.weights.replace('.pt', '.mlmodel') # filename 135 | # ct_model.save(f) 136 | # print('CoreML export success, saved as %s' % f) 137 | # except Exception as e: 138 | # print('CoreML export failure: %s' % e) 139 | 140 | # TorchScript-Lite export 141 | ''' 142 | try: 143 | print('\nStarting TorchScript-Lite export with torch %s...' % torch.__version__) 144 | f = opt.weights.replace('.pt', '.torchscript.ptl') # filename 145 | tsl = torch.jit.trace(model, img, strict=False) 146 | tsl = optimize_for_mobile(tsl) 147 | tsl._save_for_lite_interpreter(f) 148 | print('TorchScript-Lite export success, saved as %s' % f) 149 | except Exception as e: 150 | print('TorchScript-Lite export failure: %s' % e) 151 | ''' 152 | 153 | # ONNX export 154 | ''' 155 | try: 156 | import onnx 157 | 158 | print('\nStarting ONNX export with onnx %s...' % onnx.__version__) 159 | f = opt.weights.replace('.pt', '.onnx') # filename 160 | model.eval() 161 | output_names = ['classes', 'boxes'] if y is None else ['output'] 162 | dynamic_axes = None 163 | if opt.dynamic: 164 | dynamic_axes = {'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640) 165 | 'output': {0: 'batch', 2: 'y', 3: 'x'}} 166 | if opt.dynamic_batch: 167 | opt.batch_size = 'batch' 168 | dynamic_axes = { 169 | 'images': { 170 | 0: 'batch', 171 | }, } 172 | if opt.end2end and opt.max_wh is None: 173 | output_axes = { 174 | 'num_dets': {0: 'batch'}, 175 | 'det_boxes': {0: 'batch'}, 176 | 'det_scores': {0: 'batch'}, 177 | 'det_classes': {0: 'batch'}, 178 | } 179 | else: 180 | output_axes = { 181 | 'output': {0: 'batch'}, 182 | } 183 | dynamic_axes.update(output_axes) 184 | if opt.grid: 185 | if opt.end2end: 186 | print('\nStarting export end2end onnx model for %s...' % 'TensorRT' if opt.max_wh is None else 'onnxruntime') 187 | model = End2End(model,opt.topk_all,opt.iou_thres,opt.conf_thres,opt.max_wh,device,len(labels)) 188 | if opt.end2end and opt.max_wh is None: 189 | output_names = ['num_dets', 'det_boxes', 'det_scores', 'det_classes'] 190 | shapes = [opt.batch_size, 1, opt.batch_size, opt.topk_all, 4, 191 | opt.batch_size, opt.topk_all, opt.batch_size, opt.topk_all] 192 | else: 193 | output_names = ['output'] 194 | else: 195 | model.model[-1].concat = True 196 | 197 | torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'], 198 | output_names=output_names, 199 | dynamic_axes=dynamic_axes) 200 | 201 | # Checks 202 | onnx_model = onnx.load(f) # load onnx model 203 | onnx.checker.check_model(onnx_model) # check onnx model 204 | 205 | if opt.end2end and opt.max_wh is None: 206 | for i in onnx_model.graph.output: 207 | for j in i.type.tensor_type.shape.dim: 208 | j.dim_param = str(shapes.pop(0)) 209 | 210 | # print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model 211 | 212 | # # Metadata 213 | # d = {'stride': int(max(model.stride))} 214 | # for k, v in d.items(): 215 | # meta = onnx_model.metadata_props.add() 216 | # meta.key, meta.value = k, str(v) 217 | # onnx.save(onnx_model, f) 218 | 219 | if opt.simplify: 220 | try: 221 | import onnxsim 222 | 223 | print('\nStarting to simplify ONNX...') 224 | onnx_model, check = onnxsim.simplify(onnx_model) 225 | assert check, 'assert check failed' 226 | except Exception as e: 227 | print(f'Simplifier failure: {e}') 228 | 229 | # print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model 230 | onnx.save(onnx_model,f) 231 | print('ONNX export success, saved as %s' % f) 232 | 233 | if opt.include_nms: 234 | print('Registering NMS plugin for ONNX...') 235 | mo = RegisterNMS(f) 236 | mo.register_nms() 237 | mo.save(f) 238 | 239 | except Exception as e: 240 | print('ONNX export failure: %s' % e) 241 | ''' 242 | 243 | # Finish 244 | print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t)) 245 | -------------------------------------------------------------------------------- /figure/horses_prediction.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/horses_prediction.jpg -------------------------------------------------------------------------------- /figure/mask.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/mask.png -------------------------------------------------------------------------------- /figure/performance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/performance.png -------------------------------------------------------------------------------- /figure/pose.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/pose.png -------------------------------------------------------------------------------- /figure/tennis.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/tennis.jpg -------------------------------------------------------------------------------- /figure/tennis_caption.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/tennis_caption.png -------------------------------------------------------------------------------- /figure/tennis_panoptic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/tennis_panoptic.png -------------------------------------------------------------------------------- /figure/tennis_semantic.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/figure/tennis_semantic.jpg -------------------------------------------------------------------------------- /hubconf.py: -------------------------------------------------------------------------------- 1 | """PyTorch Hub models 2 | 3 | Usage: 4 | import torch 5 | model = torch.hub.load('repo', 'model') 6 | """ 7 | 8 | from pathlib import Path 9 | 10 | import torch 11 | 12 | from models.yolo import Model 13 | from utils.general import check_requirements, set_logging 14 | from utils.google_utils import attempt_download 15 | from utils.torch_utils import select_device 16 | 17 | dependencies = ['torch', 'yaml'] 18 | check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop')) 19 | set_logging() 20 | 21 | 22 | def create(name, pretrained, channels, classes, autoshape): 23 | """Creates a specified model 24 | 25 | Arguments: 26 | name (str): name of model, i.e. 