├── README.md ├── __init__.py ├── activations.py ├── augmentations.py ├── autoanchor.py ├── autobatch.py ├── aws ├── __init__.py ├── mime.sh ├── resume.py └── userdata.sh ├── callbacks.py ├── data ├── Argoverse.yaml ├── GlobalWheat2020.yaml ├── Objects365.yaml ├── SKU-110K.yaml ├── VOC.yaml ├── VisDrone.yaml ├── coco.yaml ├── coco128.yaml ├── data.yaml ├── fire_data.yaml ├── hyps │ ├── hyp.finetune.yaml │ ├── hyp.finetune_objects365.yaml │ ├── hyp.scratch-high.yaml │ ├── hyp.scratch-low.yaml │ ├── hyp.scratch-med.yaml │ └── hyp.scratch.yaml ├── images │ ├── bus.jpg │ ├── fishman.jpg │ ├── phone │ │ ├── phone_1310.jpg │ │ ├── phone_2096.jpg │ │ ├── phone_2402.jpg │ │ ├── phone_2423.jpg │ │ ├── phone_419.jpg │ │ ├── phone_633.jpg │ │ ├── phone_689.jpg │ │ └── phone_89.jpg │ └── zidane.jpg ├── mask_data.yaml ├── scripts │ ├── download_weights.sh │ ├── get_coco.sh │ └── get_coco128.sh └── xView.yaml ├── datasets.py ├── datasets_not_print.py ├── downloads.py ├── flask_rest_api ├── README.md ├── example_request.py └── restapi.py ├── general.py ├── images ├── 1_20.jpg ├── 1_67.jpg ├── 1c992e2b-108a-4e3c-859d-ae84d6f8ce7f.jpg ├── UI │ ├── logo.jpeg │ ├── lufei.png │ ├── qq.png │ ├── right.jpeg │ ├── up.jpeg │ └── xf.jpg ├── right.jpeg ├── tmp │ ├── single_result.jpg │ ├── single_result_vid.jpg │ ├── tmp_upload.jpeg │ ├── tmp_upload.jpg │ ├── tmp_upload.png │ └── upload_show_result.jpg └── up.jpeg ├── loggers ├── __init__.py ├── __pycache__ │ └── __init__.cpython-38.pyc └── wandb │ ├── README.md │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-38.pyc │ └── wandb_utils.cpython-38.pyc │ ├── log_dataset.py │ ├── sweep.py │ ├── sweep.yaml │ └── wandb_utils.py ├── loss.py ├── metrics.py ├── models ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── common.cpython-38.pyc │ ├── experimental.cpython-38.pyc │ └── yolo.cpython-38.pyc ├── common.py ├── experimental.py ├── hub │ ├── anchors.yaml │ ├── yolov3-spp.yaml │ ├── yolov3-tiny.yaml │ ├── yolov3.yaml │ ├── yolov5-bifpn.yaml │ ├── yolov5-fpn.yaml │ ├── yolov5-p2.yaml │ ├── yolov5-p6.yaml │ ├── yolov5-p7.yaml │ ├── yolov5-panet.yaml │ ├── yolov5l6.yaml │ ├── yolov5m6.yaml │ ├── yolov5n6.yaml │ ├── yolov5s-ghost.yaml │ ├── yolov5s-transformer.yaml │ ├── yolov5s6.yaml │ └── yolov5x6.yaml ├── mask_yolov5l.yaml ├── mask_yolov5m.yaml ├── mask_yolov5s.yaml ├── tf.py ├── yolo.py ├── yolov5l.yaml ├── yolov5m.yaml ├── yolov5n.yaml ├── yolov5s.yaml └── yolov5x.yaml ├── pic ├── 1.png ├── 11.png ├── 12.png ├── 13.png ├── 14.png ├── 2.png ├── 3.png ├── 4.png └── 5.png ├── plots.py ├── torch_utils.py ├── ui ├── __init__.py ├── ji.py ├── server_main.py ├── train_server.py └── x.py └── yolov5s.pt /README.md: -------------------------------------------------------------------------------- 1 | ## yolov5-fire 2 | yolov5-fire：基于YoloV5的火灾检测系统，将深度学习算法应用于火灾识别与检测领域，致力于研发准确高效的火灾识别与检测方法，实现图像中火灾区域的定位，为火灾检测技术走向实际应用提供理论和技术支持。 3 | 4 | 5 | 6 | 7 | YOUR-ALT-TEXT 8 | 9 | 10 | ## 环境配置 11 | 基于 Windows10 操作系统，python3.7，torch1.20，cuda11以及torchvision0.40的环境，使用VOC格式数据集进行训练。 12 | 训练前将标签文件放在fire_yolo_format文件夹下的labels文件夹中，训练前将图片文件放在fire_yolo_format文件夹下的images文件夹中。 13 | 14 | ## 训练样本集设计 15 |
16 | 从线上收集了2059张包含起火点事物的图片，组合训练集和测试集，训练集包括1442张图像，测试集包括617张图像，通过labelimg对起火位置进行标注，如图所示。 17 | 18 | 19 | 20 | YOUR-ALT-TEXT 21 | 22 |
23 | 24 | ## 模型训练过程 25 |
26 | 模型训练流程图、训练过程及测试结果 27 | 28 | 29 | 30 | YOUR-ALT-TEXT 31 | 32 | 33 | 34 | 模型训练 35 | 36 | 37 | 38 | 39 | YOUR-ALT-TEXT 40 | 41 | 42 | 43 | 44 | 45 | 46 | YOUR-ALT-TEXT 47 | 48 | 49 | 模型检测 50 | 51 | 52 | 53 | 54 | YOUR-ALT-TEXT 55 | 56 |
57 | 58 | ## 基于Yolov5的火灾检测系统 59 |
60 | 系统界面设计及效果图 61 | 62 | 63 | 64 | YOUR-ALT-TEXT 65 | 66 | 67 | 图片检测界面 68 | 69 | 70 | 71 | 72 | YOUR-ALT-TEXT 73 | 74 | 75 | 摄像头实时检测界面 76 | 77 | 78 | 79 | 80 | YOUR-ALT-TEXT 81 | 82 | 83 | 视频文件检测界面 84 | 85 | 86 | 87 | 88 | YOUR-ALT-TEXT 89 | 90 |
91 | 92 | -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | utils/initialization 4 | """ 5 | 6 | 7 | def notebook_init(): 8 | # For YOLOv5 notebooks 9 | print('Checking setup...') 10 | from IPython import display # to display images and clear console output 11 | 12 | from utils.general import emojis 13 | from utils.torch_utils import select_device # YOLOv5 imports 14 | 15 | display.clear_output() 16 | select_device(newline=False) 17 | print(emojis('Setup complete ✅')) 18 | return display 19 | -------------------------------------------------------------------------------- /activations.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Activation functions 4 | """ 5 | 6 | import torch 7 | import torch.nn as nn 8 | import torch.nn.functional as F 9 | 10 | 11 | # SiLU https://arxiv.org/pdf/1606.08415.pdf ---------------------------------------------------------------------------- 12 | class SiLU(nn.Module): # export-friendly version of nn.SiLU() 13 | @staticmethod 14 | def forward(x): 15 | return x * torch.sigmoid(x) 16 | 17 | 18 | class Hardswish(nn.Module): # export-friendly version of nn.Hardswish() 19 | @staticmethod 20 | def forward(x): 21 | # return x * F.hardsigmoid(x) # for torchscript and CoreML 22 | return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for torchscript, CoreML and ONNX 23 | 24 | 25 | # Mish https://github.com/digantamisra98/Mish -------------------------------------------------------------------------- 26 | class Mish(nn.Module): 27 | @staticmethod 28 | def forward(x): 29 | return x * F.softplus(x).tanh() 30 | 31 | 32 | class MemoryEfficientMish(nn.Module): 33 | class F(torch.autograd.Function): 34 | @staticmethod 35 | def forward(ctx, x): 36 | ctx.save_for_backward(x) 37 | return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) 38 | 39 | @staticmethod 40 | def backward(ctx, grad_output): 41 | x = ctx.saved_tensors[0] 42 | sx = torch.sigmoid(x) 43 | fx = F.softplus(x).tanh() 44 | return grad_output * (fx + x * sx * (1 - fx * fx)) 45 | 46 | def forward(self, x): 47 | return self.F.apply(x) 48 | 49 | 50 | # FReLU https://arxiv.org/abs/2007.11824 ------------------------------------------------------------------------------- 51 | class FReLU(nn.Module): 52 | def __init__(self, c1, k=3): # ch_in, kernel 53 | super().__init__() 54 | self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False) 55 | self.bn = nn.BatchNorm2d(c1) 56 | 57 | def forward(self, x): 58 | return torch.max(x, self.bn(self.conv(x))) 59 | 60 | 61 | # ACON https://arxiv.org/pdf/2009.04759.pdf ---------------------------------------------------------------------------- 62 | class AconC(nn.Module): 63 | r""" ACON activation (activate or not). 64 | AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter 65 | according to "Activate or Not: Learning Customized Activation" . 66 | """ 67 | 68 | def __init__(self, c1): 69 | super().__init__() 70 | self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) 71 | self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) 72 | self.beta = nn.Parameter(torch.ones(1, c1, 1, 1)) 73 | 74 | def forward(self, x): 75 | dpx = (self.p1 - self.p2) * x 76 | return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x 77 | 78 | 79 | class MetaAconC(nn.Module): 80 | r""" ACON activation (activate or not). 81 | MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network 82 | according to "Activate or Not: Learning Customized Activation" . 83 | """ 84 | 85 | def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r 86 | super().__init__() 87 | c2 = max(r, c1 // r) 88 | self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) 89 | self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) 90 | self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True) 91 | self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True) 92 | # self.bn1 = nn.BatchNorm2d(c2) 93 | # self.bn2 = nn.BatchNorm2d(c1) 94 | 95 | def forward(self, x): 96 | y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True) 97 | # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891 98 | # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable 99 | beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed 100 | dpx = (self.p1 - self.p2) * x 101 | return dpx * torch.sigmoid(beta * dpx) + self.p2 * x 102 | -------------------------------------------------------------------------------- /augmentations.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Image augmentation functions 4 | """ 5 | 6 | import math 7 | import random 8 | 9 | import cv2 10 | import numpy as np 11 | 12 | from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box 13 | from utils.metrics import bbox_ioa 14 | 15 | 16 | class Albumentations: 17 | # YOLOv5 Albumentations class (optional, only used if package is installed) 18 | def __init__(self): 19 | self.transform = None 20 | try: 21 | import albumentations as A 22 | check_version(A.__version__, '1.0.3', hard=True) # version requirement 23 | 24 | self.transform = A.Compose([ 25 | A.Blur(p=0.01), 26 | A.MedianBlur(p=0.01), 27 | A.ToGray(p=0.01), 28 | A.CLAHE(p=0.01), 29 | A.RandomBrightnessContrast(p=0.0), 30 | A.RandomGamma(p=0.0), 31 | A.ImageCompression(quality_lower=75, p=0.0)], 32 | bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels'])) 33 | 34 | LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p)) 35 | except ImportError: # package not installed, skip 36 | pass 37 | except Exception as e: 38 | LOGGER.info(colorstr('albumentations: ') + f'{e}') 39 | 40 | def __call__(self, im, labels, p=1.0): 41 | if self.transform and random.random() < p: 42 | new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed 43 | im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) 44 | return im, labels 45 | 46 | 47 | def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5): 48 | # HSV color-space augmentation 49 | if hgain or sgain or vgain: 50 | r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains 51 | hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV)) 52 | dtype = im.dtype # uint8 53 | 54 | x = np.arange(0, 256, dtype=r.dtype) 55 | lut_hue = ((x * r[0]) % 180).astype(dtype) 56 | lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) 57 | lut_val = np.clip(x * r[2], 0, 255).astype(dtype) 58 | 59 | im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) 60 | cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed 61 | 62 | 63 | def hist_equalize(im, clahe=True, bgr=False): 64 | # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255 65 | yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) 66 | if clahe: 67 | c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) 68 | yuv[:, :, 0] = c.apply(yuv[:, :, 0]) 69 | else: 70 | yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram 71 | return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB 72 | 73 | 74 | def replicate(im, labels): 75 | # Replicate labels 76 | h, w = im.shape[:2] 77 | boxes = labels[:, 1:].astype(int) 78 | x1, y1, x2, y2 = boxes.T 79 | s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) 80 | for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices 81 | x1b, y1b, x2b, y2b = boxes[i] 82 | bh, bw = y2b - y1b, x2b - x1b 83 | yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y 84 | x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] 85 | im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax] 86 | labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) 87 | 88 | return im, labels 89 | 90 | 91 | def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): 92 | # Resize and pad image while meeting stride-multiple constraints 93 | shape = im.shape[:2] # current shape [height, width] 94 | if isinstance(new_shape, int): 95 | new_shape = (new_shape, new_shape) 96 | 97 | # Scale ratio (new / old) 98 | r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) 99 | if not scaleup: # only scale down, do not scale up (for better val mAP) 100 | r = min(r, 1.0) 101 | 102 | # Compute padding 103 | ratio = r, r # width, height ratios 104 | new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) 105 | dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding 106 | if auto: # minimum rectangle 107 | dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding 108 | elif scaleFill: # stretch 109 | dw, dh = 0.0, 0.0 110 | new_unpad = (new_shape[1], new_shape[0]) 111 | ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios 112 | 113 | dw /= 2 # divide padding into 2 sides 114 | dh /= 2 115 | 116 | if shape[::-1] != new_unpad: # resize 117 | im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) 118 | top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) 119 | left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) 120 | im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border 121 | return im, ratio, (dw, dh) 122 | 123 | 124 | def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, 125 | border=(0, 0)): 126 | # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10)) 127 | # targets = [cls, xyxy] 128 | 129 | height = im.shape[0] + border[0] * 2 # shape(h,w,c) 130 | width = im.shape[1] + border[1] * 2 131 | 132 | # Center 133 | C = np.eye(3) 134 | C[0, 2] = -im.shape[1] / 2 # x translation (pixels) 135 | C[1, 2] = -im.shape[0] / 2 # y translation (pixels) 136 | 137 | # Perspective 138 | P = np.eye(3) 139 | P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) 140 | P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) 141 | 142 | # Rotation and Scale 143 | R = np.eye(3) 144 | a = random.uniform(-degrees, degrees) 145 | # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations 146 | s = random.uniform(1 - scale, 1 + scale) 147 | # s = 2 ** random.uniform(-scale, scale) 148 | R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) 149 | 150 | # Shear 151 | S = np.eye(3) 152 | S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) 153 | S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) 154 | 155 | # Translation 156 | T = np.eye(3) 157 | T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) 158 | T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) 159 | 160 | # Combined rotation matrix 161 | M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT 162 | if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed 163 | if perspective: 164 | im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) 165 | else: # affine 166 | im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) 167 | 168 | # Visualize 169 | # import matplotlib.pyplot as plt 170 | # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() 171 | # ax[0].imshow(im[:, :, ::-1]) # base 172 | # ax[1].imshow(im2[:, :, ::-1]) # warped 173 | 174 | # Transform label coordinates 175 | n = len(targets) 176 | if n: 177 | use_segments = any(x.any() for x in segments) 178 | new = np.zeros((n, 4)) 179 | if use_segments: # warp segments 180 | segments = resample_segments(segments) # upsample 181 | for i, segment in enumerate(segments): 182 | xy = np.ones((len(segment), 3)) 183 | xy[:, :2] = segment 184 | xy = xy @ M.T # transform 185 | xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine 186 | 187 | # clip 188 | new[i] = segment2box(xy, width, height) 189 | 190 | else: # warp boxes 191 | xy = np.ones((n * 4, 3)) 192 | xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 193 | xy = xy @ M.T # transform 194 | xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine 195 | 196 | # create new boxes 197 | x = xy[:, [0, 2, 4, 6]] 198 | y = xy[:, [1, 3, 5, 7]] 199 | new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T 200 | 201 | # clip 202 | new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) 203 | new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) 204 | 205 | # filter candidates 206 | i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) 207 | targets = targets[i] 208 | targets[:, 1:5] = new[i] 209 | 210 | return im, targets 211 | 212 | 213 | def copy_paste(im, labels, segments, p=0.5): 214 | # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) 215 | n = len(segments) 216 | if p and n: 217 | h, w, c = im.shape # height, width, channels 218 | im_new = np.zeros(im.shape, np.uint8) 219 | for j in random.sample(range(n), k=round(p * n)): 220 | l, s = labels[j], segments[j] 221 | box = w - l[3], l[2], w - l[1], l[4] 222 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 223 | if (ioa < 0.30).all(): # allow 30% obscuration of existing labels 224 | labels = np.concatenate((labels, [[l[0], *box]]), 0) 225 | segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) 226 | cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) 227 | 228 | result = cv2.bitwise_and(src1=im, src2=im_new) 229 | result = cv2.flip(result, 1) # augment segments (flip left-right) 230 | i = result > 0 # pixels to replace 231 | # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch 232 | im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug 233 | 234 | return im, labels, segments 235 | 236 | 237 | def cutout(im, labels, p=0.5): 238 | # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 239 | if random.random() < p: 240 | h, w = im.shape[:2] 241 | scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction 242 | for s in scales: 243 | mask_h = random.randint(1, int(h * s)) # create random masks 244 | mask_w = random.randint(1, int(w * s)) 245 | 246 | # box 247 | xmin = max(0, random.randint(0, w) - mask_w // 2) 248 | ymin = max(0, random.randint(0, h) - mask_h // 2) 249 | xmax = min(w, xmin + mask_w) 250 | ymax = min(h, ymin + mask_h) 251 | 252 | # apply random color mask 253 | im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] 254 | 255 | # return unobscured labels 256 | if len(labels) and s > 0.03: 257 | box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) 258 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 259 | labels = labels[ioa < 0.60] # remove >60% obscured labels 260 | 261 | return labels 262 | 263 | 264 | def mixup(im, labels, im2, labels2): 265 | # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf 266 | r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 267 | im = (im * r + im2 * (1 - r)).astype(np.uint8) 268 | labels = np.concatenate((labels, labels2), 0) 269 | return im, labels 270 | 271 | 272 | def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) 273 | # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio 274 | w1, h1 = box1[2] - box1[0], box1[3] - box1[1] 275 | w2, h2 = box2[2] - box2[0], box2[3] - box2[1] 276 | ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio 277 | return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates 278 | -------------------------------------------------------------------------------- /autoanchor.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Auto-anchor utils 4 | """ 5 | 6 | import random 7 | 8 | import numpy as np 9 | import torch 10 | import yaml 11 | from tqdm import tqdm 12 | 13 | from utils.general import LOGGER, colorstr, emojis 14 | 15 | PREFIX = colorstr('AutoAnchor: ') 16 | 17 | 18 | def check_anchor_order(m): 19 | # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary 20 | a = m.anchors.prod(-1).view(-1) # anchor area 21 | da = a[-1] - a[0] # delta a 22 | ds = m.stride[-1] - m.stride[0] # delta s 23 | if da.sign() != ds.sign(): # same order 24 | LOGGER.info(f'{PREFIX}Reversing anchor order') 25 | m.anchors[:] = m.anchors.flip(0) 26 | 27 | 28 | def check_anchors(dataset, model, thr=4.0, imgsz=640): 29 | # Check anchor fit to data, recompute if necessary 30 | m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() 31 | shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) 32 | scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale 33 | wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh 34 | 35 | def metric(k): # compute metric 36 | r = wh[:, None] / k[None] 37 | x = torch.min(r, 1 / r).min(2)[0] # ratio metric 38 | best = x.max(1)[0] # best_x 39 | aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold 40 | bpr = (best > 1 / thr).float().mean() # best possible recall 41 | return bpr, aat 42 | 43 | anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors 44 | bpr, aat = metric(anchors.cpu().view(-1, 2)) 45 | s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). ' 46 | if bpr > 0.98: # threshold to recompute 47 | LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅')) 48 | else: 49 | LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...')) 