├── README.md ├── YOLO-practice.ipynb ├── capture.PNG ├── cfg ├── coco.names ├── extraction.cfg ├── extraction.conv.cfg ├── tiny-yolo-4c.cfg ├── tiny-yolo-voc.cfg ├── tiny-yolo.cfg ├── v1.1 │ ├── person-bottle.cfg │ ├── tiny-coco.cfg │ ├── tiny-yolo-4c.cfg │ ├── tiny-yolov1.cfg │ ├── yolo-coco.cfg │ └── yolov1.cfg ├── v1 │ ├── tiny-old.profile │ ├── tiny.profile │ ├── yolo-2c.cfg │ ├── yolo-4c.cfg │ ├── yolo-full.cfg │ ├── yolo-small.cfg │ ├── yolo-tiny-extract.cfg │ ├── yolo-tiny-extract_.cfg │ ├── yolo-tiny.cfg │ └── yolo-tiny4c.cfg ├── yolo-voc.cfg └── yolo.cfg ├── sample_img └── sample_multiple_objects.jpg ├── sample_video └── test_video.mp4 └── weights.PNG /README.md: -------------------------------------------------------------------------------- 1 | # Object Detection using YOLOv2 in [darkflow](https://github.com/thtrieu/darkflow) 2 | 3 | ### Introduction 4 | This notebook is not about training on your own data. However, this notebook introduces how to use YOLOv2 on your data. It shows the process of taking input from your data (image), then outputing the pre-defined labels for the localized object on the image. After completing this notebook, I will go over how the training process can be done in the separate notebook. 5 | 6 | ### Contents 7 | 1. __References for YOLO implementation__ 8 | 2. __Importing Dependences__ 9 | 3. __Build the model__ 10 | 4. __Gain the results of detected objects__ 11 | 5. __Boxing around the objects__ 12 | 6. __Boxing in Video and output the video__ 13 | 14 | capture image 15 | -------------------------------------------------------------------------------- /capture.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/capture.PNG -------------------------------------------------------------------------------- /cfg/coco.names: -------------------------------------------------------------------------------- 1 | person 2 | bicycle 3 | car 4 | motorbike 5 | aeroplane 6 | bus 7 | train 8 | truck 9 | boat 10 | traffic light 11 | fire hydrant 12 | stop sign 13 | parking meter 14 | bench 15 | bird 16 | cat 17 | dog 18 | horse 19 | sheep 20 | cow 21 | elephant 22 | bear 23 | zebra 24 | giraffe 25 | backpack 26 | umbrella 27 | handbag 28 | tie 29 | suitcase 30 | frisbee 31 | skis 32 | snowboard 33 | sports ball 34 | kite 35 | baseball bat 36 | baseball glove 37 | skateboard 38 | surfboard 39 | tennis racket 40 | bottle 41 | wine glass 42 | cup 43 | fork 44 | knife 45 | spoon 46 | bowl 47 | banana 48 | apple 49 | sandwich 50 | orange 51 | broccoli 52 | carrot 53 | hot dog 54 | pizza 55 | donut 56 | cake 57 | chair 58 | sofa 59 | pottedplant 60 | bed 61 | diningtable 62 | toilet 63 | tvmonitor 64 | laptop 65 | mouse 66 | remote 67 | keyboard 68 | cell phone 69 | microwave 70 | oven 71 | toaster 72 | sink 73 | refrigerator 74 | book 75 | clock 76 | vase 77 | scissors 78 | teddy bear 79 | hair drier 80 | toothbrush 81 | -------------------------------------------------------------------------------- /cfg/extraction.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=128 3 | subdivisions=1 4 | height=224 5 | width=224 6 | max_crop=320 7 | channels=3 8 | momentum=0.9 9 | decay=0.0005 10 | 11 | learning_rate=0.1 12 | policy=poly 13 | power=4 14 | max_batches=1600000 15 | 16 | [convolutional] 17 | batch_normalize=1 18 | filters=64 19 | size=7 20 | stride=2 21 | pad=1 22 | activation=leaky 23 | 24 | [maxpool] 25 | size=2 26 | stride=2 27 | 28 | [convolutional] 29 | batch_normalize=1 30 | filters=192 31 | size=3 32 | stride=1 33 | pad=1 34 | activation=leaky 35 | 36 | [maxpool] 37 | size=2 38 | stride=2 39 | 40 | [convolutional] 41 | batch_normalize=1 42 | filters=128 43 | size=1 44 | stride=1 45 | pad=1 46 | activation=leaky 47 | 48 | [convolutional] 49 | batch_normalize=1 50 | filters=256 51 | size=3 52 | stride=1 53 | pad=1 54 | activation=leaky 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=256 59 | size=1 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [convolutional] 65 | batch_normalize=1 66 | filters=512 67 | size=3 68 | stride=1 69 | pad=1 70 | activation=leaky 71 | 72 | [maxpool] 73 | size=2 74 | stride=2 75 | 76 | [convolutional] 77 | batch_normalize=1 78 | filters=256 79 | size=1 80 | stride=1 81 | pad=1 82 | activation=leaky 83 | 84 | [convolutional] 85 | batch_normalize=1 86 | filters=512 87 | size=3 88 | stride=1 89 | pad=1 90 | activation=leaky 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | filters=256 95 | size=1 96 | stride=1 97 | pad=1 98 | activation=leaky 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | filters=512 103 | size=3 104 | stride=1 105 | pad=1 106 | activation=leaky 107 | 108 | [convolutional] 109 | batch_normalize=1 110 | filters=256 111 | size=1 112 | stride=1 113 | pad=1 114 | activation=leaky 115 | 116 | [convolutional] 117 | batch_normalize=1 118 | filters=512 119 | size=3 120 | stride=1 121 | pad=1 122 | activation=leaky 123 | 124 | [convolutional] 125 | batch_normalize=1 126 | filters=256 127 | size=1 128 | stride=1 129 | pad=1 130 | activation=leaky 131 | 132 | [convolutional] 133 | batch_normalize=1 134 | filters=512 135 | size=3 136 | stride=1 137 | pad=1 138 | activation=leaky 139 | 140 | [convolutional] 141 | batch_normalize=1 142 | filters=512 143 | size=1 144 | stride=1 145 | pad=1 146 | activation=leaky 147 | 148 | [convolutional] 149 | batch_normalize=1 150 | filters=1024 151 | size=3 152 | stride=1 153 | pad=1 154 | activation=leaky 155 | 156 | [maxpool] 157 | size=2 158 | stride=2 159 | 160 | [convolutional] 161 | batch_normalize=1 162 | filters=512 163 | size=1 164 | stride=1 165 | pad=1 166 | activation=leaky 167 | 168 | [convolutional] 169 | batch_normalize=1 170 | filters=1024 171 | size=3 172 | stride=1 173 | pad=1 174 | activation=leaky 175 | 176 | [convolutional] 177 | batch_normalize=1 178 | filters=512 179 | size=1 180 | stride=1 181 | pad=1 182 | activation=leaky 183 | 184 | [convolutional] 185 | batch_normalize=1 186 | filters=1024 187 | size=3 188 | stride=1 189 | pad=1 190 | activation=leaky 191 | 192 | [convolutional] 193 | filters=1000 194 | size=1 195 | stride=1 196 | pad=1 197 | activation=leaky 198 | 199 | [avgpool] 200 | 201 | [softmax] 202 | groups=1 203 | 204 | [cost] 205 | type=sse 206 | 207 | -------------------------------------------------------------------------------- /cfg/extraction.conv.