'yolov7' 27 | pretrained (bool): load pretrained weights into the model 28 | channels (int): number of input channels 29 | classes (int): number of model classes 30 | 31 | Returns: 32 | pytorch model 33 | """ 34 | try: 35 | cfg = list((Path(__file__).parent / 'cfg').rglob(f'{name}.yaml'))[0] # model.yaml path 36 | model = Model(cfg, channels, classes) 37 | if pretrained: 38 | fname = f'{name}.pt' # checkpoint filename 39 | attempt_download(fname) # download if not found locally 40 | ckpt = torch.load(fname, map_location=torch.device('cpu')) # load 41 | msd = model.state_dict() # model state_dict 42 | csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 43 | csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter 44 | model.load_state_dict(csd, strict=False) # load 45 | if len(ckpt['model'].names) == classes: 46 | model.names = ckpt['model'].names # set class names attribute 47 | if autoshape: 48 | model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS 49 | device = select_device('0' if torch.cuda.is_available() else 'cpu') # default to GPU if available 50 | return model.to(device) 51 | 52 | except Exception as e: 53 | s = 'Cache maybe be out of date, try force_reload=True.' 54 | raise Exception(s) from e 55 | 56 | 57 | def custom(path_or_model='path/to/model.pt', autoshape=True): 58 | """custom mode 59 | 60 | Arguments (3 options): 61 | path_or_model (str): 'path/to/model.pt' 62 | path_or_model (dict): torch.load('path/to/model.pt') 63 | path_or_model (nn.Module): torch.load('path/to/model.pt')['model'] 64 | 65 | Returns: 66 | pytorch model 67 | """ 68 | model = torch.load(path_or_model, map_location=torch.device('cpu')) if isinstance(path_or_model, str) else path_or_model # load checkpoint 69 | if isinstance(model, dict): 70 | model = model['ema' if model.get('ema') else 'model'] # load model 71 | 72 | hub_model = Model(model.yaml).to(next(model.parameters()).device) # create 73 | hub_model.load_state_dict(model.float().state_dict()) # load state_dict 74 | hub_model.names = model.names # class names 75 | if autoshape: 76 | hub_model = hub_model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS 77 | device = select_device('0' if torch.cuda.is_available() else 'cpu') # default to GPU if available 78 | return hub_model.to(device) 79 | 80 | 81 | def yolov7(pretrained=True, channels=3, classes=80, autoshape=True): 82 | return create('yolov7', pretrained, channels, classes, autoshape) 83 | 84 | 85 | if __name__ == '__main__': 86 | model = custom(path_or_model='yolov7.pt') # custom example 87 | # model = create(name='yolov7', pretrained=True, channels=3, classes=80, autoshape=True) # pretrained example 88 | 89 | # Verify inference 90 | import numpy as np 91 | from PIL import Image 92 | 93 | imgs = [np.zeros((640, 480, 3))] 94 | 95 | results = model(imgs) # batched inference 96 | results.print() 97 | results.save() 98 | -------------------------------------------------------------------------------- /inference/images/bus.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/bus.jpg -------------------------------------------------------------------------------- /inference/images/horses.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/horses.jpg -------------------------------------------------------------------------------- /inference/images/image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/image1.jpg -------------------------------------------------------------------------------- /inference/images/image2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/image2.jpg -------------------------------------------------------------------------------- /inference/images/image3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/image3.jpg -------------------------------------------------------------------------------- /inference/images/zidane.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/inference/images/zidane.jpg -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- 1 | # init -------------------------------------------------------------------------------- /paper/yolov7.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/airockchip/yolov7/c2d39f4db6b82800ce6c61740be5ef82854c5d3e/paper/yolov7.pdf -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | # Usage: pip install -r requirements.txt 2 | 3 | # Base ---------------------------------------- 4 | matplotlib>=3.2.2 5 | numpy>=1.18.5 6 | opencv-python>=4.1.1 7 | Pillow>=7.1.2 8 | PyYAML>=5.3.1 9 | requests>=2.23.0 10 | scipy>=1.4.1 11 | torch>=1.7.0,!=1.12.0 12 | torchvision>=0.8.1,!=0.13.0 13 | tqdm>=4.41.0 14 | protobuf<4.21.3 15 | 16 | # Logging ------------------------------------- 17 | tensorboard>=2.4.1 18 | # wandb 19 | 20 | # Plotting ------------------------------------ 21 | pandas>=1.1.4 22 | seaborn>=0.11.0 23 | 24 | # Export -------------------------------------- 25 | # coremltools>=4.1 # CoreML export 26 | # onnx>=1.9.0 # ONNX export 27 | # onnx-simplifier>=0.3.6 # ONNX simplifier 28 | # scikit-learn==0.19.2 # CoreML quantization 29 | # tensorflow>=2.4.1 # TFLite export 30 | # tensorflowjs>=3.9.0 # TF.js export 31 | # openvino-dev # OpenVINO export 32 | 33 | # Extras -------------------------------------- 34 | ipython # interactive notebook 35 | psutil # system utilization 36 | thop # FLOPs computation 37 | # albumentations>=1.0.3 38 | # pycocotools>=2.0 # COCO mAP 39 | # roboflow 40 | -------------------------------------------------------------------------------- /scripts/get_coco.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # COCO 2017 dataset http://cocodataset.org 3 | # Download command: bash ./scripts/get_coco.sh 4 | 5 | # Download/unzip labels 6 | d='./' # unzip directory 7 | url=https://github.com/ultralytics/yolov5/releases/download/v1.0/ 8 | f='coco2017labels-segments.zip' # or 'coco2017labels.zip', 68 MB 9 | echo 'Downloading' $url$f ' ...' 