50 | na = m.anchors.numel() // 2 # number of anchors 51 | try: 52 | anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) 53 | except Exception as e: 54 | LOGGER.info(f'{PREFIX}ERROR: {e}') 55 | new_bpr = metric(anchors)[0] 56 | if new_bpr > bpr: # replace anchors 57 | anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) 58 | m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss 59 | check_anchor_order(m) 60 | LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.') 61 | else: 62 | LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.') 63 | 64 | 65 | def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): 66 | """ Creates kmeans-evolved anchors from training dataset 67 | 68 | Arguments: 69 | dataset: path to data.yaml, or a loaded dataset 70 | n: number of anchors 71 | img_size: image size used for training 72 | thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 73 | gen: generations to evolve anchors using genetic algorithm 74 | verbose: print all results 75 | 76 | Return: 77 | k: kmeans evolved anchors 78 | 79 | Usage: 80 | from utils.autoanchor import *; _ = kmean_anchors() 81 | """ 82 | from scipy.cluster.vq import kmeans 83 | 84 | thr = 1 / thr 85 | 86 | def metric(k, wh): # compute metrics 87 | r = wh[:, None] / k[None] 88 | x = torch.min(r, 1 / r).min(2)[0] # ratio metric 89 | # x = wh_iou(wh, torch.tensor(k)) # iou metric 90 | return x, x.max(1)[0] # x, best_x 91 | 92 | def anchor_fitness(k): # mutation fitness 93 | _, best = metric(torch.tensor(k, dtype=torch.float32), wh) 94 | return (best * (best > thr).float()).mean() # fitness 95 | 96 | def print_results(k, verbose=True): 97 | k = k[np.argsort(k.prod(1))] # sort small to large 98 | x, best = metric(k, wh0) 99 | bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr 100 | s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \ 101 | f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \ 102 | f'past_thr={x[x > thr].mean():.3f}-mean: ' 103 | for i, x in enumerate(k): 104 | s += '%i,%i, ' % (round(x[0]), round(x[1])) 105 | if verbose: 106 | LOGGER.info(s[:-2]) 107 | return k 108 | 109 | if isinstance(dataset, str): # *.yaml file 110 | with open(dataset, errors='ignore') as f: 111 | data_dict = yaml.safe_load(f) # model dict 112 | from utils.datasets import LoadImagesAndLabels 113 | dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) 114 | 115 | # Get label wh 116 | shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) 117 | wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh 118 | 119 | # Filter 120 | i = (wh0 < 3.0).any(1).sum() 121 | if i: 122 | LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.') 123 | wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels 124 | # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1 125 | 126 | # Kmeans calculation 127 | LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...') 128 | s = wh.std(0) # sigmas for whitening 129 | k, dist = kmeans(wh / s, n, iter=30) # points, mean distance 130 | assert len(k) == n, f'{PREFIX}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}' 131 | k *= s 132 | wh = torch.tensor(wh, dtype=torch.float32) # filtered 133 | wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered 134 | k = print_results(k, verbose=False) 135 | 136 | # Plot 137 | # k, d = [None] * 20, [None] * 20 138 | # for i in tqdm(range(1, 21)): 139 | # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance 140 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True) 141 | # ax = ax.ravel() 142 | # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') 143 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh 144 | # ax[0].hist(wh[wh[:, 0]<100, 0],400) 145 | # ax[1].hist(wh[wh[:, 1]<100, 1],400) 146 | # fig.savefig('wh.png', dpi=200) 147 | 148 | # Evolve 149 | npr = np.random 150 | f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma 151 | pbar = tqdm(range(gen), desc=f'{PREFIX}Evolving anchors with Genetic Algorithm:') # progress bar 152 | for _ in pbar: 153 | v = np.ones(sh) 154 | while (v == 1).all(): # mutate until a change occurs (prevent duplicates) 155 | v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) 156 | kg = (k.copy() * v).clip(min=2.0) 157 | fg = anchor_fitness(kg) 158 | if fg > f: 159 | f, k = fg, kg.copy() 160 | pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}' 161 | if verbose: 162 | print_results(k, verbose) 163 | 164 | return print_results(k) 165 | -------------------------------------------------------------------------------- /autobatch.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Auto-batch utils 4 | """ 5 | 6 | from copy import deepcopy 7 | 8 | import numpy as np 9 | import torch 10 | from torch.cuda import amp 11 | 12 | from utils.general import LOGGER, colorstr 13 | from utils.torch_utils import profile 14 | 15 | 16 | def check_train_batch_size(model, imgsz=640): 17 | # Check YOLOv5 training batch size 18 | with amp.autocast(): 19 | return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size 20 | 21 | 22 | def autobatch(model, imgsz=640, fraction=0.9, batch_size=16): 23 | # Automatically estimate best batch size to use `fraction` of available CUDA memory 24 | # Usage: 25 | # import torch 26 | # from utils.autobatch import autobatch 27 | # model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False) 28 | # print(autobatch(model)) 29 | 30 | prefix = colorstr('AutoBatch: ') 31 | LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}') 32 | device = next(model.parameters()).device # get model device 33 | if device.type == 'cpu': 34 | LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}') 35 | return batch_size 36 | 37 | d = str(device).upper() # 'CUDA:0' 38 | properties = torch.cuda.get_device_properties(device) # device properties 39 | t = properties.total_memory / 1024 ** 3 # (GiB) 40 | r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GiB) 41 | a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GiB) 42 | f = t - (r + a) # free inside reserved 43 | LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free') 44 | 45 | batch_sizes = [1, 2, 4, 8, 16] 46 | try: 47 | img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes] 48 | y = profile(img, model, n=3, device=device) 49 | except Exception as e: 50 | LOGGER.warning(f'{prefix}{e}') 51 | 52 | y = [x[2] for x in y if x] # memory [2] 53 | batch_sizes = batch_sizes[:len(y)] 54 | p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit 55 | b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) 56 | LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)') 57 | return b 58 | -------------------------------------------------------------------------------- /aws/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/aws/__init__.py -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /aws/resume.py: -------------------------------------------------------------------------------- 1 | # Resume all interrupted trainings in yolov5/ 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 | FILE = Path(__file__).resolve() 12 | ROOT = FILE.parents[2] # YOLOv5 root directory 13 | if str(ROOT) not in sys.path: 14 | sys.path.append(str(ROOT)) # add ROOT to PATH 15 | 16 | port = 0 # --master_port 17 | path = Path('').resolve() 18 | for last in path.rglob('*/**/last.pt'): 19 | ckpt = torch.load(last) 20 | if ckpt['optimizer'] is None: 21 | continue 22 | 23 | # Load opt.yaml 24 | with open(last.parent.parent / 'opt.yaml', errors='ignore') as f: 25 | opt = yaml.safe_load(f) 26 | 27 | # Get device count 28 | d = opt['device'].split(',') # devices 29 | nd = len(d) # number of devices 30 | ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel 31 | 32 | if ddp: # multi-GPU 33 | port += 1 34 | cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}' 35 | else: # single-GPU 36 | cmd = f'python train.py --resume {last}' 37 | 38 | cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread 39 | print(cmd) 40 | os.system(cmd) 41 | -------------------------------------------------------------------------------- /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 yolov5 ]; then 9 | echo "Running first-time script." # install dependencies, download COCO, pull Docker 10 | git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5 11 | cd yolov5 12 | bash data/scripts/get_coco.sh && echo "COCO done." & 13 | sudo docker pull ultralytics/yolov5:latest && 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 | -------------------------------------------------------------------------------- /callbacks.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Callback utils 4 | """ 5 | 6 | 7 | class Callbacks: 8 | """" 9 | Handles all registered callbacks for YOLOv5 Hooks 10 | """ 11 | 12 | # Define the available callbacks 13 | _callbacks = { 14 | 'on_pretrain_routine_start': [], 15 | 'on_pretrain_routine_end': [], 16 | 17 | 'on_train_start': [], 18 | 'on_train_epoch_start': [], 19 | 'on_train_batch_start': [], 20 | 'optimizer_step': [], 21 | 'on_before_zero_grad': [], 22 | 'on_train_batch_end': [], 23 | 'on_train_epoch_end': [], 24 | 25 | 'on_val_start': [], 26 | 'on_val_batch_start': [], 27 | 'on_val_image_end': [], 28 | 'on_val_batch_end': [], 29 | 'on_val_end': [], 30 | 31 | 'on_fit_epoch_end': [], # fit = train + val 32 | 'on_model_save': [], 33 | 'on_train_end': [], 34 | 35 | 'teardown': [], 36 | } 37 | 38 | def register_action(self, hook, name='', callback=None): 39 | """ 40 | Register a new action to a callback hook 41 | 42 | Args: 43 | hook The callback hook name to register the action to 44 | name The name of the action for later reference 45 | callback The callback to fire 46 | """ 47 | assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" 48 | assert callable(callback), f"callback '{callback}' is not callable" 49 | self._callbacks[hook].append({'name': name, 'callback': callback}) 50 | 51 | def get_registered_actions(self, hook=None): 52 | """" 53 | Returns all the registered actions by callback hook 54 | 55 | Args: 56 | hook The name of the hook to check, defaults to all 57 | """ 58 | if hook: 59 | return self._callbacks[hook] 60 | else: 61 | return self._callbacks 62 | 63 | def run(self, hook, *args, **kwargs): 64 | """ 65 | Loop through the registered actions and fire all callbacks 66 | 67 | Args: 68 | hook The name of the hook to check, defaults to all 69 | args Arguments to receive from YOLOv5 70 | kwargs Keyword Arguments to receive from YOLOv5 71 | """ 72 | 73 | assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" 74 | 75 | for logger in self._callbacks[hook]: 76 | logger['callback'](*args, **kwargs) 77 | -------------------------------------------------------------------------------- /data/Argoverse.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ 3 | # Example usage: python train.py --data Argoverse.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── Argoverse ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/Argoverse # dataset root dir 12 | train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images 13 | val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images 14 | test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview 15 | 16 | # Classes 17 | nc: 8 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'truck', 'traffic_light', 'stop_sign'] # class names 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | import json 24 | 25 | from tqdm import tqdm 26 | from utils.general import download, Path 27 | 28 | 29 | def argoverse2yolo(set): 30 | labels = {} 31 | a = json.load(open(set, "rb")) 32 | for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."): 33 | img_id = annot['image_id'] 34 | img_name = a['images'][img_id]['name'] 35 | img_label_name = img_name[:-3] + "txt" 36 | 37 | cls = annot['category_id'] # instance class id 38 | x_center, y_center, width, height = annot['bbox'] 39 | x_center = (x_center + width / 2) / 1920.0 # offset and scale 40 | y_center = (y_center + height / 2) / 1200.0 # offset and scale 41 | width /= 1920.0 # scale 42 | height /= 1200.0 # scale 43 | 44 | img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']] 45 | if not img_dir.exists(): 46 | img_dir.mkdir(parents=True, exist_ok=True) 47 | 48 | k = str(img_dir / img_label_name) 49 | if k not in labels: 50 | labels[k] = [] 51 | labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n") 52 | 53 | for k in labels: 54 | with open(k, "w") as f: 55 | f.writelines(labels[k]) 56 | 57 | 58 | # Download 59 | dir = Path('../datasets/Argoverse') # dataset root dir 60 | urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip'] 61 | download(urls, dir=dir, delete=False) 62 | 63 | # Convert 64 | annotations_dir = 'Argoverse-HD/annotations/' 65 | (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images' 66 | for d in "train.json", "val.json": 67 | argoverse2yolo(dir / annotations_dir / d) # convert VisDrone annotations to YOLO labels 68 | -------------------------------------------------------------------------------- /data/GlobalWheat2020.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Global Wheat 2020 dataset http://www.global-wheat.com/ 3 | # Example usage: python train.py --data GlobalWheat2020.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── GlobalWheat2020 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/GlobalWheat2020 # dataset root dir 12 | train: # train images (relative to 'path') 3422 images 13 | - images/arvalis_1 14 | - images/arvalis_2 15 | - images/arvalis_3 16 | - images/ethz_1 17 | - images/rres_1 18 | - images/inrae_1 19 | - images/usask_1 20 | val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1) 21 | - images/ethz_1 22 | test: # test images (optional) 1276 images 23 | - images/utokyo_1 24 | - images/utokyo_2 25 | - images/nau_1 26 | - images/uq_1 27 | 28 | # Classes 29 | nc: 1 # number of classes 30 | names: ['wheat_head'] # class names 31 | 32 | 33 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 34 | download: | 35 | from utils.general import download, Path 36 | 37 | # Download 38 | dir = Path(yaml['path']) # dataset root dir 39 | urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip', 40 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip'] 41 | download(urls, dir=dir) 42 | 43 | # Make Directories 44 | for p in 'annotations', 'images', 'labels': 45 | (dir / p).mkdir(parents=True, exist_ok=True) 46 | 47 | # Move 48 | for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \ 49 | 'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1': 50 | (dir / p).rename(dir / 'images' / p) # move to /images 51 | f = (dir / p).with_suffix('.json') # json file 52 | if f.exists(): 53 | f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations 54 | -------------------------------------------------------------------------------- /data/Objects365.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Objects365 dataset https://www.objects365.org/ 3 | # Example usage: python train.py --data Objects365.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── Objects365 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/Objects365 # dataset root dir 12 | train: images/train # train images (relative to 'path') 1742289 images 13 | val: images/val # val images (relative to 'path') 80000 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | nc: 365 # number of classes 18 | names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup', 19 | 'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book', 20 | 'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag', 21 | 'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV', 22 | 'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle', 23 | 'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird', 24 | 'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck', 25 | 'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning', 26 | 'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife', 27 | 'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock', 28 | 'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish', 29 | 'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan', 30 | 'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard', 31 | 'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign', 32 | 'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat', 33 | 'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard', 34 | 'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry', 35 | 'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks', 36 | 'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors', 37 | 'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape', 38 | 'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck', 39 | 'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette', 40 | 'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket', 41 | 'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine', 42 | 'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine', 43 | 'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon', 44 | 'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse', 45 | 'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball', 46 | 'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin', 47 | 'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts', 48 | 'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit', 49 | 'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD', 50 | 'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder', 51 | 'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips', 52 | 'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab', 53 | 'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal', 54 | 'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart', 55 | 'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French', 56 | 'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell', 57 | 'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil', 58 | 'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis'] 59 | 60 | 61 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 62 | download: | 63 | from pycocotools.coco import COCO 64 | from tqdm import tqdm 65 | 66 | from utils.general import Path, download, np, xyxy2xywhn 67 | 68 | # Make Directories 69 | dir = Path(yaml['path']) # dataset root dir 70 | for p in 'images', 'labels': 71 | (dir / p).mkdir(parents=True, exist_ok=True) 72 | for q in 'train', 'val': 73 | (dir / p / q).mkdir(parents=True, exist_ok=True) 74 | 75 | # Train, Val Splits 76 | for split, patches in [('train', 50 + 1), ('val', 43 + 1)]: 77 | print(f"Processing {split} in {patches} patches ...") 