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=1 3 | subdivisions=1 4 | height=256 5 | width=256 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.5 11 | policy=poly 12 | power=6 13 | max_batches=500000 14 | 15 | [convolutional] 16 | filters=64 17 | size=7 18 | stride=2 19 | pad=1 20 | activation=leaky 21 | 22 | [maxpool] 23 | size=2 24 | stride=2 25 | 26 | [convolutional] 27 | filters=192 28 | size=3 29 | stride=1 30 | pad=1 31 | activation=leaky 32 | 33 | [maxpool] 34 | size=2 35 | stride=2 36 | 37 | [convolutional] 38 | filters=128 39 | size=1 40 | stride=1 41 | pad=1 42 | activation=leaky 43 | 44 | [convolutional] 45 | filters=256 46 | size=3 47 | stride=1 48 | pad=1 49 | activation=leaky 50 | 51 | [convolutional] 52 | filters=256 53 | size=1 54 | stride=1 55 | pad=1 56 | activation=leaky 57 | 58 | [convolutional] 59 | filters=512 60 | size=3 61 | stride=1 62 | pad=1 63 | activation=leaky 64 | 65 | [maxpool] 66 | size=2 67 | stride=2 68 | 69 | [convolutional] 70 | filters=256 71 | size=1 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [convolutional] 77 | filters=512 78 | size=3 79 | stride=1 80 | pad=1 81 | activation=leaky 82 | 83 | [convolutional] 84 | filters=256 85 | size=1 86 | stride=1 87 | pad=1 88 | activation=leaky 89 | 90 | [convolutional] 91 | filters=512 92 | size=3 93 | stride=1 94 | pad=1 95 | activation=leaky 96 | 97 | [convolutional] 98 | filters=256 99 | size=1 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [convolutional] 105 | filters=512 106 | size=3 107 | stride=1 108 | pad=1 109 | activation=leaky 110 | 111 | [convolutional] 112 | filters=256 113 | size=1 114 | stride=1 115 | pad=1 116 | activation=leaky 117 | 118 | [convolutional] 119 | filters=512 120 | size=3 121 | stride=1 122 | pad=1 123 | activation=leaky 124 | 125 | [convolutional] 126 | filters=512 127 | size=1 128 | stride=1 129 | pad=1 130 | activation=leaky 131 | 132 | [convolutional] 133 | filters=1024 134 | size=3 135 | stride=1 136 | pad=1 137 | activation=leaky 138 | 139 | [maxpool] 140 | size=2 141 | stride=2 142 | 143 | [convolutional] 144 | filters=512 145 | size=1 146 | stride=1 147 | pad=1 148 | activation=leaky 149 | 150 | [convolutional] 151 | filters=1024 152 | size=3 153 | stride=1 154 | pad=1 155 | activation=leaky 156 | 157 | [convolutional] 158 | filters=512 159 | size=1 160 | stride=1 161 | pad=1 162 | activation=leaky 163 | 164 | [convolutional] 165 | filters=1024 166 | size=3 167 | stride=1 168 | pad=1 169 | activation=leaky 170 | 171 | [avgpool] 172 | 173 | [connected] 174 | output=1000 175 | activation=leaky 176 | 177 | [softmax] 178 | groups=1 179 | 180 | -------------------------------------------------------------------------------- /cfg/tiny-yolo-4c.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=8 4 | width=416 5 | height=416 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | angle=0 10 | saturation = 1.5 11 | exposure = 1.5 12 | hue=.1 13 | 14 | learning_rate=0.001 15 | max_batches = 40100 16 | policy=steps 17 | steps=-1,100,20000,30000 18 | scales=.1,10,.1,.1 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=1 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | filters=1024 95 | size=3 96 | stride=1 97 | pad=1 98 | activation=leaky 99 | 100 | ########### 101 | 102 | [convolutional] 103 | batch_normalize=1 104 | size=3 105 | stride=1 106 | pad=1 107 | filters=1024 108 | activation=leaky 109 | 110 | [convolutional] 111 | size=1 112 | stride=1 113 | pad=1 114 | filters=45 115 | activation=linear 116 | 117 | [region] 118 | anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 119 | bias_match=1 120 | classes=4 121 | coords=4 122 | num=5 123 | softmax=1 124 | jitter=.2 125 | rescore=1 126 | 127 | object_scale=5 128 | noobject_scale=1 129 | class_scale=1 130 | coord_scale=1 131 | 132 | absolute=1 133 | thresh=.6 134 | random=1 135 | -------------------------------------------------------------------------------- /cfg/tiny-yolo-voc.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=8 4 | width=416 5 | height=416 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | angle=0 10 | saturation = 1.5 11 | exposure = 1.5 12 | hue=.1 13 | 14 | learning_rate=0.001 15 | max_batches = 40100 16 | policy=steps 17 | steps=-1,100,20000,30000 18 | scales=.1,10,.1,.1 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=1 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | filters=1024 95 | size=3 96 | stride=1 97 | pad=1 98 | activation=leaky 99 | 100 | ########### 101 | 102 | [convolutional] 103 | batch_normalize=1 104 | size=3 105 | stride=1 106 | pad=1 107 | filters=1024 108 | activation=leaky 109 | 110 | [convolutional] 111 | size=1 112 | stride=1 113 | pad=1 114 | filters=125 115 | activation=linear 116 | 117 | [region] 118 | anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 119 | bias_match=1 120 | classes=20 121 | coords=4 122 | num=5 123 | softmax=1 124 | jitter=.2 125 | rescore=1 126 | 127 | object_scale=5 128 | noobject_scale=1 129 | class_scale=1 130 | coord_scale=1 131 | 132 | absolute=1 133 | thresh = .5 134 | random=1 135 | -------------------------------------------------------------------------------- /cfg/tiny-yolo.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=8 4 | width=416 5 | height=416 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | angle=0 10 | saturation = 1.5 11 | exposure = 1.5 12 | hue=.1 13 | 14 | learning_rate=0.001 15 | max_batches = 120000 16 | policy=steps 17 | steps=-1,100,80000,100000 18 | scales=.1,10,.1,.1 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=1 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | filters=1024 95 | size=3 96 | stride=1 97 | pad=1 98 | activation=leaky 99 | 100 | ########### 101 | 102 | [convolutional] 103 | batch_normalize=1 104 | size=3 105 | stride=1 106 | pad=1 107 | filters=1024 108 | activation=leaky 109 | 110 | [convolutional] 111 | size=1 112 | stride=1 113 | pad=1 114 | filters=425 115 | activation=linear 116 | 117 | [region] 118 | anchors = 0.738768,0.874946, 2.42204,2.65704, 4.30971,7.04493, 10.246,4.59428, 12.6868,11.8741 119 | bias_match=1 120 | classes=80 121 | coords=4 122 | num=5 123 | softmax=1 124 | jitter=.2 125 | rescore=1 126 | 127 | object_scale=5 128 | noobject_scale=1 129 | class_scale=1 130 | coord_scale=1 131 | 132 | absolute=1 133 | thresh = .6 134 | random=1 135 | -------------------------------------------------------------------------------- /cfg/v1.1/person-bottle.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=2 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | saturation=.75 11 | exposure=.75 12 | hue = .1 13 | 14 | learning_rate=0.0005 15 | policy=steps 16 | steps=200,400,600,800,20000,30000 17 | scales=2.5,2,2,2,.1,.1 18 | max_batches = 40000 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=2 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | size=3 95 | stride=1 96 | pad=1 97 | filters=1024 98 | activation=leaky 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | size=3 103 | stride=1 104 | pad=1 105 | filters=256 106 | activation=leaky 107 | 108 | [select] 109 | old_output=1470 110 | keep=4,14/20 111 | bins=49 112 | output=588 113 | activation=linear 114 | 115 | [detection] 116 | classes=2 117 | coords=4 118 | rescore=1 119 | side=7 120 | num=2 121 | softmax=0 122 | sqrt=1 123 | jitter=.2 124 | 125 | object_scale=1 126 | noobject_scale=.5 127 | class_scale=1 128 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1.1/tiny-coco.