10 | curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background 11 | 12 | # Download/unzip images 13 | d='./coco/images' # unzip directory 14 | url=http://images.cocodataset.org/zips/ 15 | f1='train2017.zip' # 19G, 118k images 16 | f2='val2017.zip' # 1G, 5k images 17 | f3='test2017.zip' # 7G, 41k images (optional) 18 | for f in $f1 $f2 $f3; do 19 | echo 'Downloading' $url$f '...' 20 | curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background 21 | done 22 | wait # finish background tasks 23 | -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | # init -------------------------------------------------------------------------------- /utils/activations.py: -------------------------------------------------------------------------------- 1 | # Activation functions 2 | 3 | import torch 4 | import torch.nn as nn 5 | import torch.nn.functional as F 6 | 7 | 8 | # SiLU https://arxiv.org/pdf/1606.08415.pdf ---------------------------------------------------------------------------- 9 | class SiLU(nn.Module): # export-friendly version of nn.SiLU() 10 | @staticmethod 11 | def forward(x): 12 | return x * torch.sigmoid(x) 13 | 14 | 15 | class Hardswish(nn.Module): # export-friendly version of nn.Hardswish() 16 | @staticmethod 17 | def forward(x): 18 | # return x * F.hardsigmoid(x) # for torchscript and CoreML 19 | return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX 20 | 21 | 22 | class MemoryEfficientSwish(nn.Module): 23 | class F(torch.autograd.Function): 24 | @staticmethod 25 | def forward(ctx, x): 26 | ctx.save_for_backward(x) 27 | return x * torch.sigmoid(x) 28 | 29 | @staticmethod 30 | def backward(ctx, grad_output): 31 | x = ctx.saved_tensors[0] 32 | sx = torch.sigmoid(x) 33 | return grad_output * (sx * (1 + x * (1 - sx))) 34 | 35 | def forward(self, x): 36 | return self.F.apply(x) 37 | 38 | 39 | # Mish https://github.com/digantamisra98/Mish -------------------------------------------------------------------------- 40 | class Mish(nn.Module): 41 | @staticmethod 42 | def forward(x): 43 | return x * F.softplus(x).tanh() 44 | 45 | 46 | class MemoryEfficientMish(nn.Module): 47 | class F(torch.autograd.Function): 48 | @staticmethod 49 | def forward(ctx, x): 50 | ctx.save_for_backward(x) 51 | return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) 52 | 53 | @staticmethod 54 | def backward(ctx, grad_output): 55 | x = ctx.saved_tensors[0] 56 | sx = torch.sigmoid(x) 57 | fx = F.softplus(x).tanh() 58 | return grad_output * (fx + x * sx * (1 - fx * fx)) 59 | 60 | def forward(self, x): 61 | return self.F.apply(x) 62 | 63 | 64 | # FReLU https://arxiv.org/abs/2007.11824 ------------------------------------------------------------------------------- 65 | class FReLU(nn.Module): 66 | def __init__(self, c1, k=3): # ch_in, kernel 67 | super().__init__() 68 | self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False) 69 | self.bn = nn.BatchNorm2d(c1) 70 | 71 | def forward(self, x): 72 | return torch.max(x, self.bn(self.conv(x))) 73 | -------------------------------------------------------------------------------- /utils/add_nms.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import onnx 3 | from onnx import shape_inference 4 | try: 5 | import onnx_graphsurgeon as gs 6 | except Exception as e: 7 | print('Import onnx_graphsurgeon failure: %s' % e) 8 | 9 | import logging 10 | 11 | LOGGER = logging.getLogger(__name__) 12 | 13 | class RegisterNMS(object): 14 | def __init__( 15 | self, 16 | onnx_model_path: str, 17 | precision: str = "fp32", 18 | ): 19 | 20 | self.graph = gs.import_onnx(onnx.load(onnx_model_path)) 21 | assert self.graph 22 | LOGGER.info("ONNX graph created successfully") 23 | # Fold constants via ONNX-GS that PyTorch2ONNX may have missed 24 | self.graph.fold_constants() 25 | self.precision = precision 26 | self.batch_size = 1 27 | def infer(self): 28 | """ 29 | Sanitize the graph by cleaning any unconnected nodes, do a topological resort, 30 | and fold constant inputs values. When possible, run shape inference on the 31 | ONNX graph to determine tensor shapes. 32 | """ 33 | for _ in range(3): 34 | count_before = len(self.graph.nodes) 35 | 36 | self.graph.cleanup().toposort() 37 | try: 38 | for node in self.graph.nodes: 39 | for o in node.outputs: 40 | o.shape = None 41 | model = gs.export_onnx(self.graph) 42 | model = shape_inference.infer_shapes(model) 43 | self.graph = gs.import_onnx(model) 44 | except Exception as e: 45 | LOGGER.info(f"Shape inference could not be performed at this time:\n{e}") 46 | try: 47 | self.graph.fold_constants(fold_shapes=True) 48 | except TypeError as e: 49 | LOGGER.error( 50 | "This version of ONNX GraphSurgeon does not support folding shapes, " 51 | f"please upgrade your onnx_graphsurgeon module. Error:\n{e}" 52 | ) 53 | raise 54 | 55 | count_after = len(self.graph.nodes) 56 | if count_before == count_after: 57 | # No new folding occurred in this iteration, so we can stop for now. 58 | break 59 | 60 | def save(self, output_path): 61 | """ 62 | Save the ONNX model to the given location. 63 | Args: 64 | output_path: Path pointing to the location where to write 65 | out the updated ONNX model. 66 | """ 67 | self.graph.cleanup().toposort() 68 | model = gs.export_onnx(self.graph) 69 | onnx.save(model, output_path) 70 | LOGGER.info(f"Saved ONNX model to {output_path}") 71 | 72 | def register_nms( 73 | self, 74 | *, 75 | score_thresh: float = 0.25, 76 | nms_thresh: float = 0.45, 77 | detections_per_img: int = 100, 78 | ): 79 | """ 80 | Register the ``EfficientNMS_TRT`` plugin node. 81 | NMS expects these shapes for its input tensors: 82 | - box_net: [batch_size, number_boxes, 4] 83 | - class_net: [batch_size, number_boxes, number_labels] 84 | Args: 85 | score_thresh (float): The scalar threshold for score (low scoring boxes are removed). 