78 | images, labels = dir / 'images' / split, dir / 'labels' / split 79 | 80 | # Download 81 | url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/" 82 | if split == 'train': 83 | download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False) # annotations json 84 | download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8) 85 | elif split == 'val': 86 | download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json 87 | download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8) 88 | download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8) 89 | 90 | # Move 91 | for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'): 92 | f.rename(images / f.name) # move to /images/{split} 93 | 94 | # Labels 95 | coco = COCO(dir / f'zhiyuan_objv2_{split}.json') 96 | names = [x["name"] for x in coco.loadCats(coco.getCatIds())] 97 | for cid, cat in enumerate(names): 98 | catIds = coco.getCatIds(catNms=[cat]) 99 | imgIds = coco.getImgIds(catIds=catIds) 100 | for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'): 101 | width, height = im["width"], im["height"] 102 | path = Path(im["file_name"]) # image filename 103 | try: 104 | with open(labels / path.with_suffix('.txt').name, 'a') as file: 105 | annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None) 106 | for a in coco.loadAnns(annIds): 107 | x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner) 108 | xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4) 109 | x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped 110 | file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n") 111 | except Exception as e: 112 | print(e) 113 | -------------------------------------------------------------------------------- /data/SKU-110K.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 3 | # Example usage: python train.py --data SKU-110K.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── SKU-110K ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/SKU-110K # dataset root dir 12 | train: train.txt # train images (relative to 'path') 8219 images 13 | val: val.txt # val images (relative to 'path') 588 images 14 | test: test.txt # test images (optional) 2936 images 15 | 16 | # Classes 17 | nc: 1 # number of classes 18 | names: ['object'] # class names 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | import shutil 24 | from tqdm import tqdm 25 | from utils.general import np, pd, Path, download, xyxy2xywh 26 | 27 | # Download 28 | dir = Path(yaml['path']) # dataset root dir 29 | parent = Path(dir.parent) # download dir 30 | urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz'] 31 | download(urls, dir=parent, delete=False) 32 | 33 | # Rename directories 34 | if dir.exists(): 35 | shutil.rmtree(dir) 36 | (parent / 'SKU110K_fixed').rename(dir) # rename dir 37 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir 38 | 39 | # Convert labels 40 | names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names 41 | for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv': 42 | x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations 43 | images, unique_images = x[:, 0], np.unique(x[:, 0]) 44 | with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f: 45 | f.writelines(f'./images/{s}\n' for s in unique_images) 46 | for im in tqdm(unique_images, desc=f'Converting {dir / d}'): 47 | cls = 0 # single-class dataset 48 | with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f: 49 | for r in x[images == im]: 50 | w, h = r[6], r[7] # image width, height 51 | xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance 52 | f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label 53 | -------------------------------------------------------------------------------- /data/VOC.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC 3 | # Example usage: python train.py --data VOC.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── VOC ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VOC 12 | train: # train images (relative to 'path') 16551 images 13 | - images/train2012 14 | - images/train2007 15 | - images/val2012 16 | - images/val2007 17 | val: # val images (relative to 'path') 4952 images 18 | - images/test2007 19 | test: # test images (optional) 20 | - images/test2007 21 | 22 | # Classes 23 | nc: 20 # number of classes 24 | names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 25 | 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] # class names 26 | 27 | 28 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 29 | download: | 30 | import xml.etree.ElementTree as ET 31 | 32 | from tqdm import tqdm 33 | from utils.general import download, Path 34 | 35 | 36 | def convert_label(path, lb_path, year, image_id): 37 | def convert_box(size, box): 38 | dw, dh = 1. / size[0], 1. / size[1] 39 | x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2] 40 | return x * dw, y * dh, w * dw, h * dh 41 | 42 | in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml') 43 | out_file = open(lb_path, 'w') 44 | tree = ET.parse(in_file) 45 | root = tree.getroot() 46 | size = root.find('size') 47 | w = int(size.find('width').text) 48 | h = int(size.find('height').text) 49 | 50 | for obj in root.iter('object'): 51 | cls = obj.find('name').text 52 | if cls in yaml['names'] and not int(obj.find('difficult').text) == 1: 53 | xmlbox = obj.find('bndbox') 54 | bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')]) 55 | cls_id = yaml['names'].index(cls) # class id 56 | out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n') 57 | 58 | 59 | # Download 60 | dir = Path(yaml['path']) # dataset root dir 61 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 62 | urls = [url + 'VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images 63 | url + 'VOCtest_06-Nov-2007.zip', # 438MB, 4953 images 64 | url + 'VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images 65 | download(urls, dir=dir / 'images', delete=False) 66 | 67 | # Convert 68 | path = dir / f'images/VOCdevkit' 69 | for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'): 70 | imgs_path = dir / 'images' / f'{image_set}{year}' 71 | lbs_path = dir / 'labels' / f'{image_set}{year}' 72 | imgs_path.mkdir(exist_ok=True, parents=True) 73 | lbs_path.mkdir(exist_ok=True, parents=True) 74 | 75 | image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split() 76 | for id in tqdm(image_ids, desc=f'{image_set}{year}'): 77 | f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path 78 | lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path 79 | f.rename(imgs_path / f.name) # move image 80 | convert_label(path, lb_path, year, id) # convert labels to YOLO format 81 | -------------------------------------------------------------------------------- /data/VisDrone.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset 3 | # Example usage: python train.py --data VisDrone.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── VisDrone ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VisDrone # dataset root dir 12 | train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images 13 | val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images 14 | test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images 15 | 16 | # Classes 17 | nc: 10 # number of classes 18 | names: ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor'] 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | from utils.general import download, os, Path 24 | 25 | def visdrone2yolo(dir): 26 | from PIL import Image 27 | from tqdm import tqdm 28 | 29 | def convert_box(size, box): 30 | # Convert VisDrone box to YOLO xywh box 31 | dw = 1. / size[0] 32 | dh = 1. / size[1] 33 | return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh 34 | 35 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory 36 | pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}') 37 | for f in pbar: 38 | img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size 39 | lines = [] 40 | with open(f, 'r') as file: # read annotation.txt 41 | for row in [x.split(',') for x in file.read().strip().splitlines()]: 42 | if row[4] == '0': # VisDrone 'ignored regions' class 0 43 | continue 44 | cls = int(row[5]) - 1 45 | box = convert_box(img_size, tuple(map(int, row[:4]))) 46 | lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n") 47 | with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl: 48 | fl.writelines(lines) # write label.txt 49 | 50 | 51 | # Download 52 | dir = Path(yaml['path']) # dataset root dir 53 | urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip', 54 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip', 55 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip', 56 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip'] 57 | download(urls, dir=dir) 58 | 59 | # Convert 60 | for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev': 61 | visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels 62 | -------------------------------------------------------------------------------- /data/coco.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO 2017 dataset http://cocodataset.org 3 | # Example usage: python train.py --data coco.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── coco ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco # dataset root dir 12 | train: train2017.txt # train images (relative to 'path') 118287 images 13 | val: val2017.txt # train images (relative to 'path') 5000 images 14 | test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 15 | 16 | # Classes 17 | nc: 80 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 19 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 20 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 21 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 22 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 23 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 24 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 25 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 26 | 'hair drier', 'toothbrush'] # class names 27 | 28 | 29 | # Download script/URL (optional) 30 | download: | 31 | from utils.general import download, Path 32 | 33 | # Download labels 34 | segments = False # segment or box labels 35 | dir = Path(yaml['path']) # dataset root dir 36 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 37 | urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels 38 | download(urls, dir=dir.parent) 39 | 40 | # Download data 41 | urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images 42 | 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images 43 | 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional) 44 | download(urls, dir=dir / 'images', threads=3) 45 | -------------------------------------------------------------------------------- /data/coco128.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) 3 | # Example usage: python train.py --data coco128.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── coco128 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco128 # dataset root dir 12 | train: images/train2017 # train images (relative to 'path') 128 images 13 | val: images/train2017 # val images (relative to 'path') 128 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | nc: 80 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 19 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 20 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 21 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 22 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 23 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 24 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 25 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 26 | 'hair drier', 'toothbrush'] # class names 27 | 28 | 29 | # Download script/URL (optional) 30 | download: https://ultralytics.com/assets/coco128.zip 31 | -------------------------------------------------------------------------------- /data/data.yaml: -------------------------------------------------------------------------------- 1 | # Custom data for safety helmet 2 | 3 | 4 | # train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] 5 | train: /home/data/yolo_format/images/train 6 | val: /home/data/yolo_format/images/val 7 | 8 | # number of classes 9 | nc: 2 10 | 11 | # class names 12 | names: ['phone', 'person'] 13 | -------------------------------------------------------------------------------- /data/fire_data.yaml: -------------------------------------------------------------------------------- 1 | # Custom data for safety helmet 2 | 3 | 4 | # train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] 5 | train: F:/sssssssssd/det/yolo/fire/fire_yolo_format/images/train 6 | val: F:/sssssssssd/det/yolo/fire/fire_yolo_format/images/val 7 | 8 | # number of classes 9 | nc: 2 10 | 11 | # class names 12 | names: ['fire', 'nofire'] 13 | -------------------------------------------------------------------------------- /data/hyps/hyp.finetune.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for VOC finetuning 3 | # python train.py --batch 64 --weights yolov5m.pt --data VOC.yaml --img 512 --epochs 50 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | # Hyperparameter Evolution Results 7 | # Generations: 306 8 | # P R mAP.5 mAP.5:.95 box obj cls 9 | # Metrics: 0.6 0.936 0.896 0.684 0.0115 0.00805 0.00146 10 | 11 | lr0: 0.0032 12 | lrf: 0.12 13 | momentum: 0.843 14 | weight_decay: 0.00036 15 | warmup_epochs: 2.0 16 | warmup_momentum: 0.5 17 | warmup_bias_lr: 0.05 18 | box: 0.0296 19 | cls: 0.243 20 | cls_pw: 0.631 21 | obj: 0.301 22 | obj_pw: 0.911 23 | iou_t: 0.2 24 | anchor_t: 2.91 25 | # anchors: 3.63 26 | fl_gamma: 0.0 27 | hsv_h: 0.0138 28 | hsv_s: 0.664 29 | hsv_v: 0.464 30 | degrees: 0.373 31 | translate: 0.245 32 | scale: 0.898 33 | shear: 0.602 34 | perspective: 0.0 35 | flipud: 0.00856 36 | fliplr: 0.5 37 | mosaic: 1.0 38 | mixup: 0.243 39 | copy_paste: 0.0 40 | -------------------------------------------------------------------------------- /data/hyps/hyp.finetune_objects365.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | lr0: 0.00258 4 | lrf: 0.17 5 | momentum: 0.779 6 | weight_decay: 0.00058 7 | warmup_epochs: 1.33 8 | warmup_momentum: 0.86 9 | warmup_bias_lr: 0.0711 10 | box: 0.0539 11 | cls: 0.299 12 | cls_pw: 0.825 13 | obj: 0.632 14 | obj_pw: 1.0 15 | iou_t: 0.2 16 | anchor_t: 3.44 17 | anchors: 3.2 18 | fl_gamma: 0.0 19 | hsv_h: 0.0188 20 | hsv_s: 0.704 21 | hsv_v: 0.36 22 | degrees: 0.0 23 | translate: 0.0902 24 | scale: 0.491 25 | shear: 0.0 26 | perspective: 0.0 27 | flipud: 0.0 28 | fliplr: 0.5 29 | mosaic: 1.0 30 | mixup: 0.0 31 | copy_paste: 0.0 32 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch-high.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for high-augmentation COCO training from scratch 3 | # python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.3 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 0.7 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.9 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.1 # image mixup (probability) 34 | copy_paste: 0.1 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch-low.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for low-augmentation COCO training from scratch 3 | # python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.5 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 1.0 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.5 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.0 # image mixup (probability) 34 | copy_paste: 0.0 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch-med.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for medium-augmentation COCO training from scratch 3 | # python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.3 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 0.7 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.9 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.1 # image mixup (probability) 34 | copy_paste: 0.0 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for COCO training from scratch 3 | # python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.5 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 1.0 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.5 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.0 # image mixup (probability) 34 | copy_paste: 0.0 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/images/bus.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/bus.jpg -------------------------------------------------------------------------------- /data/images/fishman.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/fishman.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_1310.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_1310.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_2096.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_2096.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_2402.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_2402.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_2423.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_2423.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_419.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_419.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_633.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_633.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_689.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_689.jpg -------------------------------------------------------------------------------- /data/images/phone/phone_89.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/phone/phone_89.jpg -------------------------------------------------------------------------------- /data/images/zidane.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/data/images/zidane.jpg -------------------------------------------------------------------------------- /data/mask_data.yaml: -------------------------------------------------------------------------------- 1 | # Custom data for safety helmet 2 | 3 | 4 | # train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] 5 | train: F:/up/1212/YOLO_Mask/score/images/train 6 | val: F:/up/1212/YOLO_Mask/score/images/val 7 | 8 | # number of classes 9 | nc: 2 10 | 11 | # class names 12 | names: ['mask', 'face'] 13 | -------------------------------------------------------------------------------- /data/scripts/download_weights.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 3 | # Download latest models from https://github.com/ultralytics/yolov5/releases 4 | # Example usage: bash path/to/download_weights.sh 5 | # parent 6 | # └── yolov5 7 | # ├── yolov5s.pt ← downloads here 8 | # ├── yolov5m.pt 9 | # └── ... 10 | 11 | python - <= cls >= 0, f'incorrect class index {cls}' 74 | 75 | # Write YOLO label 76 | if id not in shapes: 77 | shapes[id] = Image.open(file).size 78 | box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True) 79 | with open((labels / id).with_suffix('.txt'), 'a') as f: 80 | f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt 81 | except Exception as e: 82 | print(f'WARNING: skipping one label for {file}: {e}') 83 | 84 | 85 | # Download manually from https://challenge.xviewdataset.org 86 | dir = Path(yaml['path']) # dataset root dir 87 | # urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels 88 | # 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images 89 | # 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels) 90 | # download(urls, dir=dir, delete=False) 91 | 92 | # Convert labels 93 | convert_labels(dir / 'xView_train.geojson') 94 | 95 | # Move images 96 | images = Path(dir / 'images') 97 | images.mkdir(parents=True, exist_ok=True) 98 | Path(dir / 'train_images').rename(dir / 'images' / 'train') 99 | Path(dir / 'val_images').rename(dir / 'images' / 'val') 100 | 101 | # Split 102 | autosplit(dir / 'images' / 'train') 103 | -------------------------------------------------------------------------------- /downloads.