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=2 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | hue = .1 11 | saturation=.75 12 | exposure=.75 13 | 14 | learning_rate=0.0005 15 | policy=steps 16 | steps=200,400,600,800,100000,150000 17 | scales=2.5,2,2,2,.1,.1 18 | max_batches = 200000 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=2 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | size=3 95 | stride=1 96 | pad=1 97 | filters=1024 98 | activation=leaky 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | size=3 103 | stride=1 104 | pad=1 105 | filters=256 106 | activation=leaky 107 | 108 | [connected] 109 | output= 4655 110 | activation=linear 111 | 112 | [detection] 113 | classes=80 114 | coords=4 115 | rescore=1 116 | side=7 117 | num=3 118 | softmax=0 119 | sqrt=1 120 | jitter=.2 121 | 122 | object_scale=1 123 | noobject_scale=.5 124 | class_scale=1 125 | coord_scale=5 126 | -------------------------------------------------------------------------------- /cfg/v1.1/tiny-yolo-4c.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=2 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | saturation=.75 11 | exposure=.75 12 | hue = .1 13 | 14 | learning_rate=0.0005 15 | policy=steps 16 | steps=200,400,600,800,20000,30000 17 | scales=2.5,2,2,2,.1,.1 18 | max_batches = 40000 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=2 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | size=3 95 | stride=1 96 | pad=1 97 | filters=1024 98 | activation=leaky 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | size=3 103 | stride=1 104 | pad=1 105 | filters=256 106 | activation=leaky 107 | 108 | [select] 109 | old_output=1470 110 | keep=8,14,15,19/20 111 | bins=49 112 | output=686 113 | activation=linear 114 | 115 | [detection] 116 | classes=4 117 | coords=4 118 | rescore=1 119 | side=7 120 | num=2 121 | softmax=0 122 | sqrt=1 123 | jitter=.2 124 | 125 | object_scale=1 126 | noobject_scale=.5 127 | class_scale=1 128 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1.1/tiny-yolov1.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=2 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | saturation=.75 11 | exposure=.75 12 | hue = .1 13 | 14 | learning_rate=0.0005 15 | policy=steps 16 | steps=200,400,600,800,20000,30000 17 | scales=2.5,2,2,2,.1,.1 18 | max_batches = 40000 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=16 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=32 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=64 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [maxpool] 53 | size=2 54 | stride=2 55 | 56 | [convolutional] 57 | batch_normalize=1 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=256 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=512 83 | size=3 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [maxpool] 89 | size=2 90 | stride=2 91 | 92 | [convolutional] 93 | batch_normalize=1 94 | size=3 95 | stride=1 96 | pad=1 97 | filters=1024 98 | activation=leaky 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | size=3 103 | stride=1 104 | pad=1 105 | filters=256 106 | activation=leaky 107 | 108 | [connected] 109 | output= 1470 110 | activation=linear 111 | 112 | [detection] 113 | classes=20 114 | coords=4 115 | rescore=1 116 | side=7 117 | num=2 118 | softmax=0 119 | sqrt=1 120 | jitter=.2 121 | 122 | object_scale=1 123 | noobject_scale=.5 124 | class_scale=1 125 | coord_scale=5 126 | 127 | -------------------------------------------------------------------------------- /cfg/v1.1/yolo-coco.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=4 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | hue = .1 11 | saturation=.75 12 | exposure=.75 13 | 14 | learning_rate=0.0005 15 | policy=steps 16 | steps=200,400,600,800,100000,150000 17 | scales=2.5,2,2,2,.1,.1 18 | max_batches = 200000 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=64 23 | size=7 24 | stride=2 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=192 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=128 47 | size=1 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [convolutional] 53 | batch_normalize=1 54 | filters=256 55 | size=3 56 | stride=1 57 | pad=1 58 | activation=leaky 59 | 60 | [convolutional] 61 | batch_normalize=1 62 | filters=256 63 | size=1 64 | stride=1 65 | pad=1 66 | activation=leaky 67 | 68 | [convolutional] 69 | batch_normalize=1 70 | filters=512 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=256 83 | size=1 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [convolutional] 89 | batch_normalize=1 90 | filters=512 91 | size=3 92 | stride=1 93 | pad=1 94 | activation=leaky 95 | 96 | [convolutional] 97 | batch_normalize=1 98 | filters=256 99 | size=1 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [convolutional] 105 | batch_normalize=1 106 | filters=512 107 | size=3 108 | stride=1 109 | pad=1 110 | activation=leaky 111 | 112 | [convolutional] 113 | batch_normalize=1 114 | filters=256 115 | size=1 116 | stride=1 117 | pad=1 118 | activation=leaky 119 | 120 | [convolutional] 121 | batch_normalize=1 122 | filters=512 123 | size=3 124 | stride=1 125 | pad=1 126 | activation=leaky 127 | 128 | [convolutional] 129 | batch_normalize=1 130 | filters=256 131 | size=1 132 | stride=1 133 | pad=1 134 | activation=leaky 135 | 136 | [convolutional] 137 | batch_normalize=1 138 | filters=512 139 | size=3 140 | stride=1 141 | pad=1 142 | activation=leaky 143 | 144 | [convolutional] 145 | batch_normalize=1 146 | filters=512 147 | size=1 148 | stride=1 149 | pad=1 150 | activation=leaky 151 | 152 | [convolutional] 153 | batch_normalize=1 154 | filters=1024 155 | size=3 156 | stride=1 157 | pad=1 158 | activation=leaky 159 | 160 | [maxpool] 161 | size=2 162 | stride=2 163 | 164 | [convolutional] 165 | batch_normalize=1 166 | filters=512 167 | size=1 168 | stride=1 169 | pad=1 170 | activation=leaky 171 | 172 | [convolutional] 173 | batch_normalize=1 174 | filters=1024 175 | size=3 176 | stride=1 177 | pad=1 178 | activation=leaky 179 | 180 | [convolutional] 181 | batch_normalize=1 182 | filters=512 183 | size=1 184 | stride=1 185 | pad=1 186 | activation=leaky 187 | 188 | [convolutional] 189 | batch_normalize=1 190 | filters=1024 191 | size=3 192 | stride=1 193 | pad=1 194 | activation=leaky 195 | 196 | ####### 197 | 198 | [convolutional] 199 | batch_normalize=1 200 | size=3 201 | stride=1 202 | pad=1 203 | filters=1024 204 | activation=leaky 205 | 206 | [convolutional] 207 | batch_normalize=1 208 | size=3 209 | stride=2 210 | pad=1 211 | filters=1024 212 | activation=leaky 213 | 214 | [convolutional] 215 | batch_normalize=1 216 | size=3 217 | stride=1 218 | pad=1 219 | filters=1024 220 | activation=leaky 221 | 222 | [convolutional] 223 | batch_normalize=1 224 | size=3 225 | stride=1 226 | pad=1 227 | filters=1024 228 | activation=leaky 229 | 230 | [local] 231 | size=3 232 | stride=1 233 | pad=1 234 | filters=256 235 | activation=leaky 236 | 237 | [connected] 238 | output= 4655 239 | activation=linear 240 | 241 | [detection] 242 | classes=80 243 | coords=4 244 | rescore=1 245 | side=7 246 | num=3 247 | softmax=0 248 | sqrt=1 249 | jitter=.2 250 | 251 | object_scale=1 252 | noobject_scale=.5 253 | class_scale=1 254 | coord_scale=5 255 | 256 | -------------------------------------------------------------------------------- /cfg/v1.1/yolov1.