86 | nms_thresh (float): The scalar threshold for IOU (new boxes that have high IOU 87 | overlap with previously selected boxes are removed). 88 | detections_per_img (int): Number of best detections to keep after NMS. 89 | """ 90 | 91 | self.infer() 92 | # Find the concat node at the end of the network 93 | op_inputs = self.graph.outputs 94 | op = "EfficientNMS_TRT" 95 | attrs = { 96 | "plugin_version": "1", 97 | "background_class": -1, # no background class 98 | "max_output_boxes": detections_per_img, 99 | "score_threshold": score_thresh, 100 | "iou_threshold": nms_thresh, 101 | "score_activation": False, 102 | "box_coding": 0, 103 | } 104 | 105 | if self.precision == "fp32": 106 | dtype_output = np.float32 107 | elif self.precision == "fp16": 108 | dtype_output = np.float16 109 | else: 110 | raise NotImplementedError(f"Currently not supports precision: {self.precision}") 111 | 112 | # NMS Outputs 113 | output_num_detections = gs.Variable( 114 | name="num_dets", 115 | dtype=np.int32, 116 | shape=[self.batch_size, 1], 117 | ) # A scalar indicating the number of valid detections per batch image. 118 | output_boxes = gs.Variable( 119 | name="det_boxes", 120 | dtype=dtype_output, 121 | shape=[self.batch_size, detections_per_img, 4], 122 | ) 123 | output_scores = gs.Variable( 124 | name="det_scores", 125 | dtype=dtype_output, 126 | shape=[self.batch_size, detections_per_img], 127 | ) 128 | output_labels = gs.Variable( 129 | name="det_classes", 130 | dtype=np.int32, 131 | shape=[self.batch_size, detections_per_img], 132 | ) 133 | 134 | op_outputs = [output_num_detections, output_boxes, output_scores, output_labels] 135 | 136 | # Create the NMS Plugin node with the selected inputs. The outputs of the node will also 137 | # become the final outputs of the graph. 138 | self.graph.layer(op=op, name="batched_nms", inputs=op_inputs, outputs=op_outputs, attrs=attrs) 139 | LOGGER.info(f"Created NMS plugin '{op}' with attributes: {attrs}") 140 | 141 | self.graph.outputs = op_outputs 142 | 143 | self.infer() 144 | 145 | def save(self, output_path): 146 | """ 147 | Save the ONNX model to the given location. 148 | Args: 149 | output_path: Path pointing to the location where to write 150 | out the updated ONNX model. 151 | """ 152 | self.graph.cleanup().toposort() 153 | model = gs.export_onnx(self.graph) 154 | onnx.save(model, output_path) 155 | LOGGER.info(f"Saved ONNX model to {output_path}") 156 | -------------------------------------------------------------------------------- /utils/autoanchor.py: -------------------------------------------------------------------------------- 1 | # Auto-anchor utils 2 | 3 | import numpy as np 4 | import torch 5 | import yaml 6 | from scipy.cluster.vq import kmeans 7 | from tqdm import tqdm 8 | 9 | from utils.general import colorstr 10 | 11 | 12 | def check_anchor_order(m): 13 | # Check anchor order against stride order for YOLO Detect() module m, and correct if necessary 14 | a = m.anchor_grid.prod(-1).view(-1) # anchor area 15 | da = a[-1] - a[0] # delta a 16 | ds = m.stride[-1] - m.stride[0] # delta s 17 | if da.sign() != ds.sign(): # same order 18 | print('Reversing anchor order') 19 | m.anchors[:] = m.anchors.flip(0) 20 | m.anchor_grid[:] = m.anchor_grid.flip(0) 21 | 22 | 23 | def check_anchors(dataset, model, thr=4.0, imgsz=640): 24 | # Check anchor fit to data, recompute if necessary 25 | prefix = colorstr('autoanchor: ') 26 | print(f'\n{prefix}Analyzing anchors... ', end='') 27 | m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() 28 | shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) 29 | scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale 30 | wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh 31 | 32 | def metric(k): # compute metric 33 | r = wh[:, None] / k[None] 34 | x = torch.min(r, 1. / r).min(2)[0] # ratio metric 35 | best = x.max(1)[0] # best_x 36 | aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold 37 | bpr = (best > 1. / thr).float().mean() # best possible recall 38 | return bpr, aat 39 | 40 | anchors = m.anchor_grid.clone().cpu().view(-1, 2) # current anchors 41 | bpr, aat = metric(anchors) 42 | print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='') 43 | if bpr < 0.98: # threshold to recompute 44 | print('. Attempting to improve anchors, please wait...') 45 | na = m.anchor_grid.numel() // 2 # number of anchors 46 | try: 47 | anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) 48 | except Exception as e: 49 | print(f'{prefix}ERROR: {e}') 50 | new_bpr = metric(anchors)[0] 51 | if new_bpr > bpr: # replace anchors 52 | anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) 53 | m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid) # for inference 54 | check_anchor_order(m) 55 | m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss 56 | print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.') 57 | else: 58 | print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.') 59 | print('') # newline 60 | 61 | 62 | def kmean_anchors(path='./data/coco.