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Download utils 4 | """ 5 | 6 | import os 7 | import platform 8 | import subprocess 9 | import time 10 | import urllib 11 | from pathlib import Path 12 | from zipfile import ZipFile 13 | 14 | import requests 15 | import torch 16 | 17 | 18 | def gsutil_getsize(url=''): 19 | # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du 20 | s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') 21 | return eval(s.split(' ')[0]) if len(s) else 0 # bytes 22 | 23 | 24 | def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): 25 | # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes 26 | file = Path(file) 27 | assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}" 28 | try: # url1 29 | print(f'Downloading {url} to {file}...') 30 | torch.hub.download_url_to_file(url, str(file)) 31 | assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check 32 | except Exception as e: # url2 33 | file.unlink(missing_ok=True) # remove partial downloads 34 | print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') 35 | os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail 36 | finally: 37 | if not file.exists() or file.stat().st_size < min_bytes: # check 38 | file.unlink(missing_ok=True) # remove partial downloads 39 | print(f"ERROR: {assert_msg}\n{error_msg}") 40 | print('') 41 | 42 | 43 | def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download() 44 | # Attempt file download if does not exist 45 | file = Path(str(file).strip().replace("'", '')) 46 | 47 | if not file.exists(): 48 | # URL specified 49 | name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc. 50 | if str(file).startswith(('http:/', 'https:/')): # download 51 | url = str(file).replace(':/', '://') # Pathlib turns :// -> :/ 52 | name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth... 53 | safe_download(file=name, url=url, min_bytes=1E5) 54 | return name 55 | 56 | # GitHub assets 57 | file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) 58 | try: 59 | response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api 60 | assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...] 61 | tag = response['tag_name'] # i.e. 'v1.0' 62 | except: # fallback plan 63 | assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 64 | 'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt'] 65 | try: 66 | tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1] 67 | except: 68 | tag = 'v6.0' # current release 69 | 70 | if name in assets: 71 | safe_download(file, 72 | url=f'https://github.com/{repo}/releases/download/{tag}/{name}', 73 | # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional) 74 | min_bytes=1E5, 75 | error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/') 76 | 77 | return str(file) 78 | 79 | 80 | def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'): 81 | # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download() 82 | t = time.time() 83 | file = Path(file) 84 | cookie = Path('cookie') # gdrive cookie 85 | print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='') 86 | file.unlink(missing_ok=True) # remove existing file 87 | cookie.unlink(missing_ok=True) # remove existing cookie 88 | 89 | # Attempt file download 90 | out = "NUL" if platform.system() == "Windows" else "/dev/null" 91 | os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}') 92 | if os.path.exists('cookie'): # large file 93 | s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}' 94 | else: # small file 95 | s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"' 96 | r = os.system(s) # execute, capture return 97 | cookie.unlink(missing_ok=True) # remove existing cookie 98 | 99 | # Error check 100 | if r != 0: 101 | file.unlink(missing_ok=True) # remove partial 102 | print('Download error ') # raise Exception('Download error') 103 | return r 104 | 105 | # Unzip if archive 106 | if file.suffix == '.zip': 107 | print('unzipping... ', end='') 108 | ZipFile(file).extractall(path=file.parent) # unzip 109 | file.unlink() # remove zip 110 | 111 | print(f'Done ({time.time() - t:.1f}s)') 112 | return r 113 | 114 | 115 | def get_token(cookie="./cookie"): 116 | with open(cookie) as f: 117 | for line in f: 118 | if "download" in line: 119 | return line.split()[-1] 120 | return "" 121 | 122 | # Google utils: https://cloud.google.com/storage/docs/reference/libraries ---------------------------------------------- 123 | # 124 | # 125 | # def upload_blob(bucket_name, source_file_name, destination_blob_name): 126 | # # Uploads a file to a bucket 127 | # # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python 128 | # 129 | # storage_client = storage.Client() 130 | # bucket = storage_client.get_bucket(bucket_name) 131 | # blob = bucket.blob(destination_blob_name) 132 | # 133 | # blob.upload_from_filename(source_file_name) 134 | # 135 | # print('File {} uploaded to {}.'.format( 136 | # source_file_name, 137 | # destination_blob_name)) 138 | # 139 | # 140 | # def download_blob(bucket_name, source_blob_name, destination_file_name): 141 | # # Uploads a blob from a bucket 142 | # storage_client = storage.Client() 143 | # bucket = storage_client.get_bucket(bucket_name) 144 | # blob = bucket.blob(source_blob_name) 145 | # 146 | # blob.download_to_filename(destination_file_name) 147 | # 148 | # print('Blob {} downloaded to {}.'.format( 149 | # source_blob_name, 150 | # destination_file_name)) 151 | -------------------------------------------------------------------------------- /flask_rest_api/README.md: -------------------------------------------------------------------------------- 1 | # Flask REST API 2 | 3 | [REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are 4 | commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API 5 | created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/). 6 | 7 | ## Requirements 8 | 9 | [Flask](https://palletsprojects.com/p/flask/) is required. Install with: 10 | 11 | ```shell 12 | $ pip install Flask 13 | ``` 14 | 15 | ## Run 16 | 17 | After Flask installation run: 18 | 19 | ```shell 20 | $ python3 restapi.py --port 5000 21 | ``` 22 | 23 | Then use [curl](https://curl.se/) to perform a request: 24 | 25 | ```shell 26 | $ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s' 27 | ``` 28 | 29 | The model inference results are returned as a JSON response: 30 | 31 | ```json 32 | [ 33 | { 34 | "class": 0, 35 | "confidence": 0.8900438547, 36 | "height": 0.9318675399, 37 | "name": "person", 38 | "width": 0.3264600933, 39 | "xcenter": 0.7438579798, 40 | "ycenter": 0.5207948685 41 | }, 42 | { 43 | "class": 0, 44 | "confidence": 0.8440024257, 45 | "height": 0.7155083418, 46 | "name": "person", 47 | "width": 0.6546785235, 48 | "xcenter": 0.427829951, 49 | "ycenter": 0.6334488392 50 | }, 51 | { 52 | "class": 27, 53 | "confidence": 0.3771208823, 54 | "height": 0.3902671337, 55 | "name": "tie", 56 | "width": 0.0696444362, 57 | "xcenter": 0.3675483763, 58 | "ycenter": 0.7991207838 59 | }, 60 | { 61 | "class": 27, 62 | "confidence": 0.3527112305, 63 | "height": 0.1540903747, 64 | "name": "tie", 65 | "width": 0.0336618312, 66 | "xcenter": 0.7814827561, 67 | "ycenter": 0.5065554976 68 | } 69 | ] 70 | ``` 71 | 72 | An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given 73 | in `example_request.py` 74 | -------------------------------------------------------------------------------- /flask_rest_api/example_request.py: -------------------------------------------------------------------------------- 1 | """Perform test request""" 2 | import pprint 3 | 4 | import requests 5 | 6 | DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s" 7 | TEST_IMAGE = "zidane.jpg" 8 | 9 | image_data = open(TEST_IMAGE, "rb").read() 10 | 11 | response = requests.post(DETECTION_URL, files={"image": image_data}).json() 12 | 13 | pprint.pprint(response) 14 | -------------------------------------------------------------------------------- /flask_rest_api/restapi.py: -------------------------------------------------------------------------------- 1 | """ 2 | Run a rest API exposing the yolov5s object detection model 3 | """ 4 | import argparse 5 | import io 6 | 7 | import torch 8 | from flask import Flask, request 9 | from PIL import Image 10 | 11 | app = Flask(__name__) 12 | 13 | DETECTION_URL = "/v1/object-detection/yolov5s" 14 | 15 | 16 | @app.route(DETECTION_URL, methods=["POST"]) 17 | def predict(): 18 | if not request.method == "POST": 19 | return 20 | 21 | if request.files.get("image"): 22 | image_file = request.files["image"] 23 | image_bytes = image_file.read() 24 | 25 | img = Image.open(io.BytesIO(image_bytes)) 26 | 27 | results = model(img, size=640) # reduce size=320 for faster inference 28 | return results.pandas().xyxy[0].to_json(orient="records") 29 | 30 | 31 | if __name__ == "__main__": 32 | parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model") 33 | parser.add_argument("--port", default=5000, type=int, help="port number") 34 | args = parser.parse_args() 35 | 36 | model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache 37 | app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat 38 | -------------------------------------------------------------------------------- /images/1_20.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/1_20.jpg -------------------------------------------------------------------------------- /images/1_67.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/1_67.jpg -------------------------------------------------------------------------------- /images/1c992e2b-108a-4e3c-859d-ae84d6f8ce7f.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/1c992e2b-108a-4e3c-859d-ae84d6f8ce7f.jpg -------------------------------------------------------------------------------- /images/UI/logo.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/logo.jpeg -------------------------------------------------------------------------------- /images/UI/lufei.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/lufei.png -------------------------------------------------------------------------------- /images/UI/qq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/qq.png -------------------------------------------------------------------------------- /images/UI/right.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/right.jpeg -------------------------------------------------------------------------------- /images/UI/up.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/up.jpeg -------------------------------------------------------------------------------- /images/UI/xf.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/UI/xf.jpg -------------------------------------------------------------------------------- /images/right.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/right.jpeg -------------------------------------------------------------------------------- /images/tmp/single_result.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/single_result.jpg -------------------------------------------------------------------------------- /images/tmp/single_result_vid.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/single_result_vid.jpg -------------------------------------------------------------------------------- /images/tmp/tmp_upload.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/tmp_upload.jpeg -------------------------------------------------------------------------------- /images/tmp/tmp_upload.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/tmp_upload.jpg -------------------------------------------------------------------------------- /images/tmp/tmp_upload.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/tmp_upload.png -------------------------------------------------------------------------------- /images/tmp/upload_show_result.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/tmp/upload_show_result.jpg -------------------------------------------------------------------------------- /images/up.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/images/up.jpeg -------------------------------------------------------------------------------- /loggers/__init__.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Logging utils 4 | """ 5 | 6 | import os 7 | import warnings 8 | from threading import Thread 9 | 10 | import pkg_resources as pkg 11 | import torch 12 | from torch.utils.tensorboard import SummaryWriter 13 | 14 | from utils.general import colorstr, emojis 15 | from utils.loggers.wandb.wandb_utils import WandbLogger 16 | from utils.plots import plot_images, plot_results 17 | from utils.torch_utils import de_parallel 18 | 19 | LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases 20 | RANK = int(os.getenv('RANK', -1)) 21 | 22 | try: 23 | import wandb 24 | 25 | assert hasattr(wandb, '__version__') # verify package import not local dir 26 | if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]: 27 | wandb_login_success = wandb.login(timeout=30) 28 | if not wandb_login_success: 29 | wandb = None 30 | except (ImportError, AssertionError): 31 | wandb = None 32 | 33 | 34 | class Loggers(): 35 | # YOLOv5 Loggers class 36 | def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS): 37 | self.save_dir = save_dir 38 | self.weights = weights 39 | self.opt = opt 40 | self.hyp = hyp 41 | self.logger = logger # for printing results to console 42 | self.include = include 43 | self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss 44 | 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics 45 | 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss 46 | 'x/lr0', 'x/lr1', 'x/lr2'] # params 47 | for k in LOGGERS: 48 | setattr(self, k, None) # init empty logger dictionary 49 | self.csv = True # always log to csv 50 | 51 | # Message 52 | if not wandb: 53 | prefix = colorstr('Weights & Biases: ') 54 | s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)" 55 | print(emojis(s)) 56 | 57 | # TensorBoard 58 | s = self.save_dir 59 | if 'tb' in self.include and not self.opt.evolve: 60 | prefix = colorstr('TensorBoard: ') 61 | self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/") 62 | self.tb = SummaryWriter(str(s)) 63 | 64 | # W&B 65 | if wandb and 'wandb' in self.include: 66 | wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') 67 | run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None 68 | self.opt.hyp = self.hyp # add hyperparameters 69 | self.wandb = WandbLogger(self.opt, run_id) 70 | else: 71 | self.wandb = None 72 | 73 | def on_pretrain_routine_end(self): 74 | # Callback runs on pre-train routine end 75 | paths = self.save_dir.glob('*labels*.jpg') # training labels 76 | if self.wandb: 77 | self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) 78 | 79 | def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn): 80 | # Callback runs on train batch end 81 | if plots: 82 | if ni == 0: 83 | if not sync_bn: # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754 84 | with warnings.catch_warnings(): 85 | warnings.simplefilter('ignore') # suppress jit trace warning 86 | self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), []) 87 | if ni < 3: 88 | f = self.save_dir / f'train_batch{ni}.jpg' # filename 89 | Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start() 90 | if self.wandb and ni == 10: 91 | files = sorted(self.save_dir.glob('train*.jpg')) 92 | self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]}) 93 | 94 | def on_train_epoch_end(self, epoch): 95 | # Callback runs on train epoch end 96 | if self.wandb: 97 | self.wandb.current_epoch = epoch + 1 98 | 99 | def on_val_image_end(self, pred, predn, path, names, im): 100 | # Callback runs on val image end 101 | if self.wandb: 102 | self.wandb.val_one_image(pred, predn, path, names, im) 103 | 104 | def on_val_end(self): 105 | # Callback runs on val end 106 | if self.wandb: 107 | files = sorted(self.save_dir.glob('val*.jpg')) 108 | self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) 109 | 110 | def on_fit_epoch_end(self, vals, epoch, best_fitness, fi): 111 | # Callback runs at the end of each fit (train+val) epoch 112 | x = {k: v for k, v in zip(self.keys, vals)} # dict 113 | if self.csv: 114 | file = self.save_dir / 'results.csv' 115 | n = len(x) + 1 # number of cols 116 | s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header 117 | with open(file, 'a') as f: 118 | f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') 119 | 120 | if self.tb: 121 | for k, v in x.items(): 122 | self.tb.add_scalar(k, v, epoch) 123 | 124 | if self.wandb: 125 | self.wandb.log(x) 126 | self.wandb.end_epoch(best_result=best_fitness == fi) 127 | 128 | def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): 129 | # Callback runs on model save event 130 | if self.wandb: 131 | if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1: 132 | self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) 133 | 134 | def on_train_end(self, last, best, plots, epoch, results): 135 | # Callback runs on training end 136 | if plots: 137 | plot_results(file=self.save_dir / 'results.csv') # save results.png 138 | files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))] 139 | files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter 140 | 141 | if self.tb: 142 | import cv2 143 | for f in files: 144 | self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') 145 | 146 | if self.wandb: 147 | self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) 148 | # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model 149 | if not self.opt.evolve: 150 | wandb.log_artifact(str(best if best.exists() else last), type='model', 151 | name='run_' + self.wandb.wandb_run.id + '_model', 152 | aliases=['latest', 'best', 'stripped']) 153 | self.wandb.finish_run() 154 | else: 155 | self.wandb.finish_run() 156 | self.wandb = WandbLogger(self.opt) 157 | -------------------------------------------------------------------------------- /loggers/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/loggers/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /loggers/wandb/README.md: -------------------------------------------------------------------------------- 1 | 📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 29 September 2021. 2 | * [About Weights & Biases](#about-weights-&-biases) 3 | * [First-Time Setup](#first-time-setup) 4 | * [Viewing runs](#viewing-runs) 5 | * [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) 6 | * [Reports: Share your work with the world!](#reports) 7 | 8 | ## About Weights & Biases 9 | Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions. 10 | 11 | Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows: 12 | 13 | * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time 14 | * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically 15 | * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization 16 | * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators 17 | * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently 18 | * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models 19 | 20 | ## First-Time Setup 21 |
22 | Toggle Details 23 | When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device. 24 | 25 | W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as: 26 | 27 | ```shell 28 | $ python train.py --project ... --name ... 29 | ``` 30 | 31 | YOLOv5 notebook example: Open In Colab Open In Kaggle 32 | Screen Shot 2021-09-29 at 10 23 13 PM 33 | 34 | 35 |
36 | 37 | ## Viewing Runs 38 |
39 | Toggle Details 40 | Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged: 41 | 42 | * Training & Validation losses 43 | * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 44 | * Learning Rate over time 45 | * A bounding box debugging panel, showing the training progress over time 46 | * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** 47 | * System: Disk I/0, CPU utilization, RAM memory usage 48 | * Your trained model as W&B Artifact 49 | * Environment: OS and Python types, Git repository and state, **training command** 50 | 51 |