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=1 3 | subdivisions=1 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | saturation=1.5 10 | exposure=1.5 11 | hue=.1 12 | 13 | learning_rate=0.0005 14 | policy=steps 15 | steps=200,400,600,20000,30000 16 | scales=2.5,2,2,.1,.1 17 | max_batches = 40000 18 | 19 | [convolutional] 20 | batch_normalize=1 21 | filters=64 22 | size=7 23 | stride=2 24 | pad=1 25 | activation=leaky 26 | 27 | [maxpool] 28 | size=2 29 | stride=2 30 | 31 | [convolutional] 32 | batch_normalize=1 33 | filters=192 34 | size=3 35 | stride=1 36 | pad=1 37 | activation=leaky 38 | 39 | [maxpool] 40 | size=2 41 | stride=2 42 | 43 | [convolutional] 44 | batch_normalize=1 45 | filters=128 46 | size=1 47 | stride=1 48 | pad=1 49 | activation=leaky 50 | 51 | [convolutional] 52 | batch_normalize=1 53 | filters=256 54 | size=3 55 | stride=1 56 | pad=1 57 | activation=leaky 58 | 59 | [convolutional] 60 | batch_normalize=1 61 | filters=256 62 | size=1 63 | stride=1 64 | pad=1 65 | activation=leaky 66 | 67 | [convolutional] 68 | batch_normalize=1 69 | filters=512 70 | size=3 71 | stride=1 72 | pad=1 73 | activation=leaky 74 | 75 | [maxpool] 76 | size=2 77 | stride=2 78 | 79 | [convolutional] 80 | batch_normalize=1 81 | filters=256 82 | size=1 83 | stride=1 84 | pad=1 85 | activation=leaky 86 | 87 | [convolutional] 88 | batch_normalize=1 89 | filters=512 90 | size=3 91 | stride=1 92 | pad=1 93 | activation=leaky 94 | 95 | [convolutional] 96 | batch_normalize=1 97 | filters=256 98 | size=1 99 | stride=1 100 | pad=1 101 | activation=leaky 102 | 103 | [convolutional] 104 | batch_normalize=1 105 | filters=512 106 | size=3 107 | stride=1 108 | pad=1 109 | activation=leaky 110 | 111 | [convolutional] 112 | batch_normalize=1 113 | filters=256 114 | size=1 115 | stride=1 116 | pad=1 117 | activation=leaky 118 | 119 | [convolutional] 120 | batch_normalize=1 121 | filters=512 122 | size=3 123 | stride=1 124 | pad=1 125 | activation=leaky 126 | 127 | [convolutional] 128 | batch_normalize=1 129 | filters=256 130 | size=1 131 | stride=1 132 | pad=1 133 | activation=leaky 134 | 135 | [convolutional] 136 | batch_normalize=1 137 | filters=512 138 | size=3 139 | stride=1 140 | pad=1 141 | activation=leaky 142 | 143 | [convolutional] 144 | batch_normalize=1 145 | filters=512 146 | size=1 147 | stride=1 148 | pad=1 149 | activation=leaky 150 | 151 | [convolutional] 152 | batch_normalize=1 153 | filters=1024 154 | size=3 155 | stride=1 156 | pad=1 157 | activation=leaky 158 | 159 | [maxpool] 160 | size=2 161 | stride=2 162 | 163 | [convolutional] 164 | batch_normalize=1 165 | filters=512 166 | size=1 167 | stride=1 168 | pad=1 169 | activation=leaky 170 | 171 | [convolutional] 172 | batch_normalize=1 173 | filters=1024 174 | size=3 175 | stride=1 176 | pad=1 177 | activation=leaky 178 | 179 | [convolutional] 180 | batch_normalize=1 181 | filters=512 182 | size=1 183 | stride=1 184 | pad=1 185 | activation=leaky 186 | 187 | [convolutional] 188 | batch_normalize=1 189 | filters=1024 190 | size=3 191 | stride=1 192 | pad=1 193 | activation=leaky 194 | 195 | ####### 196 | 197 | [convolutional] 198 | batch_normalize=1 199 | size=3 200 | stride=1 201 | pad=1 202 | filters=1024 203 | activation=leaky 204 | 205 | [convolutional] 206 | batch_normalize=1 207 | size=3 208 | stride=2 209 | pad=1 210 | filters=1024 211 | activation=leaky 212 | 213 | [convolutional] 214 | batch_normalize=1 215 | size=3 216 | stride=1 217 | pad=1 218 | filters=1024 219 | activation=leaky 220 | 221 | [convolutional] 222 | batch_normalize=1 223 | size=3 224 | stride=1 225 | pad=1 226 | filters=1024 227 | activation=leaky 228 | 229 | [local] 230 | size=3 231 | stride=1 232 | pad=1 233 | filters=256 234 | activation=leaky 235 | 236 | [dropout] 237 | probability=.5 238 | 239 | [connected] 240 | output= 1715 241 | activation=linear 242 | 243 | [detection] 244 | classes=20 245 | coords=4 246 | rescore=1 247 | side=7 248 | num=3 249 | softmax=0 250 | sqrt=1 251 | jitter=.2 252 | 253 | object_scale=1 254 | noobject_scale=.5 255 | class_scale=1 256 | coord_scale=5 257 | 258 | -------------------------------------------------------------------------------- /cfg/v1/tiny-old.profile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/cfg/v1/tiny-old.profile -------------------------------------------------------------------------------- /cfg/v1/tiny.profile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/cfg/v1/tiny.profile -------------------------------------------------------------------------------- /cfg/v1/yolo-2c.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.0001 11 | policy=steps 12 | steps=20,40,60,80,20000,30000 13 | scales=5,5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=16 26 | size=3 27 | stride=1 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=32 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=64 48 | size=3 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [maxpool] 54 | size=2 55 | stride=2 56 | 57 | [convolutional] 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | filters=256 70 | size=3 71 | stride=1 72 | pad=1 73 | activation=leaky 74 | 75 | [maxpool] 76 | size=2 77 | stride=2 78 | 79 | [convolutional] 80 | filters=512 81 | size=3 82 | stride=1 83 | pad=1 84 | activation=leaky 85 | 86 | [maxpool] 87 | size=2 88 | stride=2 89 | 90 | [convolutional] 91 | filters=1024 92 | size=3 93 | stride=1 94 | pad=1 95 | activation=leaky 96 | 97 | [convolutional] 98 | filters=1024 99 | size=3 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [convolutional] 105 | filters=1024 106 | size=3 107 | stride=1 108 | pad=1 109 | activation=leaky 110 | 111 | [connected] 112 | output=256 113 | activation=linear 114 | 115 | [connected] 116 | output=4096 117 | activation=leaky 118 | 119 | [dropout] 120 | probability=.5 121 | 122 | [select] 123 | old_output=1470 124 | keep=14,19/20 125 | bins=49 126 | output=588 127 | activation=linear 128 | 129 | [detection] 130 | classes=2 131 | coords=4 132 | rescore=1 133 | side=7 134 | num=2 135 | softmax=0 136 | sqrt=1 137 | jitter=.2 138 | object_scale=1 139 | noobject_scale=.5 140 | class_scale=1 141 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1/yolo-4c.