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): 63 | """ Creates kmeans-evolved anchors from training dataset 64 | 65 | Arguments: 66 | path: path to dataset *.yaml, or a loaded dataset 67 | n: number of anchors 68 | img_size: image size used for training 69 | thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 70 | gen: generations to evolve anchors using genetic algorithm 71 | verbose: print all results 72 | 73 | Return: 74 | k: kmeans evolved anchors 75 | 76 | Usage: 77 | from utils.autoanchor import *; _ = kmean_anchors() 78 | """ 79 | thr = 1. / thr 80 | prefix = colorstr('autoanchor: ') 81 | 82 | def metric(k, wh): # compute metrics 83 | r = wh[:, None] / k[None] 84 | x = torch.min(r, 1. / r).min(2)[0] # ratio metric 85 | # x = wh_iou(wh, torch.tensor(k)) # iou metric 86 | return x, x.max(1)[0] # x, best_x 87 | 88 | def anchor_fitness(k): # mutation fitness 89 | _, best = metric(torch.tensor(k, dtype=torch.float32), wh) 90 | return (best * (best > thr).float()).mean() # fitness 91 | 92 | def print_results(k): 93 | k = k[np.argsort(k.prod(1))] # sort small to large 94 | x, best = metric(k, wh0) 95 | bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr 96 | print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr') 97 | print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' 98 | f'past_thr={x[x > thr].mean():.3f}-mean: ', end='') 99 | for i, x in enumerate(k): 100 | print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg 101 | return k 102 | 103 | if isinstance(path, str): # *.yaml file 104 | with open(path) as f: 105 | data_dict = yaml.load(f, Loader=yaml.SafeLoader) # model dict 106 | from utils.datasets import LoadImagesAndLabels 107 | dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) 108 | else: 109 | dataset = path # dataset 110 | 111 | # Get label wh 112 | shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) 113 | wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh 114 | 115 | # Filter 116 | i = (wh0 < 3.0).any(1).sum() 117 | if i: 118 | print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.') 119 | wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels 120 | # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1 121 | 122 | # Kmeans calculation 123 | print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...') 124 | s = wh.std(0) # sigmas for whitening 125 | k, dist = kmeans(wh / s, n, iter=30) # points, mean distance 126 | assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}') 127 | k *= s 128 | wh = torch.tensor(wh, dtype=torch.float32) # filtered 129 | wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered 130 | k = print_results(k) 131 | 132 | # Plot 133 | # k, d = [None] * 20, [None] * 20 134 | # for i in tqdm(range(1, 21)): 135 | # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance 136 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True) 137 | # ax = ax.ravel() 138 | # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') 139 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh 140 | # ax[0].hist(wh[wh[:, 0]<100, 0],400) 141 | # ax[1].hist(wh[wh[:, 1]<100, 1],400) 142 | # fig.savefig('wh.png', dpi=200) 143 | 144 | # Evolve 145 | npr = np.random 146 | f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma 147 | pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar 148 | for _ in pbar: 149 | v = np.ones(sh) 150 | while (v == 1).all(): # mutate until a change occurs (prevent duplicates) 151 | v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) 152 | kg = (k.copy() * v).clip(min=2.0) 153 | fg = anchor_fitness(kg) 154 | if fg > f: 155 | f, k = fg, kg.copy() 156 | pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}' 157 | if verbose: 158 | print_results(k) 159 | 160 | return print_results(k) 161 | -------------------------------------------------------------------------------- /utils/aws/__init__.py: -------------------------------------------------------------------------------- 1 | #init -------------------------------------------------------------------------------- /utils/aws/mime.sh: -------------------------------------------------------------------------------- 1 | # AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/ 2 | # This script will run on every instance restart, not only on first start 3 | # --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA --- 4 | 5 | Content-Type: multipart/mixed; boundary="//" 6 | MIME-Version: 1.0 7 | 8 | --// 9 | Content-Type: text/cloud-config; charset="us-ascii" 10 | MIME-Version: 1.0 11 | Content-Transfer-Encoding: 7bit 12 | Content-Disposition: attachment; filename="cloud-config.txt" 13 | 14 | #cloud-config 15 | cloud_final_modules: 16 | - [scripts-user, always] 17 | 18 | --// 19 | Content-Type: text/x-shellscript; charset="us-ascii" 20 | MIME-Version: 1.0 21 | Content-Transfer-Encoding: 7bit 22 | Content-Disposition: attachment; filename="userdata.txt" 23 | 24 | #!/bin/bash 25 | # --- paste contents of userdata.sh here --- 26 | --// 27 | -------------------------------------------------------------------------------- /utils/aws/resume.py: -------------------------------------------------------------------------------- 1 | # Resume all interrupted trainings in yolor/ dir including DDP trainings 2 | # Usage: $ python utils/aws/resume.py 3 | 4 | import os 5 | import sys 6 | from pathlib import Path 7 | 8 | import torch 9 | import yaml 10 | 11 | sys.path.append('./') # to run '$ python *.py' files in subdirectories 12 | 13 | port = 0 # --master_port 14 | path = Path('').resolve() 15 | for last in path.rglob('*/**/last.pt'): 16 | ckpt = torch.load(last) 17 | if ckpt['optimizer'] is None: 18 | continue 19 | 20 | # Load opt.yaml 21 | with open(last.parent.parent / 'opt.yaml') as f: 22 | opt = yaml.load(f, Loader=yaml.SafeLoader) 23 | 24 | # Get device count 25 | d = opt['device'].split(',') # devices 26 | nd = len(d) # number of devices 27 | ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel 28 | 29 | if ddp: # multi-GPU 30 | port += 1 31 | cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}' 32 | else: # single-GPU 33 | cmd = f'python train.py --resume {last}' 34 | 35 | cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread 36 | print(cmd) 37 | os.system(cmd) 38 | -------------------------------------------------------------------------------- /utils/aws/userdata.