Weights & Biases dashboard

52 | 53 | 54 |
55 | 56 | ## Advanced Usage 57 | You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started. 58 |
59 |

1. Visualize and Version Datasets

60 | Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact. 61 |
62 | Usage 63 | Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. 64 | 65 | ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) 66 |
67 | 68 |

2: Train and Log Evaluation simultaneousy

69 | This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table 70 | Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, 71 | so no images will be uploaded from your system more than once. 72 |
73 | Usage 74 | Code $ python utils/logger/wandb/log_dataset.py --data .. --upload_data 75 | 76 | ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) 77 |
78 | 79 |

3: Train using dataset artifact

80 | When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that 81 | can be used to train a model directly from the dataset artifact. This also logs evaluation 82 |
83 | Usage 84 | Code $ python utils/logger/wandb/log_dataset.py --data {data}_wandb.yaml 85 | 86 | ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) 87 |
88 | 89 |

4: Save model checkpoints as artifacts

90 | To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. 91 | You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged 92 | 93 |
94 | Usage 95 | Code $ python train.py --save_period 1 96 | 97 | ![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) 98 |
99 | 100 |
101 | 102 |

5: Resume runs from checkpoint artifacts.

103 | Any run can be resumed using artifacts if the --resume argument starts with wandb-artifact:// prefix followed by the run path, i.e, wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system. 104 | 105 |
106 | Usage 107 | Code $ python train.py --resume wandb-artifact://{run_path} 108 | 109 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 110 |
111 | 112 |

6: Resume runs from dataset artifact & checkpoint artifacts.