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.001 11 | policy=steps 12 | steps=200,400,600,20000,30000 13 | scales=2.5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=64 26 | size=7 27 | stride=2 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=192 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=128 48 | size=1 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [convolutional] 54 | filters=256 55 | size=3 56 | stride=1 57 | pad=1 58 | activation=leaky 59 | 60 | [convolutional] 61 | filters=256 62 | size=1 63 | stride=1 64 | pad=1 65 | activation=leaky 66 | 67 | [convolutional] 68 | filters=512 69 | size=3 70 | stride=1 71 | pad=1 72 | activation=leaky 73 | 74 | [maxpool] 75 | size=2 76 | stride=2 77 | 78 | [convolutional] 79 | filters=256 80 | size=1 81 | stride=1 82 | pad=1 83 | activation=leaky 84 | 85 | [convolutional] 86 | filters=512 87 | size=3 88 | stride=1 89 | pad=1 90 | activation=leaky 91 | 92 | [convolutional] 93 | filters=256 94 | size=1 95 | stride=1 96 | pad=1 97 | activation=leaky 98 | 99 | [convolutional] 100 | filters=512 101 | size=3 102 | stride=1 103 | pad=1 104 | activation=leaky 105 | 106 | [convolutional] 107 | filters=256 108 | size=1 109 | stride=1 110 | pad=1 111 | activation=leaky 112 | 113 | [convolutional] 114 | filters=512 115 | size=3 116 | stride=1 117 | pad=1 118 | activation=leaky 119 | 120 | [convolutional] 121 | filters=256 122 | size=1 123 | stride=1 124 | pad=1 125 | activation=leaky 126 | 127 | [convolutional] 128 | filters=512 129 | size=3 130 | stride=1 131 | pad=1 132 | activation=leaky 133 | 134 | [convolutional] 135 | filters=512 136 | size=1 137 | stride=1 138 | pad=1 139 | activation=leaky 140 | 141 | [convolutional] 142 | filters=1024 143 | size=3 144 | stride=1 145 | pad=1 146 | activation=leaky 147 | 148 | [maxpool] 149 | size=2 150 | stride=2 151 | 152 | [convolutional] 153 | filters=512 154 | size=1 155 | stride=1 156 | pad=1 157 | activation=leaky 158 | 159 | [convolutional] 160 | filters=1024 161 | size=3 162 | stride=1 163 | pad=1 164 | activation=leaky 165 | 166 | [convolutional] 167 | filters=512 168 | size=1 169 | stride=1 170 | pad=1 171 | activation=leaky 172 | 173 | [convolutional] 174 | filters=1024 175 | size=3 176 | stride=1 177 | pad=1 178 | activation=leaky 179 | 180 | ####### 181 | 182 | [convolutional] 183 | size=3 184 | stride=1 185 | pad=1 186 | filters=1024 187 | activation=leaky 188 | 189 | [convolutional] 190 | size=3 191 | stride=2 192 | pad=1 193 | filters=1024 194 | activation=leaky 195 | 196 | [convolutional] 197 | size=3 198 | stride=1 199 | pad=1 200 | filters=1024 201 | activation=leaky 202 | 203 | [convolutional] 204 | size=3 205 | stride=1 206 | pad=1 207 | filters=1024 208 | activation=leaky 209 | 210 | [connected] 211 | output=4096 212 | activation=leaky 213 | 214 | [dropout] 215 | probability=.5 216 | 217 | [select] 218 | old_output=1470 219 | keep=8,14,15,19/20 220 | bins=49 221 | output=686 222 | activation=linear 223 | 224 | [detection] 225 | classes=4 226 | coords=4 227 | rescore=1 228 | side=7 229 | num=2 230 | softmax=0 231 | sqrt=1 232 | jitter=.2 233 | 234 | object_scale=1 235 | noobject_scale=.5 236 | class_scale=1 237 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1/yolo-full.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.001 11 | policy=steps 12 | steps=200,400,600,20000,30000 13 | scales=2.5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=64 26 | size=7 27 | stride=2 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=192 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=128 48 | size=1 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [convolutional] 54 | filters=256 55 | size=3 56 | stride=1 57 | pad=1 58 | activation=leaky 59 | 60 | [convolutional] 61 | filters=256 62 | size=1 63 | stride=1 64 | pad=1 65 | activation=leaky 66 | 67 | [convolutional] 68 | filters=512 69 | size=3 70 | stride=1 71 | pad=1 72 | activation=leaky 73 | 74 | [maxpool] 75 | size=2 76 | stride=2 77 | 78 | [convolutional] 79 | filters=256 80 | size=1 81 | stride=1 82 | pad=1 83 | activation=leaky 84 | 85 | [convolutional] 86 | filters=512 87 | size=3 88 | stride=1 89 | pad=1 90 | activation=leaky 91 | 92 | [convolutional] 93 | filters=256 94 | size=1 95 | stride=1 96 | pad=1 97 | activation=leaky 98 | 99 | [convolutional] 100 | filters=512 101 | size=3 102 | stride=1 103 | pad=1 104 | activation=leaky 105 | 106 | [convolutional] 107 | filters=256 108 | size=1 109 | stride=1 110 | pad=1 111 | activation=leaky 112 | 113 | [convolutional] 114 | filters=512 115 | size=3 116 | stride=1 117 | pad=1 118 | activation=leaky 119 | 120 | [convolutional] 121 | filters=256 122 | size=1 123 | stride=1 124 | pad=1 125 | activation=leaky 126 | 127 | [convolutional] 128 | filters=512 129 | size=3 130 | stride=1 131 | pad=1 132 | activation=leaky 133 | 134 | [convolutional] 135 | filters=512 136 | size=1 137 | stride=1 138 | pad=1 139 | activation=leaky 140 | 141 | [convolutional] 142 | filters=1024 143 | size=3 144 | stride=1 145 | pad=1 146 | activation=leaky 147 | 148 | [maxpool] 149 | size=2 150 | stride=2 151 | 152 | [convolutional] 153 | filters=512 154 | size=1 155 | stride=1 156 | pad=1 157 | activation=leaky 158 | 159 | [convolutional] 160 | filters=1024 161 | size=3 162 | stride=1 163 | pad=1 164 | activation=leaky 165 | 166 | [convolutional] 167 | filters=512 168 | size=1 169 | stride=1 170 | pad=1 171 | activation=leaky 172 | 173 | [convolutional] 174 | filters=1024 175 | size=3 176 | stride=1 177 | pad=1 178 | activation=leaky 179 | 180 | ####### 181 | 182 | [convolutional] 183 | size=3 184 | stride=1 185 | pad=1 186 | filters=1024 187 | activation=leaky 188 | 189 | [convolutional] 190 | size=3 191 | stride=2 192 | pad=1 193 | filters=1024 194 | activation=leaky 195 | 196 | [convolutional] 197 | size=3 198 | stride=1 199 | pad=1 200 | filters=1024 201 | activation=leaky 202 | 203 | [convolutional] 204 | size=3 205 | stride=1 206 | pad=1 207 | filters=1024 208 | activation=leaky 209 | 210 | [connected] 211 | output=4096 212 | activation=leaky 213 | 214 | [dropout] 215 | probability=.5 216 | 217 | [connected] 218 | output= 1470 219 | activation=linear 220 | 221 | [detection] 222 | classes=20 223 | coords=4 224 | rescore=1 225 | side=7 226 | num=2 227 | softmax=0 228 | sqrt=1 229 | jitter=.2 230 | 231 | object_scale=1 232 | noobject_scale=.5 233 | class_scale=1 234 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1/yolo-small.