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html 3 | # This script will run only once on first instance start (for a re-start script see mime.sh) 4 | # /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir 5 | # Use >300 GB SSD 6 | 7 | cd home/ubuntu 8 | if [ ! -d yolor ]; then 9 | echo "Running first-time script." # install dependencies, download COCO, pull Docker 10 | git clone -b main https://github.com/WongKinYiu/yolov7 && sudo chmod -R 777 yolov7 11 | cd yolov7 12 | bash data/scripts/get_coco.sh && echo "Data done." & 13 | sudo docker pull nvcr.io/nvidia/pytorch:21.08-py3 && echo "Docker done." & 14 | python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." & 15 | wait && echo "All tasks done." # finish background tasks 16 | else 17 | echo "Running re-start script." # resume interrupted runs 18 | i=0 19 | list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour' 20 | while IFS= read -r id; do 21 | ((i++)) 22 | echo "restarting container $i: $id" 23 | sudo docker start $id 24 | # sudo docker exec -it $id python train.py --resume # single-GPU 25 | sudo docker exec -d $id python utils/aws/resume.py # multi-scenario 26 | done <<<"$list" 27 | fi 28 | -------------------------------------------------------------------------------- /utils/google_app_engine/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM gcr.io/google-appengine/python 2 | 3 | # Create a virtualenv for dependencies. This isolates these packages from 4 | # system-level packages. 5 | # Use -p python3 or -p python3.7 to select python version. Default is version 2. 6 | RUN virtualenv /env -p python3 7 | 8 | # Setting these environment variables are the same as running 9 | # source /env/bin/activate. 10 | ENV VIRTUAL_ENV /env 11 | ENV PATH /env/bin:$PATH 12 | 13 | RUN apt-get update && apt-get install -y python-opencv 14 | 15 | # Copy the application's requirements.txt and run pip to install all 16 | # dependencies into the virtualenv. 17 | ADD requirements.txt /app/requirements.txt 18 | RUN pip install -r /app/requirements.txt 19 | 20 | # Add the application source code. 21 | ADD . /app 22 | 23 | # Run a WSGI server to serve the application. gunicorn must be declared as 24 | # a dependency in requirements.txt. 25 | CMD gunicorn -b :$PORT main:app 26 | -------------------------------------------------------------------------------- /utils/google_app_engine/additional_requirements.txt: -------------------------------------------------------------------------------- 1 | # add these requirements in your app on top of the existing ones 2 | pip==18.1 3 | Flask==1.0.2 4 | gunicorn==19.9.0 5 | -------------------------------------------------------------------------------- /utils/google_app_engine/app.yaml: -------------------------------------------------------------------------------- 1 | runtime: custom 2 | env: flex 3 | 4 | service: yolorapp 5 | 6 | liveness_check: 7 | initial_delay_sec: 600 8 | 9 | manual_scaling: 10 | instances: 1 11 | resources: 12 | cpu: 1 13 | memory_gb: 4 14 | disk_size_gb: 20 -------------------------------------------------------------------------------- /utils/google_utils.py: -------------------------------------------------------------------------------- 1 | # Google utils: https://cloud.google.com/storage/docs/reference/libraries 2 | 3 | import os 4 | import platform 5 | import subprocess 6 | import time 7 | from pathlib import Path 8 | 9 | import requests 10 | import torch 11 | 12 | 13 | def gsutil_getsize(url=''): 14 | # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du 15 | s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') 16 | return eval(s.split(' ')[0]) if len(s) else 0 # bytes 17 | 18 | 19 | def attempt_download(file, repo='WongKinYiu/yolov7'): 20 | # Attempt file download if does not exist 21 | file = Path(str(file).strip().replace("'", '').lower()) 22 | 23 | if not file.exists(): 24 | try: 25 | response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api 26 | assets = [x['name'] for x in response['assets']] # release assets 27 | tag = response['tag_name'] # i.e. 'v1.0' 28 | except: # fallback plan 29 | assets = ['yolov7.pt', 'yolov7-tiny.pt', 'yolov7x.pt', 'yolov7-d6.pt', 'yolov7-e6.pt', 30 | 'yolov7-e6e.pt', 'yolov7-w6.pt'] 31 | if not subprocess.check_output('git tag', shell=True).decode().split(): 32 | tag = 'v0.1' 33 | else: 34 | tag = subprocess.check_output('git tag', shell=True).decode().split()[-1] 35 | 36 | name = file.name 37 | if name in assets: 38 | msg = f'{file} missing, try downloading from https://github.com/{repo}/releases/' 39 | redundant = False # second download option 40 | try: # GitHub 41 | url = f'https://github.com/{repo}/releases/download/{tag}/{name}' 42 | print(f'Downloading {url} to {file}...') 43 | torch.hub.download_url_to_file(url, file) 44 | assert file.exists() and file.stat().st_size > 1E6 # check 45 | except Exception as e: # GCP 46 | print(f'Download error: {e}') 47 | assert redundant, 'No secondary mirror' 48 | url = f'https://storage.googleapis.com/{repo}/ckpt/{name}' 49 | print(f'Downloading {url} to {file}...') 50 | os.system(f'curl -L {url} -o {file}') # torch.hub.download_url_to_file(url, weights) 51 | finally: 52 | if not file.exists() or file.stat().st_size < 1E6: # check 53 | file.unlink(missing_ok=True) # remove partial downloads 54 | print(f'ERROR: Download failure: {msg}') 55 | print('') 56 | return 57 | 58 | 59 | def gdrive_download(id='', file='tmp.zip'): 60 | # Downloads a file from Google Drive. from yolov7.utils.google_utils import *; gdrive_download() 61 | t = time.time() 62 | file = Path(file) 63 | cookie = Path('cookie') # gdrive cookie 64 | print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='') 65 | file.unlink(missing_ok=True) # remove existing file 66 | cookie.unlink(missing_ok=True) # remove existing cookie 67 | 68 | # Attempt file download 69 | out = "NUL" if platform.system() == "Windows" else "/dev/null" 70 | os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}') 71 | if os.path.exists('cookie'): # large file 72 | s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}' 73 | else: # small file 74 | s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"' 75 | r = os.system(s) # execute, capture return 76 | cookie.unlink(missing_ok=True) # remove existing cookie 77 | 78 | # Error check 79 | if r != 0: 80 | file.unlink(missing_ok=True) # remove partial 81 | print('Download error ') # raise Exception('Download error') 82 | return r 83 | 84 | # Unzip if archive 85 | if file.suffix == '.zip': 86 | print('unzipping... ', end='') 87 | os.system(f'unzip -q {file}') # unzip 88 | file.unlink() # remove zip to free space 89 | 90 | print(f'Done ({time.time() - t:.1f}s)') 91 | return r 92 | 93 | 94 | def get_token(cookie="./cookie"): 95 | with open(cookie) as f: 96 | for line in f: 97 | if "download" in line: 98 | return line.split()[-1] 99 | return "" 100 | 101 | # def upload_blob(bucket_name, source_file_name, destination_blob_name): 102 | # # Uploads a file to a bucket 103 | # # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python 104 | # 105 | # storage_client = storage.Client() 106 | # bucket = storage_client.get_bucket(bucket_name) 107 | # blob = bucket.blob(destination_blob_name) 108 | # 109 | # blob.upload_from_filename(source_file_name) 110 | # 111 | # print('File {} uploaded to {}.'.format( 112 | # source_file_name, 113 | # destination_blob_name)) 114 | # 115 | # 116 | # def download_blob(bucket_name, source_blob_name, destination_file_name): 117 | # # Uploads a blob from a bucket 118 | # storage_client = storage.Client() 119 | # bucket = storage_client.get_bucket(bucket_name) 120 | # blob = bucket.blob(source_blob_name) 121 | # 122 | # blob.download_to_filename(destination_file_name) 123 | # 124 | # print('Blob {} downloaded to {}.'.format( 125 | # source_blob_name, 126 | # destination_file_name)) 127 | -------------------------------------------------------------------------------- /utils/metrics.py: -------------------------------------------------------------------------------- 1 | # Model validation metrics 2 | 3 | from pathlib import Path 4 | 5 | import matplotlib.pyplot as plt 6 | import numpy as np 7 | import torch 8 | 9 | from . import general 10 | 11 | 12 | def fitness(x): 13 | # Model fitness as a weighted combination of metrics 14 | w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] 15 | return (x[:, :4] * w).sum(1) 16 | 17 | 18 | def ap_per_class(tp, conf, pred_cls, target_cls, v5_metric=False, plot=False, save_dir='.', names=()): 19 | """ Compute the average precision, given the recall and precision curves. 20 | Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. 21 | # Arguments 22 | tp: True positives (nparray, nx1 or nx10). 23 | conf: Objectness value from 0-1 (nparray). 24 | pred_cls: Predicted object classes (nparray). 25 | target_cls: True object classes (nparray). 26 | plot: Plot precision-recall curve at mAP@0.5 27 | save_dir: Plot save directory 28 | # Returns 29 | The average precision as computed in py-faster-rcnn. 30 | """ 31 | 32 | # Sort by objectness 33 | i = np.argsort(-conf) 34 | tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] 35 | 36 | # Find unique classes 37 | unique_classes = np.unique(target_cls) 38 | nc = unique_classes.shape[0] # number of classes, number of detections 39 | 40 | # Create Precision-Recall curve and compute AP for each class 41 | px, py = np.linspace(0, 1, 1000), [] # for plotting 42 | ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000)) 43 | for ci, c in enumerate(unique_classes): 44 | i = pred_cls == c 45 | n_l = (target_cls == c).sum() # number of labels 46 | n_p = i.sum() # number of predictions 47 | 48 | if n_p == 0 or n_l == 0: 49 | continue 50 | else: 51 | # Accumulate FPs and TPs 52 | fpc = (1 - tp[i]).cumsum(0) 53 | tpc = tp[i].cumsum(0) 54 | 55 | # Recall 56 | recall = tpc / (n_l + 1e-16) # recall curve 57 | r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases 58 | 59 | # Precision 60 | precision = tpc / (tpc + fpc) # precision curve 61 | p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score 62 | 63 | # AP from recall-precision curve 64 | for j in range(tp.shape[1]): 65 | ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j], v5_metric=v5_metric) 66 | if plot and j == 0: 67 | py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5 68 | 69 | # Compute F1 (harmonic mean of precision and recall) 70 | f1 = 2 * p * r / (p + r + 1e-16) 71 | if plot: 72 | plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names) 73 | plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1') 74 | plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision') 75 | plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall') 76 | 77 | i = f1.mean(0).argmax() # max F1 index 78 | return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32') 79 | 80 | 81 | def compute_ap(recall, precision, v5_metric=False): 82 | """ Compute the average precision, given the recall and precision curves 83 | # Arguments 84 | recall: The recall curve (list) 85 | precision: The precision curve (list) 86 | v5_metric: Assume maximum recall to be 1.0, as in YOLOv5, MMDetetion etc. 87 | # Returns 88 | Average precision, precision curve, recall curve 89 | """ 90 | 91 | # Append sentinel values to beginning and end 92 | if v5_metric: # New YOLOv5 metric, same as MMDetection and Detectron2 repositories 93 | mrec = np.concatenate(([0.], recall, [1.0])) 94 | else: # Old YOLOv5 metric, i.e. default YOLOv7 metric 95 | mrec = np.concatenate(([0.], recall, [recall[-1] + 0.01])) 96 | mpre = np.concatenate(([1.], precision, [0.])) 