113 | Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device 114 | The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset or 115 | train from _wandb.yaml file and set --save_period 116 | 117 |
118 | Usage 119 | Code $ python train.py --resume wandb-artifact://{run_path} 120 | 121 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 122 |
123 | 124 | 125 | 126 | 127 |

Reports

128 | W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)). 129 | 130 | Weights & Biases Reports 131 | 132 | 133 | ## Environments 134 | 135 | YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): 136 | 137 | - **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle 138 | - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 139 | - **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) 140 | - **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls 141 | 142 | 143 | ## Status 144 | 145 | ![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) 146 | 147 | If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit. 148 | -------------------------------------------------------------------------------- /loggers/wandb/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/loggers/wandb/__init__.py -------------------------------------------------------------------------------- /loggers/wandb/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/loggers/wandb/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /loggers/wandb/__pycache__/wandb_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/loggers/wandb/__pycache__/wandb_utils.cpython-38.pyc -------------------------------------------------------------------------------- /loggers/wandb/log_dataset.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | from wandb_utils import WandbLogger 4 | 5 | from utils.general import LOGGER 6 | 7 | WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' 8 | 9 | 10 | def create_dataset_artifact(opt): 11 | logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused 12 | if not logger.wandb: 13 | LOGGER.info("install wandb using `pip install wandb` to log the dataset") 14 | 15 | 16 | if __name__ == '__main__': 17 | parser = argparse.ArgumentParser() 18 | parser.add_argument('--data', type=str, default='data/coco128.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='YOLOv5', help='name of W&B Project') 21 | parser.add_argument('--entity', default=None, help='W&B entity') 22 | parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run') 23 | 24 | opt = parser.parse_args() 25 | opt.resume = False # Explicitly disallow resume check for dataset upload job 26 | 27 | create_dataset_artifact(opt) 28 | -------------------------------------------------------------------------------- /loggers/wandb/sweep.py: -------------------------------------------------------------------------------- 1 | import sys 2 | from pathlib import Path 3 | 4 | import wandb 5 | 6 | FILE = Path(__file__).resolve() 7 | ROOT = FILE.parents[3] # YOLOv5 root directory 8 | if str(ROOT) not in sys.path: 9 | sys.path.append(str(ROOT)) # add ROOT to PATH 10 | 11 | from train import parse_opt, train 12 | from utils.callbacks import Callbacks 13 | from utils.general import increment_path 14 | from utils.torch_utils import select_device 15 | 16 | 17 | def sweep(): 18 | wandb.init() 19 | # Get hyp dict from sweep agent 20 | hyp_dict = vars(wandb.config).get("_items") 21 | 22 | # Workaround: get necessary opt args 23 | opt = parse_opt(known=True) 24 | opt.batch_size = hyp_dict.get("batch_size") 25 | opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) 26 | opt.epochs = hyp_dict.get("epochs") 27 | opt.nosave = True 28 | opt.data = hyp_dict.get("data") 29 | opt.weights = str(opt.weights) 30 | opt.cfg = str(opt.cfg) 31 | opt.data = str(opt.data) 32 | opt.hyp = str(opt.hyp) 33 | opt.project = str(opt.project) 34 | device = select_device(opt.device, batch_size=opt.batch_size) 35 | 36 | # train 37 | train(hyp_dict, opt, device, callbacks=Callbacks()) 38 | 39 | 40 | if __name__ == "__main__": 41 | sweep() 42 | -------------------------------------------------------------------------------- /loggers/wandb/sweep.yaml: -------------------------------------------------------------------------------- 1 | # Hyperparameters for training 2 | # To set range- 3 | # Provide min and max values as: 4 | # parameter: 5 | # 6 | # min: scalar 7 | # max: scalar 8 | # OR 9 | # 10 | # Set a specific list of search space- 11 | # parameter: 12 | # values: [scalar1, scalar2, scalar3...] 13 | # 14 | # You can use grid, bayesian and hyperopt search strategy 15 | # For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration 16 | 17 | program: utils/loggers/wandb/sweep.py 18 | method: random 19 | metric: 20 | name: metrics/mAP_0.5 21 | goal: maximize 22 | 23 | parameters: 24 | # hyperparameters: set either min, max range or values list 25 | data: 26 | value: "data/coco128.yaml" 27 | batch_size: 28 | values: [64] 29 | epochs: 30 | values: [10] 31 | 32 | lr0: 33 | distribution: uniform 34 | min: 1e-5 35 | max: 1e-1 36 | lrf: 37 | distribution: uniform 38 | min: 0.01 39 | max: 1.0 40 | momentum: 41 | distribution: uniform 42 | min: 0.6 43 | max: 0.98 44 | weight_decay: 45 | distribution: uniform 46 | min: 0.0 47 | max: 0.001 48 | warmup_epochs: 49 | distribution: uniform 50 | min: 0.0 51 | max: 5.0 52 | warmup_momentum: 53 | distribution: uniform 54 | min: 0.0 55 | max: 0.95 56 | warmup_bias_lr: 57 | distribution: uniform 58 | min: 0.0 59 | max: 0.2 60 | box: 61 | distribution: uniform 62 | min: 0.02 63 | max: 0.2 64 | cls: 65 | distribution: uniform 66 | min: 0.2 67 | max: 4.0 68 | cls_pw: 69 | distribution: uniform 70 | min: 0.5 71 | max: 2.0 72 | obj: 73 | distribution: uniform 74 | min: 0.2 75 | max: 4.0 76 | obj_pw: 77 | distribution: uniform 78 | min: 0.5 79 | max: 2.0 80 | iou_t: 81 | distribution: uniform 82 | min: 0.1 83 | max: 0.7 84 | anchor_t: 85 | distribution: uniform 86 | min: 2.0 87 | max: 8.0 88 | fl_gamma: 89 | distribution: uniform 90 | min: 0.0 91 | max: 0.1 92 | hsv_h: 93 | distribution: uniform 94 | min: 0.0 95 | max: 0.1 96 | hsv_s: 97 | distribution: uniform 98 | min: 0.0 99 | max: 0.9 100 | hsv_v: 101 | distribution: uniform 102 | min: 0.0 103 | max: 0.9 104 | degrees: 105 | distribution: uniform 106 | min: 0.0 107 | max: 45.0 108 | translate: 109 | distribution: uniform 110 | min: 0.0 111 | max: 0.9 112 | scale: 113 | distribution: uniform 114 | min: 0.0 115 | max: 0.9 116 | shear: 117 | distribution: uniform 118 | min: 0.0 119 | max: 10.0 120 | perspective: 121 | distribution: uniform 122 | min: 0.0 123 | max: 0.001 124 | flipud: 125 | distribution: uniform 126 | min: 0.0 127 | max: 1.0 128 | fliplr: 129 | distribution: uniform 130 | min: 0.0 131 | max: 1.0 132 | mosaic: 133 | distribution: uniform 134 | min: 0.0 135 | max: 1.0 136 | mixup: 137 | distribution: uniform 138 | min: 0.0 139 | max: 1.0 140 | copy_paste: 141 | distribution: uniform 142 | min: 0.0 143 | max: 1.0 144 | -------------------------------------------------------------------------------- /loss.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Loss functions 4 | """ 5 | 6 | import torch 7 | import torch.nn as nn 8 | 9 | from utils.metrics import bbox_iou 10 | from utils.torch_utils import is_parallel 11 | 12 | 13 | def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441 14 | # return positive, negative label smoothing BCE targets 15 | return 1.0 - 0.5 * eps, 0.5 * eps 16 | 17 | 18 | class BCEBlurWithLogitsLoss(nn.Module): 19 | # BCEwithLogitLoss() with reduced missing label effects. 20 | def __init__(self, alpha=0.05): 21 | super().__init__() 22 | self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss() 23 | self.alpha = alpha 24 | 25 | def forward(self, pred, true): 26 | loss = self.loss_fcn(pred, true) 27 | pred = torch.sigmoid(pred) # prob from logits 28 | dx = pred - true # reduce only missing label effects 29 | # dx = (pred - true).abs() # reduce missing label and false label effects 30 | alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4)) 31 | loss *= alpha_factor 32 | return loss.mean() 33 | 34 | 35 | class FocalLoss(nn.Module): 36 | # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) 37 | def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): 38 | super().__init__() 39 | self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() 40 | self.gamma = gamma 41 | self.alpha = alpha 42 | self.reduction = loss_fcn.reduction 43 | self.loss_fcn.reduction = 'none' # required to apply FL to each element 44 | 45 | def forward(self, pred, true): 46 | loss = self.loss_fcn(pred, true) 47 | # p_t = torch.exp(-loss) 48 | # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability 49 | 50 | # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py 51 | pred_prob = torch.sigmoid(pred) # prob from logits 52 | p_t = true * pred_prob + (1 - true) * (1 - pred_prob) 53 | alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) 54 | modulating_factor = (1.0 - p_t) ** self.gamma 55 | loss *= alpha_factor * modulating_factor 56 | 57 | if self.reduction == 'mean': 58 | return loss.mean() 59 | elif self.reduction == 'sum': 60 | return loss.sum() 61 | else: # 'none' 62 | return loss 63 | 64 | 65 | class QFocalLoss(nn.Module): 66 | # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) 67 | def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): 68 | super().__init__() 69 | self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() 70 | self.gamma = gamma 71 | self.alpha = alpha 72 | self.reduction = loss_fcn.reduction 73 | self.loss_fcn.reduction = 'none' # required to apply FL to each element 74 | 75 | def forward(self, pred, true): 76 | loss = self.loss_fcn(pred, true) 77 | 78 | pred_prob = torch.sigmoid(pred) # prob from logits 79 | alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) 80 | modulating_factor = torch.abs(true - pred_prob) ** self.gamma 81 | loss *= alpha_factor * modulating_factor 82 | 83 | if self.reduction == 'mean': 84 | return loss.mean() 85 | elif self.reduction == 'sum': 86 | return loss.sum() 87 | else: # 'none' 88 | return loss 89 | 90 | 91 | class ComputeLoss: 92 | # Compute losses 93 | def __init__(self, model, autobalance=False): 94 | self.sort_obj_iou = False 95 | device = next(model.parameters()).device # get model device 96 | h = model.hyp # hyperparameters 97 | 98 | # Define criteria 99 | BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) 100 | BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) 101 | 102 | # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 103 | self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets 104 | 105 | # Focal loss 106 | g = h['fl_gamma'] # focal loss gamma 107 | if g > 0: 108 | BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) 109 | 110 | det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module 111 | self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7 112 | self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index 113 | self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance 114 | for k in 'na', 'nc', 'nl', 'anchors': 115 | setattr(self, k, getattr(det, k)) 116 | 117 | def __call__(self, p, targets): # predictions, targets, model 118 | device = targets.device 119 | lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device) 120 | tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets 121 | 122 | # Losses 123 | for i, pi in enumerate(p): # layer index, layer predictions 124 | b, a, gj, gi = indices[i] # image, anchor, gridy, gridx 125 | tobj = torch.zeros_like(pi[..., 0], device=device) # target obj 126 | 127 | n = b.shape[0] # number of targets 128 | if n: 129 | ps = pi[b, a, gj, gi] # prediction subset corresponding to targets 130 | 131 | # Regression 132 | pxy = ps[:, :2].sigmoid() * 2 - 0.5 133 | pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i] 134 | pbox = torch.cat((pxy, pwh), 1) # predicted box 135 | iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) 136 | lbox += (1.0 - iou).mean() # iou loss 137 | 138 | # Objectness 139 | score_iou = iou.detach().clamp(0).type(tobj.dtype) 140 | if self.sort_obj_iou: 141 | sort_id = torch.argsort(score_iou) 142 | b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id] 143 | tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio 144 | 145 | # Classification 146 | if self.nc > 1: # cls loss (only if multiple classes) 147 | t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets 148 | t[range(n), tcls[i]] = self.cp 149 | lcls += self.BCEcls(ps[:, 5:], t) # BCE 150 | 151 | # Append targets to text file 152 | # with open('targets.txt', 'a') as file: 153 | # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] 154 | 155 | obji = self.BCEobj(pi[..., 4], tobj) 156 | lobj += obji * self.balance[i] # obj loss 157 | if self.autobalance: 158 | self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() 159 | 160 | if self.autobalance: 161 | self.balance = [x / self.balance[self.ssi] for x in self.balance] 162 | lbox *= self.hyp['box'] 163 | lobj *= self.hyp['obj'] 164 | lcls *= self.hyp['cls'] 165 | bs = tobj.shape[0] # batch size 166 | 167 | return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach() 168 | 169 | def build_targets(self, p, targets): 170 | # Build targets for compute_loss(), input targets(image,class,x,y,w,h) 171 | na, nt = self.na, targets.shape[0] # number of anchors, targets 172 | tcls, tbox, indices, anch = [], [], [], [] 173 | gain = torch.ones(7, device=targets.device) # normalized to gridspace gain 174 | ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) 175 | targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices 176 | 177 | g = 0.5 # bias 178 | off = torch.tensor([[0, 0], 179 | [1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m 180 | # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm 181 | ], device=targets.device).float() * g # offsets 182 | 183 | for i in range(self.nl): 184 | anchors = self.anchors[i] 185 | gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain 186 | 187 | # Match targets to anchors 188 | t = targets * gain 189 | if nt: 190 | # Matches 191 | r = t[:, :, 4:6] / anchors[:, None] # wh ratio 192 | j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare 193 | # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) 194 | t = t[j] # filter 195 | 196 | # Offsets 197 | gxy = t[:, 2:4] # grid xy 198 | gxi = gain[[2, 3]] - gxy # inverse 199 | j, k = ((gxy % 1 < g) & (gxy > 1)).T 200 | l, m = ((gxi % 1 < g) & (gxi > 1)).T 201 | j = torch.stack((torch.ones_like(j), j, k, l, m)) 202 | t = t.repeat((5, 1, 1))[j] 203 | offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] 204 | else: 205 | t = targets[0] 206 | offsets = 0 207 | 208 | # Define 209 | b, c = t[:, :2].long().T # image, class 210 | gxy = t[:, 2:4] # grid xy 211 | gwh = t[:, 4:6] # grid wh 212 | gij = (gxy - offsets).long() 213 | gi, gj = gij.T # grid xy indices 214 | 215 | # Append 216 | a = t[:, 6].long() # anchor indices 217 | indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices 218 | tbox.append(torch.cat((gxy - gij, gwh), 1)) # box 219 | anch.append(anchors[a]) # anchors 220 | tcls.append(c) # class 221 | 222 | return tcls, tbox, indices, anch 223 | -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/models/__init__.py -------------------------------------------------------------------------------- /models/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/models/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/common.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/models/__pycache__/common.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/experimental.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/models/__pycache__/experimental.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/yolo.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/models/__pycache__/yolo.cpython-38.pyc -------------------------------------------------------------------------------- /models/experimental.