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.001 11 | policy=steps 12 | steps=200,400,600,20000,30000 13 | scales=2.5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=64 26 | size=7 27 | stride=2 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=192 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=128 48 | size=1 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [convolutional] 54 | filters=256 55 | size=3 56 | stride=1 57 | pad=1 58 | activation=leaky 59 | 60 | [convolutional] 61 | filters=256 62 | size=1 63 | stride=1 64 | pad=1 65 | activation=leaky 66 | 67 | [convolutional] 68 | filters=512 69 | size=3 70 | stride=1 71 | pad=1 72 | activation=leaky 73 | 74 | [maxpool] 75 | size=2 76 | stride=2 77 | 78 | [convolutional] 79 | filters=256 80 | size=1 81 | stride=1 82 | pad=1 83 | activation=leaky 84 | 85 | [convolutional] 86 | filters=512 87 | size=3 88 | stride=1 89 | pad=1 90 | activation=leaky 91 | 92 | [convolutional] 93 | filters=256 94 | size=1 95 | stride=1 96 | pad=1 97 | activation=leaky 98 | 99 | [convolutional] 100 | filters=512 101 | size=3 102 | stride=1 103 | pad=1 104 | activation=leaky 105 | 106 | [convolutional] 107 | filters=256 108 | size=1 109 | stride=1 110 | pad=1 111 | activation=leaky 112 | 113 | [convolutional] 114 | filters=512 115 | size=3 116 | stride=1 117 | pad=1 118 | activation=leaky 119 | 120 | [convolutional] 121 | filters=256 122 | size=1 123 | stride=1 124 | pad=1 125 | activation=leaky 126 | 127 | [convolutional] 128 | filters=512 129 | size=3 130 | stride=1 131 | pad=1 132 | activation=leaky 133 | 134 | [convolutional] 135 | filters=512 136 | size=1 137 | stride=1 138 | pad=1 139 | activation=leaky 140 | 141 | [convolutional] 142 | filters=1024 143 | size=3 144 | stride=1 145 | pad=1 146 | activation=leaky 147 | 148 | [maxpool] 149 | size=2 150 | stride=2 151 | 152 | [convolutional] 153 | filters=512 154 | size=1 155 | stride=1 156 | pad=1 157 | activation=leaky 158 | 159 | [convolutional] 160 | filters=1024 161 | size=3 162 | stride=1 163 | pad=1 164 | activation=leaky 165 | 166 | [convolutional] 167 | filters=512 168 | size=1 169 | stride=1 170 | pad=1 171 | activation=leaky 172 | 173 | [convolutional] 174 | filters=1024 175 | size=3 176 | stride=1 177 | pad=1 178 | activation=leaky 179 | 180 | ####### 181 | 182 | [convolutional] 183 | size=3 184 | stride=1 185 | pad=1 186 | filters=1024 187 | activation=leaky 188 | 189 | [convolutional] 190 | size=3 191 | stride=2 192 | pad=1 193 | filters=1024 194 | activation=leaky 195 | 196 | [convolutional] 197 | size=3 198 | stride=1 199 | pad=1 200 | filters=1024 201 | activation=leaky 202 | 203 | [convolutional] 204 | size=3 205 | stride=1 206 | pad=1 207 | filters=1024 208 | activation=leaky 209 | 210 | [connected] 211 | output=512 212 | activation=leaky 213 | 214 | [connected] 215 | output=4096 216 | activation=leaky 217 | 218 | [dropout] 219 | probability=.5 220 | 221 | [connected] 222 | output= 1470 223 | activation=linear 224 | 225 | [detection] 226 | classes=20 227 | coords=4 228 | rescore=1 229 | side=7 230 | num=2 231 | softmax=0 232 | sqrt=1 233 | jitter=.2 234 | 235 | object_scale=1 236 | noobject_scale=.5 237 | class_scale=1 238 | coord_scale=5 239 | 240 | -------------------------------------------------------------------------------- /cfg/v1/yolo-tiny-extract.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.0001 11 | policy=steps 12 | steps=20,40,60,80,20000,30000 13 | scales=5,5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [conv-extract] 25 | profile=cfg/v1/tiny.profile 26 | input=-1 27 | output=0 28 | filters=16 29 | size=3 30 | stride=1 31 | pad=1 32 | activation=leaky 33 | 34 | [maxpool] 35 | size=2 36 | stride=2 37 | 38 | [conv-extract] 39 | profile=cfg/v1/tiny.profile 40 | input=0 41 | output=1 42 | filters=32 43 | size=3 44 | stride=1 45 | pad=1 46 | activation=leaky 47 | 48 | [maxpool] 49 | size=2 50 | stride=2 51 | 52 | [conv-extract] 53 | profile=cfg/v1/tiny.profile 54 | input=1 55 | output=2 56 | filters=64 57 | size=3 58 | stride=1 59 | pad=1 60 | activation=leaky 61 | 62 | [maxpool] 63 | size=2 64 | stride=2 65 | 66 | [conv-extract] 67 | profile=cfg/v1/tiny.profile 68 | input=2 69 | output=3 70 | filters=128 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [conv-extract] 81 | profile=cfg/v1/tiny.profile 82 | input=3 83 | output=4 84 | filters=256 85 | size=3 86 | stride=1 87 | pad=1 88 | activation=leaky 89 | 90 | [maxpool] 91 | size=2 92 | stride=2 93 | 94 | [conv-extract] 95 | profile=cfg/v1/tiny.profile 96 | input=4 97 | output=5 98 | filters=512 99 | size=3 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [maxpool] 105 | size=2 106 | stride=2 107 | 108 | [conv-extract] 109 | profile=cfg/v1/tiny.profile 110 | input=5 111 | output=6 112 | filters=1024 113 | size=3 114 | stride=1 115 | pad=1 116 | activation=leaky 117 | 118 | [conv-extract] 119 | profile=cfg/v1/tiny.profile 120 | input=6 121 | output=7 122 | filters=1024 123 | size=3 124 | stride=1 125 | pad=1 126 | activation=leaky 127 | 128 | [conv-extract] 129 | profile=cfg/v1/tiny.profile 130 | input=7 131 | output=8 132 | filters=1024 133 | size=3 134 | stride=1 135 | pad=1 136 | activation=leaky 137 | 138 | [extract] 139 | profile=cfg/v1/tiny.profile 140 | input=8 141 | output=9 142 | old=7,7,1024,256 143 | activation=linear 144 | 145 | [extract] 146 | profile=cfg/v1/tiny.profile 147 | input=9 148 | output=10 149 | old=256,4096 150 | activation=leaky 151 | 152 | [dropout] 153 | probability=1. 154 | 155 | [select] 156 | input=cfg/v1/tiny.profile,10 157 | old_output=1470 158 | keep=8,14,15,19/20 159 | bins=49 160 | output=686 161 | activation=linear 162 | 163 | [detection] 164 | classes=4 165 | coords=4 166 | rescore=1 167 | side=7 168 | num=2 169 | softmax=0 170 | sqrt=1 171 | jitter=.2 172 | object_scale=1 173 | noobject_scale=.5 174 | class_scale=1 175 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1/yolo-tiny-extract_.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.0001 11 | policy=steps 12 | steps=20,40,60,80,20000,30000 13 | scales=5,5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [conv-extract] 25 | profile=cfg/v1/tiny-old.profile 26 | input=-1 27 | output=0 28 | filters=16 29 | size=3 30 | stride=1 31 | pad=1 32 | activation=leaky 33 | 34 | [maxpool] 35 | size=2 36 | stride=2 37 | 38 | [conv-extract] 39 | profile=cfg/v1/tiny-old.profile 40 | input=0 41 | output=1 42 | filters=32 43 | size=3 44 | stride=1 45 | pad=1 46 | activation=leaky 47 | 48 | [maxpool] 49 | size=2 50 | stride=2 51 | 52 | [conv-extract] 53 | profile=cfg/v1/tiny-old.profile 54 | input=1 55 | output=2 56 | filters=64 57 | size=3 58 | stride=1 59 | pad=1 60 | activation=leaky 61 | 62 | [maxpool] 63 | size=2 64 | stride=2 65 | 66 | [conv-extract] 67 | profile=cfg/v1/tiny-old.profile 68 | input=2 69 | output=3 70 | filters=128 71 | size=3 72 | stride=1 73 | pad=1 74 | activation=leaky 75 | 76 | [maxpool] 77 | size=2 78 | stride=2 79 | 80 | [conv-extract] 81 | profile=cfg/v1/tiny-old.profile 82 | input=3 83 | output=4 84 | filters=256 85 | size=3 86 | stride=1 87 | pad=1 88 | activation=leaky 89 | 90 | [maxpool] 91 | size=2 92 | stride=2 93 | 94 | [conv-extract] 95 | profile=cfg/v1/tiny-old.profile 96 | input=4 97 | output=5 98 | filters=512 99 | size=3 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [maxpool] 105 | size=2 106 | stride=2 107 | 108 | [conv-extract] 109 | profile=cfg/v1/tiny-old.profile 110 | input=5 111 | output=6 112 | filters=1024 113 | size=3 114 | stride=1 115 | pad=1 116 | activation=leaky 117 | 118 | [conv-extract] 119 | profile=cfg/v1/tiny-old.profile 120 | input=6 121 | output=7 122 | filters=1024 123 | size=3 124 | stride=1 125 | pad=1 126 | activation=leaky 127 | 128 | [conv-extract] 129 | profile=cfg/v1/tiny-old.profile 130 | input=7 131 | output=8 132 | filters=1024 133 | size=3 134 | stride=1 135 | pad=1 136 | activation=leaky 137 | 138 | [extract] 139 | profile=cfg/v1/tiny-old.profile 140 | input=8 141 | output=9 142 | old=7,7,1024,256 143 | activation=linear 144 | 145 | [extract] 146 | profile=cfg/v1/tiny-old.profile 147 | input=9 148 | output=10 149 | old=256,4096 150 | activation=leaky 151 | 152 | [dropout] 153 | probability=1. 