97 | 98 | # Compute the precision envelope 99 | mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) 100 | 101 | # Integrate area under curve 102 | method = 'interp' # methods: 'continuous', 'interp' 103 | if method == 'interp': 104 | x = np.linspace(0, 1, 101) # 101-point interp (COCO) 105 | ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate 106 | else: # 'continuous' 107 | i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes 108 | ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve 109 | 110 | return ap, mpre, mrec 111 | 112 | 113 | class ConfusionMatrix: 114 | # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix 115 | def __init__(self, nc, conf=0.25, iou_thres=0.45): 116 | self.matrix = np.zeros((nc + 1, nc + 1)) 117 | self.nc = nc # number of classes 118 | self.conf = conf 119 | self.iou_thres = iou_thres 120 | 121 | def process_batch(self, detections, labels): 122 | """ 123 | Return intersection-over-union (Jaccard index) of boxes. 124 | Both sets of boxes are expected to be in (x1, y1, x2, y2) format. 125 | Arguments: 126 | detections (Array[N, 6]), x1, y1, x2, y2, conf, class 127 | labels (Array[M, 5]), class, x1, y1, x2, y2 128 | Returns: 129 | None, updates confusion matrix accordingly 130 | """ 131 | detections = detections[detections[:, 4] > self.conf] 132 | gt_classes = labels[:, 0].int() 133 | detection_classes = detections[:, 5].int() 134 | iou = general.box_iou(labels[:, 1:], detections[:, :4]) 135 | 136 | x = torch.where(iou > self.iou_thres) 137 | if x[0].shape[0]: 138 | matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() 139 | if x[0].shape[0] > 1: 140 | matches = matches[matches[:, 2].argsort()[::-1]] 141 | matches = matches[np.unique(matches[:, 1], return_index=True)[1]] 142 | matches = matches[matches[:, 2].argsort()[::-1]] 143 | matches = matches[np.unique(matches[:, 0], return_index=True)[1]] 144 | else: 145 | matches = np.zeros((0, 3)) 146 | 147 | n = matches.shape[0] > 0 148 | m0, m1, _ = matches.transpose().astype(np.int16) 149 | for i, gc in enumerate(gt_classes): 150 | j = m0 == i 151 | if n and sum(j) == 1: 152 | self.matrix[gc, detection_classes[m1[j]]] += 1 # correct 153 | else: 154 | self.matrix[self.nc, gc] += 1 # background FP 155 | 156 | if n: 157 | for i, dc in enumerate(detection_classes): 158 | if not any(m1 == i): 159 | self.matrix[dc, self.nc] += 1 # background FN 160 | 161 | def matrix(self): 162 | return self.matrix 163 | 164 | def plot(self, save_dir='', names=()): 165 | try: 166 | import seaborn as sn 167 | 168 | array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6) # normalize 169 | array[array < 0.005] = np.nan # don't annotate (would appear as 0.00) 170 | 171 | fig = plt.figure(figsize=(12, 9), tight_layout=True) 172 | sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size 173 | labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels 174 | sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True, 175 | xticklabels=names + ['background FP'] if labels else "auto", 176 | yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1)) 177 | fig.axes[0].set_xlabel('True') 178 | fig.axes[0].set_ylabel('Predicted') 179 | fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250) 180 | except Exception as e: 181 | pass 182 | 183 | def print(self): 184 | for i in range(self.nc + 1): 185 | print(' '.join(map(str, self.matrix[i]))) 186 | 187 | 188 | # Plots ---------------------------------------------------------------------------------------------------------------- 189 | 190 | def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()): 191 | # Precision-recall curve 192 | fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) 193 | py = np.stack(py, axis=1) 194 | 195 | if 0 < len(names) < 21: # display per-class legend if < 21 classes 196 | for i, y in enumerate(py.T): 197 | ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision) 198 | else: 199 | ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision) 200 | 201 | ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean()) 202 | ax.set_xlabel('Recall') 203 | ax.set_ylabel('Precision') 204 | ax.set_xlim(0, 1) 205 | ax.set_ylim(0, 1) 206 | plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") 207 | fig.savefig(Path(save_dir), dpi=250) 208 | 209 | 210 | def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'): 211 | # Metric-confidence curve 212 | fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) 213 | 214 | if 0 < len(names) < 21: # display per-class legend if < 21 classes 215 | for i, y in enumerate(py): 216 | ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric) 217 | else: 218 | ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric) 219 | 220 | y = py.mean(0) 221 | ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}') 222 | ax.set_xlabel(xlabel) 223 | ax.set_ylabel(ylabel) 224 | ax.set_xlim(0, 1) 225 | ax.set_ylim(0, 1) 226 | plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") 227 | fig.savefig(Path(save_dir), dpi=250) 228 | -------------------------------------------------------------------------------- /utils/wandb_logging/__init__.py: -------------------------------------------------------------------------------- 1 | # init -------------------------------------------------------------------------------- /utils/wandb_logging/log_dataset.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | import yaml 4 | 5 | from wandb_utils import WandbLogger 6 | 7 | WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' 8 | 9 | 10 | def create_dataset_artifact(opt): 11 | with open(opt.data) as f: 12 | data = yaml.load(f, Loader=yaml.SafeLoader) # data dict 13 | logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation') 14 | 15 | 16 | if __name__ == '__main__': 17 | parser = argparse.ArgumentParser() 18 | parser.add_argument('--data', type=str, default='data/coco.yaml', help='data.yaml path') 19 | parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') 20 | parser.add_argument('--project', type=str, default='YOLOR', help='name of W&B Project') 21 | opt = parser.parse_args() 22 | opt.resume = False # Explicitly disallow resume check for dataset upload job 23 | 24 | create_dataset_artifact(opt) 25 | --------------------------------------------------------------------------------