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Experimental modules 4 | """ 5 | import math 6 | 7 | import numpy as np 8 | import torch 9 | import torch.nn as nn 10 | 11 | from models.common import Conv 12 | from utils.downloads import attempt_download 13 | 14 | 15 | class CrossConv(nn.Module): 16 | # Cross Convolution Downsample 17 | def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): 18 | # ch_in, ch_out, kernel, stride, groups, expansion, shortcut 19 | super().__init__() 20 | c_ = int(c2 * e) # hidden channels 21 | self.cv1 = Conv(c1, c_, (1, k), (1, s)) 22 | self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) 23 | self.add = shortcut and c1 == c2 24 | 25 | def forward(self, x): 26 | return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) 27 | 28 | 29 | class Sum(nn.Module): 30 | # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 31 | def __init__(self, n, weight=False): # n: number of inputs 32 | super().__init__() 33 | self.weight = weight # apply weights boolean 34 | self.iter = range(n - 1) # iter object 35 | if weight: 36 | self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights 37 | 38 | def forward(self, x): 39 | y = x[0] # no weight 40 | if self.weight: 41 | w = torch.sigmoid(self.w) * 2 42 | for i in self.iter: 43 | y = y + x[i + 1] * w[i] 44 | else: 45 | for i in self.iter: 46 | y = y + x[i + 1] 47 | return y 48 | 49 | 50 | class MixConv2d(nn.Module): 51 | # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595 52 | def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy 53 | super().__init__() 54 | n = len(k) # number of convolutions 55 | if equal_ch: # equal c_ per group 56 | i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices 57 | c_ = [(i == g).sum() for g in range(n)] # intermediate channels 58 | else: # equal weight.numel() per group 59 | b = [c2] + [0] * n 60 | a = np.eye(n + 1, n, k=-1) 61 | a -= np.roll(a, 1, axis=1) 62 | a *= np.array(k) ** 2 63 | a[0] = 1 64 | c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b 65 | 66 | self.m = nn.ModuleList( 67 | [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)]) 68 | self.bn = nn.BatchNorm2d(c2) 69 | self.act = nn.SiLU() 70 | 71 | def forward(self, x): 72 | return self.act(self.bn(torch.cat([m(x) for m in self.m], 1))) 73 | 74 | 75 | class Ensemble(nn.ModuleList): 76 | # Ensemble of models 77 | def __init__(self): 78 | super().__init__() 79 | 80 | def forward(self, x, augment=False, profile=False, visualize=False): 81 | y = [] 82 | for module in self: 83 | y.append(module(x, augment, profile, visualize)[0]) 84 | # y = torch.stack(y).max(0)[0] # max ensemble 85 | # y = torch.stack(y).mean(0) # mean ensemble 86 | y = torch.cat(y, 1) # nms ensemble 87 | return y, None # inference, train output 88 | 89 | 90 | def attempt_load(weights, map_location=None, inplace=True, fuse=True): 91 | from models.yolo import Detect, Model 92 | 93 | # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a 94 | model = Ensemble() 95 | for w in weights if isinstance(weights, list) else [weights]: 96 | ckpt = torch.load(attempt_download(w), map_location=map_location) # load 97 | if fuse: 98 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model 99 | else: 100 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse 101 | 102 | # Compatibility updates 103 | for m in model.modules(): 104 | if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]: 105 | m.inplace = inplace # pytorch 1.7.0 compatibility 106 | if type(m) is Detect: 107 | if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility 108 | delattr(m, 'anchor_grid') 109 | setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl) 110 | elif type(m) is Conv: 111 | m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility 112 | 113 | if len(model) == 1: 114 | return model[-1] # return model 115 | else: 116 | print(f'Ensemble created with {weights}\n') 117 | for k in ['names']: 118 | setattr(model, k, getattr(model[-1], k)) 119 | model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride 120 | return model # return ensemble 121 | -------------------------------------------------------------------------------- /models/hub/anchors.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Default anchors for COCO data 3 | 4 | 5 | # P5 ------------------------------------------------------------------------------------------------------------------- 6 | # P5-640: 7 | anchors_p5_640: 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 | 13 | # P6 ------------------------------------------------------------------------------------------------------------------- 14 | # P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387 15 | anchors_p6_640: 16 | - [9,11, 21,19, 17,41] # P3/8 17 | - [43,32, 39,70, 86,64] # P4/16 18 | - [65,131, 134,130, 120,265] # P5/32 19 | - [282,180, 247,354, 512,387] # P6/64 20 | 21 | # P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 22 | anchors_p6_1280: 23 | - [19,27, 44,40, 38,94] # P3/8 24 | - [96,68, 86,152, 180,137] # P4/16 25 | - [140,301, 303,264, 238,542] # P5/32 26 | - [436,615, 739,380, 925,792] # P6/64 27 | 28 | # P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187 29 | anchors_p6_1920: 30 | - [28,41, 67,59, 57,141] # P3/8 31 | - [144,103, 129,227, 270,205] # P4/16 32 | - [209,452, 455,396, 358,812] # P5/32 33 | - [653,922, 1109,570, 1387,1187] # P6/64 34 | 35 | 36 | # P7 ------------------------------------------------------------------------------------------------------------------- 37 | # P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372 38 | anchors_p7_640: 39 | - [11,11, 13,30, 29,20] # P3/8 40 | - [30,46, 61,38, 39,92] # P4/16 41 | - [78,80, 146,66, 79,163] # P5/32 42 | - [149,150, 321,143, 157,303] # P6/64 43 | - [257,402, 359,290, 524,372] # P7/128 44 | 45 | # P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818 46 | anchors_p7_1280: 47 | - [19,22, 54,36, 32,77] # P3/8 48 | - [70,83, 138,71, 75,173] # P4/16 49 | - [165,159, 148,334, 375,151] # P5/32 50 | - [334,317, 251,626, 499,474] # P6/64 51 | - [750,326, 534,814, 1079,818] # P7/128 52 | 53 | # P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227 54 | anchors_p7_1920: 55 | - [29,34, 81,55, 47,115] # P3/8 56 | - [105,124, 207,107, 113,259] # P4/16 57 | - [247,238, 222,500, 563,227] # P5/32 58 | - [501,476, 376,939, 749,711] # P6/64 59 | - [1126,489, 801,1222, 1618,1227] # P7/128 60 | -------------------------------------------------------------------------------- /models/hub/yolov3-spp.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | -------------------------------------------------------------------------------- /models/hub/yolov3-tiny.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,14, 23,27, 37,58] # P4/16 9 | - [81,82, 135,169, 344,319] # P5/32 10 | 11 | # YOLOv3-tiny backbone 12 | backbone: 13 | # [from, number, module, args] 14 | [[-1, 1, Conv, [16, 3, 1]], # 0 15 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2 16 | [-1, 1, Conv, [32, 3, 1]], 17 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4 18 | [-1, 1, Conv, [64, 3, 1]], 19 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8 20 | [-1, 1, Conv, [128, 3, 1]], 21 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16 22 | [-1, 1, Conv, [256, 3, 1]], 23 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32 24 | [-1, 1, Conv, [512, 3, 1]], 25 | [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11 26 | [-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12 27 | ] 28 | 29 | # YOLOv3-tiny head 30 | head: 31 | [[-1, 1, Conv, [1024, 3, 1]], 32 | [-1, 1, Conv, [256, 1, 1]], 33 | [-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large) 34 | 35 | [-2, 1, Conv, [128, 1, 1]], 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 38 | [-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium) 39 | 40 | [[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5) 41 | ] 42 | -------------------------------------------------------------------------------- /models/hub/yolov3.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | -------------------------------------------------------------------------------- /models/hub/yolov5-bifpn.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 BiFPN head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14, 6], 1, Concat, [1]], # cat P4 <--- BiFPN change 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5-fpn.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 FPN head 28 | head: 29 | [[-1, 3, C3, [1024, False]], # 10 (P5/32-large) 30 | 31 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 32 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 3, C3, [512, False]], # 14 (P4/16-medium) 35 | 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 3, C3, [256, False]], # 18 (P3/8-small) 40 | 41 | [[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 42 | ] 43 | -------------------------------------------------------------------------------- /models/hub/yolov5-p2.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 # auto-anchor evolves 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 6, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 20 | [-1, 3, C3, [1024]], 21 | [-1, 1, SPPF, [1024, 5]], # 9 22 | ] 23 | 24 | # YOLOv5 v6.0 head 25 | head: 26 | [[-1, 1, Conv, [512, 1, 1]], 27 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 28 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 29 | [-1, 3, C3, [512, False]], # 13 30 | 31 | [-1, 1, Conv, [256, 1, 1]], 32 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 33 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 34 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 35 | 36 | [-1, 1, Conv, [128, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 2], 1, Concat, [1]], # cat backbone P2 39 | [-1, 1, C3, [128, False]], # 21 (P2/4-xsmall) 40 | 41 | [-1, 1, Conv, [128, 3, 2]], 42 | [[-1, 18], 1, Concat, [1]], # cat head P3 43 | [-1, 3, C3, [256, False]], # 24 (P3/8-small) 44 | 45 | [-1, 1, Conv, [256, 3, 2]], 46 | [[-1, 14], 1, Concat, [1]], # cat head P4 47 | [-1, 3, C3, [512, False]], # 27 (P4/16-medium) 48 | 49 | [-1, 1, Conv, [512, 3, 2]], 50 | [[-1, 10], 1, Concat, [1]], # cat head P5 51 | [-1, 3, C3, [1024, False]], # 30 (P5/32-large) 52 | 53 | [[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5) 54 | ] 55 | -------------------------------------------------------------------------------- /models/hub/yolov5-p6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 # auto-anchor 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 6, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 20 | [-1, 3, C3, [768]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 22 | [-1, 3, C3, [1024]], 23 | [-1, 1, SPPF, [1024, 5]], # 11 24 | ] 25 | 26 | # YOLOv5 v6.0 head 27 | head: 28 | [[-1, 1, Conv, [768, 1, 1]], 29 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 30 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 31 | [-1, 3, C3, [768, False]], # 15 32 | 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 36 | [-1, 3, C3, [512, False]], # 19 37 | 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 41 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 42 | 43 | [-1, 1, Conv, [256, 3, 2]], 44 | [[-1, 20], 1, Concat, [1]], # cat head P4 45 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 46 | 47 | [-1, 1, Conv, [512, 3, 2]], 48 | [[-1, 16], 1, Concat, [1]], # cat head P5 49 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 50 | 51 | [-1, 1, Conv, [768, 3, 2]], 52 | [[-1, 12], 1, Concat, [1]], # cat head P6 53 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 54 | 55 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 56 | ] 57 | -------------------------------------------------------------------------------- /models/hub/yolov5-p7.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 # auto-anchor 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 6, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 20 | [-1, 3, C3, [768]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 22 | [-1, 3, C3, [1024]], 23 | [-1, 1, Conv, [1280, 3, 2]], # 11-P7/128 24 | [-1, 3, C3, [1280]], 25 | [-1, 1, SPPF, [1280, 5]], # 13 26 | ] 27 | 28 | # YOLOv5 head 29 | head: 30 | [[-1, 1, Conv, [1024, 1, 1]], 31 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 32 | [[-1, 10], 1, Concat, [1]], # cat backbone P6 33 | [-1, 3, C3, [1024, False]], # 17 34 | 35 | [-1, 1, Conv, [768, 1, 1]], 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 38 | [-1, 3, C3, [768, False]], # 21 39 | 40 | [-1, 1, Conv, [512, 1, 1]], 41 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 42 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 43 | [-1, 3, C3, [512, False]], # 25 44 | 45 | [-1, 1, Conv, [256, 1, 1]], 46 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 47 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 48 | [-1, 3, C3, [256, False]], # 29 (P3/8-small) 49 | 50 | [-1, 1, Conv, [256, 3, 2]], 51 | [[-1, 26], 1, Concat, [1]], # cat head P4 52 | [-1, 3, C3, [512, False]], # 32 (P4/16-medium) 53 | 54 | [-1, 1, Conv, [512, 3, 2]], 55 | [[-1, 22], 1, Concat, [1]], # cat head P5 56 | [-1, 3, C3, [768, False]], # 35 (P5/32-large) 57 | 58 | [-1, 1, Conv, [768, 3, 2]], 59 | [[-1, 18], 1, Concat, [1]], # cat head P6 60 | [-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge) 61 | 62 | [-1, 1, Conv, [1024, 3, 2]], 63 | [[-1, 14], 1, Concat, [1]], # cat head P7 64 | [-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge) 65 | 66 | [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7) 67 | ] 68 | -------------------------------------------------------------------------------- /models/hub/yolov5-panet.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 PANet head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5l6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5m6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.67 # model depth multiple 6 | width_multiple: 0.75 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5n6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.25 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5s-ghost.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3Ghost, [128]], 18 | [-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3Ghost, [256]], 20 | [-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3Ghost, [512]], 22 | [-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3Ghost, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, GhostConv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3Ghost, [512, False]], # 13 33 | 34 | [-1, 1, GhostConv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, GhostConv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, GhostConv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5s-transformer.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3TR, [1024]], # 9 <--- C3TR() Transformer module 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5s6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5x6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.33 # model depth multiple 6 | width_multiple: 1.25 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/mask_yolov5l.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/mask_yolov5m.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 0.67 # model depth multiple 6 | width_multiple: 0.75 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/mask_yolov5s.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5l.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5m.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 0.67 # model depth multiple 6 | width_multiple: 0.75 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5n.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.25 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5s.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5x.