154 | 155 | [select] 156 | input=cfg/v1/tiny-old.profile,10 157 | old_output=1470 158 | keep=8,14,15,19/20 159 | bins=49 160 | output=686 161 | activation=linear 162 | 163 | [detection] 164 | classes=4 165 | coords=4 166 | rescore=1 167 | side=7 168 | num=2 169 | softmax=0 170 | sqrt=1 171 | jitter=.2 172 | object_scale=2.5 173 | noobject_scale=2 174 | class_scale=2.5 175 | coord_scale=5 176 | 177 | save=11250 -------------------------------------------------------------------------------- /cfg/v1/yolo-tiny.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.0001 11 | policy=steps 12 | steps=20,40,60,80,20000,30000 13 | scales=5,5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=16 26 | size=3 27 | stride=1 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=32 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=64 48 | size=3 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [maxpool] 54 | size=2 55 | stride=2 56 | 57 | [convolutional] 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | filters=256 70 | size=3 71 | stride=1 72 | pad=1 73 | activation=leaky 74 | 75 | [maxpool] 76 | size=2 77 | stride=2 78 | 79 | [convolutional] 80 | filters=512 81 | size=3 82 | stride=1 83 | pad=1 84 | activation=leaky 85 | 86 | [maxpool] 87 | size=2 88 | stride=2 89 | 90 | [convolutional] 91 | filters=1024 92 | size=3 93 | stride=1 94 | pad=1 95 | activation=leaky 96 | 97 | [convolutional] 98 | filters=1024 99 | size=3 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [convolutional] 105 | filters=1024 106 | size=3 107 | stride=1 108 | pad=1 109 | activation=leaky 110 | 111 | [connected] 112 | output=256 113 | activation=linear 114 | 115 | [connected] 116 | output=4096 117 | activation=leaky 118 | 119 | [dropout] 120 | probability=.5 121 | 122 | [connected] 123 | output= 1470 124 | activation=linear 125 | 126 | [detection] 127 | classes=20 128 | coords=4 129 | rescore=1 130 | side=7 131 | num=2 132 | softmax=0 133 | sqrt=1 134 | jitter=.2 135 | object_scale=1 136 | noobject_scale=.5 137 | class_scale=1 138 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/v1/yolo-tiny4c.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=64 4 | height=448 5 | width=448 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | 10 | learning_rate=0.0001 11 | policy=steps 12 | steps=20,40,60,80,20000,30000 13 | scales=5,5,2,2,.1,.1 14 | max_batches = 40000 15 | 16 | [crop] 17 | crop_width=448 18 | crop_height=448 19 | flip=0 20 | angle=0 21 | saturation = 1.5 22 | exposure = 1.5 23 | 24 | [convolutional] 25 | filters=16 26 | size=3 27 | stride=1 28 | pad=1 29 | activation=leaky 30 | 31 | [maxpool] 32 | size=2 33 | stride=2 34 | 35 | [convolutional] 36 | filters=32 37 | size=3 38 | stride=1 39 | pad=1 40 | activation=leaky 41 | 42 | [maxpool] 43 | size=2 44 | stride=2 45 | 46 | [convolutional] 47 | filters=64 48 | size=3 49 | stride=1 50 | pad=1 51 | activation=leaky 52 | 53 | [maxpool] 54 | size=2 55 | stride=2 56 | 57 | [convolutional] 58 | filters=128 59 | size=3 60 | stride=1 61 | pad=1 62 | activation=leaky 63 | 64 | [maxpool] 65 | size=2 66 | stride=2 67 | 68 | [convolutional] 69 | filters=256 70 | size=3 71 | stride=1 72 | pad=1 73 | activation=leaky 74 | 75 | [maxpool] 76 | size=2 77 | stride=2 78 | 79 | [convolutional] 80 | filters=512 81 | size=3 82 | stride=1 83 | pad=1 84 | activation=leaky 85 | 86 | [maxpool] 87 | size=2 88 | stride=2 89 | 90 | [convolutional] 91 | filters=1024 92 | size=3 93 | stride=1 94 | pad=1 95 | activation=leaky 96 | 97 | [convolutional] 98 | filters=1024 99 | size=3 100 | stride=1 101 | pad=1 102 | activation=leaky 103 | 104 | [convolutional] 105 | filters=1024 106 | size=3 107 | stride=1 108 | pad=1 109 | activation=leaky 110 | 111 | [connected] 112 | output=256 113 | activation=linear 114 | 115 | [connected] 116 | output=4096 117 | activation=leaky 118 | 119 | [dropout] 120 | probability=.5 121 | 122 | [select] 123 | old_output=1470 124 | keep=8,14,15,19/20 125 | bins=49 126 | output=686 127 | activation=linear 128 | 129 | [detection] 130 | classes=4 131 | coords=4 132 | rescore=1 133 | side=7 134 | num=2 135 | softmax=0 136 | sqrt=1 137 | jitter=.2 138 | object_scale=1 139 | noobject_scale=.5 140 | class_scale=1 141 | coord_scale=5 -------------------------------------------------------------------------------- /cfg/yolo-voc.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | batch=64 3 | subdivisions=8 4 | height=416 5 | width=416 6 | channels=3 7 | momentum=0.9 8 | decay=0.0005 9 | angle=0 10 | saturation = 1.5 11 | exposure = 1.5 12 | hue=.1 13 | 14 | learning_rate=0.0001 15 | max_batches = 45000 16 | policy=steps 17 | steps=100,25000,35000 18 | scales=10,.1,.1 19 | 20 | [convolutional] 21 | batch_normalize=1 22 | filters=32 23 | size=3 24 | stride=1 25 | pad=1 26 | activation=leaky 27 | 28 | [maxpool] 29 | size=2 30 | stride=2 31 | 32 | [convolutional] 33 | batch_normalize=1 34 | filters=64 35 | size=3 36 | stride=1 37 | pad=1 38 | activation=leaky 39 | 40 | [maxpool] 41 | size=2 42 | stride=2 43 | 44 | [convolutional] 45 | batch_normalize=1 46 | filters=128 47 | size=3 48 | stride=1 49 | pad=1 50 | activation=leaky 51 | 52 | [convolutional] 53 | batch_normalize=1 54 | filters=64 55 | size=1 56 | stride=1 57 | pad=1 58 | activation=leaky 59 | 60 | [convolutional] 61 | batch_normalize=1 62 | filters=128 63 | size=3 64 | stride=1 65 | pad=1 66 | activation=leaky 67 | 68 | [maxpool] 69 | size=2 70 | stride=2 71 | 72 | [convolutional] 73 | batch_normalize=1 74 | filters=256 75 | size=3 76 | stride=1 77 | pad=1 78 | activation=leaky 79 | 80 | [convolutional] 81 | batch_normalize=1 82 | filters=128 83 | size=1 84 | stride=1 85 | pad=1 86 | activation=leaky 87 | 88 | [convolutional] 89 | batch_normalize=1 90 | filters=256 91 | size=3 92 | stride=1 93 | pad=1 94 | activation=leaky 95 | 96 | [maxpool] 97 | size=2 98 | stride=2 99 | 100 | [convolutional] 101 | batch_normalize=1 102 | filters=512 103 | size=3 104 | stride=1 105 | pad=1 106 | activation=leaky 107 | 108 | [convolutional] 109 | batch_normalize=1 110 | filters=256 111 | size=1 112 | stride=1 113 | pad=1 114 | activation=leaky 115 | 116 | [convolutional] 117 | batch_normalize=1 118 | filters=512 119 | size=3 120 | stride=1 121 | pad=1 122 | activation=leaky 123 | 124 | [convolutional] 125 | batch_normalize=1 126 | filters=256 127 | size=1 128 | stride=1 129 | pad=1 130 | activation=leaky 131 | 132 | [convolutional] 133 | batch_normalize=1 134 | filters=512 135 | size=3 136 | stride=1 137 | pad=1 138 | activation=leaky 139 | 140 | [maxpool] 141 | size=2 142 | stride=2 143 | 144 | [convolutional] 145 | batch_normalize=1 146 | filters=1024 147 | size=3 148 | stride=1 149 | pad=1 150 | activation=leaky 151 | 152 | [convolutional] 153 | batch_normalize=1 154 | filters=512 155 | size=1 156 | stride=1 157 | pad=1 158 | activation=leaky 159 | 160 | [convolutional] 161 | batch_normalize=1 162 | filters=1024 163 | size=3 164 | stride=1 165 | pad=1 166 | activation=leaky 167 | 168 | [convolutional] 169 | batch_normalize=1 170 | filters=512 171 | size=1 172 | stride=1 173 | pad=1 174 | activation=leaky 175 | 176 | [convolutional] 177 | batch_normalize=1 178 | filters=1024 179 | size=3 180 | stride=1 181 | pad=1 182 | activation=leaky 183 | 184 | 185 | ####### 186 | 187 | [convolutional] 188 | batch_normalize=1 189 | size=3 190 | stride=1 191 | pad=1 192 | filters=1024 193 | activation=leaky 194 | 195 | [convolutional] 196 | batch_normalize=1 197 | size=3 198 | stride=1 199 | pad=1 200 | filters=1024 201 | activation=leaky 202 | 203 | [route] 204 | layers=-9 205 | 206 | [reorg] 207 | stride=2 208 | 209 | [route] 210 | layers=-1,-3 211 | 212 | [convolutional] 213 | batch_normalize=1 214 | size=3 215 | stride=1 216 | pad=1 217 | filters=1024 218 | activation=leaky 219 | 220 | [convolutional] 221 | size=1 222 | stride=1 223 | pad=1 224 | filters=125 225 | activation=linear 226 | 227 | [region] 228 | anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 229 | bias_match=1 230 | classes=20 231 | coords=4 232 | num=5 233 | softmax=1 234 | jitter=.2 235 | rescore=1 236 | 237 | object_scale=5 238 | noobject_scale=1 239 | class_scale=1 240 | coord_scale=1 241 | 242 | absolute=1 243 | thresh = .6 244 | random=0 245 | -------------------------------------------------------------------------------- /cfg/yolo.cfg: -------------------------------------------------------------------------------- 1 | [net] 2 | # Testing 3 | batch=1 4 | subdivisions=1 5 | # Training 6 | # batch=64 7 | # subdivisions=8 8 | width=608 9 | height=608 10 | channels=3 11 | momentum=0.9 12 | decay=0.0005 13 | angle=0 14 | saturation = 1.5 15 | exposure = 1.5 16 | hue=.1 17 | 18 | learning_rate=0.001 19 | burn_in=1000 20 | max_batches = 500200 21 | policy=steps 22 | steps=400000,450000 23 | scales=.1,.1 24 | 25 | [convolutional] 26 | batch_normalize=1 27 | filters=32 28 | size=3 29 | stride=1 30 | pad=1 31 | activation=leaky 32 | 33 | [maxpool] 34 | size=2 35 | stride=2 36 | 37 | [convolutional] 38 | batch_normalize=1 39 | filters=64 40 | size=3 41 | stride=1 42 | pad=1 43 | activation=leaky 44 | 45 | [maxpool] 46 | size=2 47 | stride=2 48 | 49 | [convolutional] 50 | batch_normalize=1 51 | filters=128 52 | size=3 53 | stride=1 54 | pad=1 55 | activation=leaky 56 | 57 | [convolutional] 58 | batch_normalize=1 59 | filters=64 60 | size=1 61 | stride=1 62 | pad=1 63 | activation=leaky 64 | 65 | [convolutional] 66 | batch_normalize=1 67 | filters=128 68 | size=3 69 | stride=1 70 | pad=1 71 | activation=leaky 72 | 73 | [maxpool] 74 | size=2 75 | stride=2 76 | 77 | [convolutional] 78 | batch_normalize=1 79 | filters=256 80 | size=3 81 | stride=1 82 | pad=1 83 | activation=leaky 84 | 85 | [convolutional] 86 | batch_normalize=1 87 | filters=128 88 | size=1 89 | stride=1 90 | pad=1 91 | activation=leaky 92 | 93 | [convolutional] 94 | batch_normalize=1 95 | filters=256 96 | size=3 97 | stride=1 98 | pad=1 99 | activation=leaky 100 | 101 | [maxpool] 102 | size=2 103 | stride=2 104 | 105 | [convolutional] 106 | batch_normalize=1 107 | filters=512 108 | size=3 109 | stride=1 110 | pad=1 111 | activation=leaky 112 | 113 | [convolutional] 114 | batch_normalize=1 115 | filters=256 116 | size=1 117 | stride=1 118 | pad=1 119 | activation=leaky 120 | 121 | [convolutional] 122 | batch_normalize=1 123 | filters=512 124 | size=3 125 | stride=1 126 | pad=1 127 | activation=leaky 128 | 129 | [convolutional] 130 | batch_normalize=1 131 | filters=256 132 | size=1 133 | stride=1 134 | pad=1 135 | activation=leaky 136 | 137 | [convolutional] 138 | batch_normalize=1 139 | filters=512 140 | size=3 141 | stride=1 142 | pad=1 143 | activation=leaky 144 | 145 | [maxpool] 146 | size=2 147 | stride=2 148 | 149 | [convolutional] 150 | batch_normalize=1 151 | filters=1024 152 | size=3 153 | stride=1 154 | pad=1 155 | activation=leaky 156 | 157 | [convolutional] 158 | batch_normalize=1 159 | filters=512 160 | size=1 161 | stride=1 162 | pad=1 163 | activation=leaky 164 | 165 | [convolutional] 166 | batch_normalize=1 167 | filters=1024 168 | size=3 169 | stride=1 170 | pad=1 171 | activation=leaky 172 | 173 | [convolutional] 174 | batch_normalize=1 175 | filters=512 176 | size=1 177 | stride=1 178 | pad=1 179 | activation=leaky 180 | 181 | [convolutional] 182 | batch_normalize=1 183 | filters=1024 184 | size=3 185 | stride=1 186 | pad=1 187 | activation=leaky 188 | 189 | 190 | ####### 191 | 192 | [convolutional] 193 | batch_normalize=1 194 | size=3 195 | stride=1 196 | pad=1 197 | filters=1024 198 | activation=leaky 199 | 200 | [convolutional] 201 | batch_normalize=1 202 | size=3 203 | stride=1 204 | pad=1 205 | filters=1024 206 | activation=leaky 207 | 208 | [route] 209 | layers=-9 210 | 211 | [convolutional] 212 | batch_normalize=1 213 | size=1 214 | stride=1 215 | pad=1 216 | filters=64 217 | activation=leaky 218 | 219 | [reorg] 220 | stride=2 221 | 222 | [route] 223 | layers=-1,-4 224 | 225 | [convolutional] 226 | batch_normalize=1 227 | size=3 228 | stride=1 229 | pad=1 230 | filters=1024 231 | activation=leaky 232 | 233 | [convolutional] 234 | size=1 235 | stride=1 236 | pad=1 237 | filters=425 238 | activation=linear 239 | 240 | 241 | [region] 242 | anchors = 0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828 243 | bias_match=1 244 | classes=80 245 | coords=4 246 | num=5 247 | softmax=1 248 | jitter=.3 249 | rescore=1 250 | 251 | object_scale=5 252 | noobject_scale=1 253 | class_scale=1 254 | coord_scale=1 255 | 256 | absolute=1 257 | thresh = .1 258 | random=1 259 | -------------------------------------------------------------------------------- /sample_img/sample_multiple_objects.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/sample_img/sample_multiple_objects.jpg -------------------------------------------------------------------------------- /sample_video/test_video.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/sample_video/test_video.mp4 -------------------------------------------------------------------------------- /weights.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/deep-diver/Object-Detection-YOLOv2-Darkflow/dd41f84999341d50408611fdc90bcb81dfe82e97/weights.PNG --------------------------------------------------------------------------------