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 2 # number of classes 5 | depth_multiple: 1.33 # model depth multiple 6 | width_multiple: 1.25 # layer channel multiple 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 | # YOLOv5 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 6, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /pic/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/1.png -------------------------------------------------------------------------------- /pic/11.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/11.png -------------------------------------------------------------------------------- /pic/12.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/12.png -------------------------------------------------------------------------------- /pic/13.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/13.png -------------------------------------------------------------------------------- /pic/14.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/14.png -------------------------------------------------------------------------------- /pic/2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/2.png -------------------------------------------------------------------------------- /pic/3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/3.png -------------------------------------------------------------------------------- /pic/4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/4.png -------------------------------------------------------------------------------- /pic/5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/pic/5.png -------------------------------------------------------------------------------- /torch_utils.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | PyTorch utils 4 | """ 5 | 6 | import datetime 7 | import math 8 | import os 9 | import platform 10 | import subprocess 11 | import time 12 | from contextlib import contextmanager 13 | from copy import deepcopy 14 | from pathlib import Path 15 | 16 | import torch 17 | import torch.distributed as dist 18 | import torch.nn as nn 19 | import torch.nn.functional as F 20 | 21 | from utils.general import LOGGER 22 | 23 | try: 24 | import thop # for FLOPs computation 25 | except ImportError: 26 | thop = None 27 | 28 | 29 | @contextmanager 30 | def torch_distributed_zero_first(local_rank: int): 31 | """ 32 | Decorator to make all processes in distributed training wait for each local_master to do something. 33 | """ 34 | if local_rank not in [-1, 0]: 35 | dist.barrier(device_ids=[local_rank]) 36 | yield 37 | if local_rank == 0: 38 | dist.barrier(device_ids=[0]) 39 | 40 | 41 | def date_modified(path=__file__): 42 | # return human-readable file modification date, i.e. '2021-3-26' 43 | t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime) 44 | return f'{t.year}-{t.month}-{t.day}' 45 | 46 | 47 | def git_describe(path=Path(__file__).parent): # path must be a directory 48 | # return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe 49 | s = f'git -C {path} describe --tags --long --always' 50 | try: 51 | return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1] 52 | except subprocess.CalledProcessError as e: 53 | return '' # not a git repository 54 | 55 | 56 | def select_device(device='', batch_size=None, newline=True): 57 | # device = 'cpu' or '0' or '0,1,2,3' 58 | s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string 59 | device = str(device).strip().lower().replace('cuda:', '') # to string, 'cuda:0' to '0' 60 | cpu = device == 'cpu' 61 | if cpu: 62 | os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False 63 | elif device: # non-cpu device requested 64 | os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable 65 | assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availability 66 | 67 | cuda = not cpu and torch.cuda.is_available() 68 | if cuda: 69 | devices = device.split(',') if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7 70 | n = len(devices) # device count 71 | if n > 1 and batch_size: # check batch_size is divisible by device_count 72 | assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}' 73 | space = ' ' * (len(s) + 1) 74 | for i, d in enumerate(devices): 75 | p = torch.cuda.get_device_properties(i) 76 | s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2:.0f}MiB)\n" # bytes to MB 77 | else: 78 | s += 'CPU\n' 79 | 80 | if not newline: 81 | s = s.rstrip() 82 | LOGGER.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe 83 | return torch.device('cuda:0' if cuda else 'cpu') 84 | 85 | 86 | def time_sync(): 87 | # pytorch-accurate time 88 | if torch.cuda.is_available(): 89 | torch.cuda.synchronize() 90 | return time.time() 91 | 92 | 93 | def profile(input, ops, n=10, device=None): 94 | # YOLOv5 speed/memory/FLOPs profiler 95 | # 96 | # Usage: 97 | # input = torch.randn(16, 3, 640, 640) 98 | # m1 = lambda x: x * torch.sigmoid(x) 99 | # m2 = nn.SiLU() 100 | # profile(input, [m1, m2], n=100) # profile over 100 iterations 101 | 102 | results = [] 103 | device = device or select_device() 104 | print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}" 105 | f"{'input':>24s}{'output':>24s}") 106 | 107 | for x in input if isinstance(input, list) else [input]: 108 | x = x.to(device) 109 | x.requires_grad = True 110 | for m in ops if isinstance(ops, list) else [ops]: 111 | m = m.to(device) if hasattr(m, 'to') else m # device 112 | m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m 113 | tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward 114 | try: 115 | flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs 116 | except: 117 | flops = 0 118 | 119 | try: 120 | for _ in range(n): 121 | t[0] = time_sync() 122 | y = m(x) 123 | t[1] = time_sync() 124 | try: 125 | _ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward() 126 | t[2] = time_sync() 127 | except Exception as e: # no backward method 128 | # print(e) # for debug 129 | t[2] = float('nan') 130 | tf += (t[1] - t[0]) * 1000 / n # ms per op forward 131 | tb += (t[2] - t[1]) * 1000 / n # ms per op backward 132 | mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0 # (GB) 133 | s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list' 134 | s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list' 135 | p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters 136 | print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}') 137 | results.append([p, flops, mem, tf, tb, s_in, s_out]) 138 | except Exception as e: 139 | print(e) 140 | results.append(None) 141 | torch.cuda.empty_cache() 142 | return results 143 | 144 | 145 | def is_parallel(model): 146 | # Returns True if model is of type DP or DDP 147 | return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel) 148 | 149 | 150 | def de_parallel(model): 151 | # De-parallelize a model: returns single-GPU model if model is of type DP or DDP 152 | return model.module if is_parallel(model) else model 153 | 154 | 155 | def initialize_weights(model): 156 | for m in model.modules(): 157 | t = type(m) 158 | if t is nn.Conv2d: 159 | pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') 160 | elif t is nn.BatchNorm2d: 161 | m.eps = 1e-3 162 | m.momentum = 0.03 163 | elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]: 164 | m.inplace = True 165 | 166 | 167 | def find_modules(model, mclass=nn.Conv2d): 168 | # Finds layer indices matching module class 'mclass' 169 | return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)] 170 | 171 | 172 | def sparsity(model): 173 | # Return global model sparsity 174 | a, b = 0, 0 175 | for p in model.parameters(): 176 | a += p.numel() 177 | b += (p == 0).sum() 178 | return b / a 179 | 180 | 181 | def prune(model, amount=0.3): 182 | # Prune model to requested global sparsity 183 | import torch.nn.utils.prune as prune 184 | print('Pruning model... ', end='') 185 | for name, m in model.named_modules(): 186 | if isinstance(m, nn.Conv2d): 187 | prune.l1_unstructured(m, name='weight', amount=amount) # prune 188 | prune.remove(m, 'weight') # make permanent 189 | print(' %.3g global sparsity' % sparsity(model)) 190 | 191 | 192 | def fuse_conv_and_bn(conv, bn): 193 | # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/ 194 | fusedconv = nn.Conv2d(conv.in_channels, 195 | conv.out_channels, 196 | kernel_size=conv.kernel_size, 197 | stride=conv.stride, 198 | padding=conv.padding, 199 | groups=conv.groups, 200 | bias=True).requires_grad_(False).to(conv.weight.device) 201 | 202 | # prepare filters 203 | w_conv = conv.weight.clone().view(conv.out_channels, -1) 204 | w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) 205 | fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape)) 206 | 207 | # prepare spatial bias 208 | b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias 209 | b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) 210 | fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) 211 | 212 | return fusedconv 213 | 214 | 215 | def model_info(model, verbose=False, img_size=640): 216 | # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320] 217 | n_p = sum(x.numel() for x in model.parameters()) # number parameters 218 | n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients 219 | if verbose: 220 | print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}") 221 | for i, (name, p) in enumerate(model.named_parameters()): 222 | name = name.replace('module_list.', '') 223 | print('%5g %40s %9s %12g %20s %10.3g %10.3g' % 224 | (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std())) 225 | 226 | try: # FLOPs 227 | from thop import profile 228 | stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32 229 | img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input 230 | flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPs 231 | img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float 232 | fs = ', %.1f GFLOPs' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPs 233 | except (ImportError, Exception): 234 | fs = '' 235 | 236 | LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}") 237 | 238 | 239 | def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416) 240 | # scales img(bs,3,y,x) by ratio constrained to gs-multiple 241 | if ratio == 1.0: 242 | return img 243 | else: 244 | h, w = img.shape[2:] 245 | s = (int(h * ratio), int(w * ratio)) # new size 246 | img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize 247 | if not same_shape: # pad/crop img 248 | h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w)) 249 | return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean 250 | 251 | 252 | def copy_attr(a, b, include=(), exclude=()): 253 | # Copy attributes from b to a, options to only include [...] and to exclude [...] 254 | for k, v in b.__dict__.items(): 255 | if (len(include) and k not in include) or k.startswith('_') or k in exclude: 256 | continue 257 | else: 258 | setattr(a, k, v) 259 | 260 | 261 | class EarlyStopping: 262 | # YOLOv5 simple early stopper 263 | def __init__(self, patience=30): 264 | self.best_fitness = 0.0 # i.e. mAP 265 | self.best_epoch = 0 266 | self.patience = patience or float('inf') # epochs to wait after fitness stops improving to stop 267 | self.possible_stop = False # possible stop may occur next epoch 268 | 269 | def __call__(self, epoch, fitness): 270 | if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training 271 | self.best_epoch = epoch 272 | self.best_fitness = fitness 273 | delta = epoch - self.best_epoch # epochs without improvement 274 | self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch 275 | stop = delta >= self.patience # stop training if patience exceeded 276 | if stop: 277 | LOGGER.info(f'Stopping training early as no improvement observed in last {self.patience} epochs. ' 278 | f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n' 279 | f'To update EarlyStopping(patience={self.patience}) pass a new patience value, ' 280 | f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.') 281 | return stop 282 | 283 | 284 | class ModelEMA: 285 | """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models 286 | Keep a moving average of everything in the model state_dict (parameters and buffers). 287 | This is intended to allow functionality like 288 | https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage 289 | A smoothed version of the weights is necessary for some training schemes to perform well. 290 | This class is sensitive where it is initialized in the sequence of model init, 291 | GPU assignment and distributed training wrappers. 292 | """ 293 | 294 | def __init__(self, model, decay=0.9999, updates=0): 295 | # Create EMA 296 | self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA 297 | # if next(model.parameters()).device.type != 'cpu': 298 | # self.ema.half() # FP16 EMA 299 | self.updates = updates # number of EMA updates 300 | self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs) 301 | for p in self.ema.parameters(): 302 | p.requires_grad_(False) 303 | 304 | def update(self, model): 305 | # Update EMA parameters 306 | with torch.no_grad(): 307 | self.updates += 1 308 | d = self.decay(self.updates) 309 | 310 | msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict 311 | for k, v in self.ema.state_dict().items(): 312 | if v.dtype.is_floating_point: 313 | v *= d 314 | v += (1 - d) * msd[k].detach() 315 | 316 | def update_attr(self, model, include=(), exclude=('process_group', 'reducer')): 317 | # Update EMA attributes 318 | copy_attr(self.ema, model, include, exclude) 319 | -------------------------------------------------------------------------------- /ui/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: UTF-8 -*- 3 | ''' 4 | @Project ：yolov5-60 5 | @File ：__init__.py.py 6 | @Author ：ChenmingSong 7 | @Date ：2021/12/12 16:55 8 | @Description： 9 | ''' 10 | -------------------------------------------------------------------------------- /ui/ji.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | ------------------------------------------------- 4 | Project Name: yolov5-60 5 | File Name: ji.py 6 | Author: chenming 7 | Create Date: 2021/11/18 8 | Description： 9 | ------------------------------------------------- 10 | """ 11 | import argparse 12 | import os 13 | os.chdir("/home/chenming/scm/xianyu/det/yolov5-60/yolov5-60") 14 | import sys 15 | from pathlib import Path 16 | import cv2 17 | import torch 18 | import torch.backends.cudnn as cudnn 19 | import json 20 | FILE = Path(__file__).resolve() 21 | ROOT = FILE.parents[0] # YOLOv5 root directory 22 | if str(ROOT) not in sys.path: 23 | sys.path.append(str(ROOT)) # add ROOT to PATH 24 | ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative 25 | from models.common import DetectMultiBackend 26 | from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams 27 | from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, 28 | increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh) 29 | from utils.plots import Annotator, colors, save_one_box 30 | from utils.torch_utils import select_device, time_sync 31 | from utils.augmentations import letterbox 32 | import numpy as np 33 | 34 | 35 | @torch.no_grad() 36 | def init(): 37 | weights = "runs/train/exp2/weights/best.pt" # model.pt path(s) 38 | device = '' # cuda device, i.e. 0 or 0,1,2,3 or cpu 39 | half = False # use FP16 half-precision inference 40 | dnn = False # use OpenCV DNN for ONNX inference 41 | device = select_device(device) 42 | half &= device.type != 'cpu' # half precision only supported on CUDA 43 | # Load model 44 | # Load model 45 | device = select_device(device) 46 | model = DetectMultiBackend(weights, device=device, dnn=dnn) 47 | stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx 48 | # Half 49 | half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA 50 | if pt: 51 | model.model.half() if half else model.model.float() 52 | print("模型加载完成!") 53 | return model 54 | 55 | 56 | @torch.no_grad() 57 | def process_image(handle=None, input_image=None, args=None, **kwargs): 58 | '''Do inference to analysis input_image and get output 59 | Attributes: 60 | handle: algorithm handle returned by init() 61 | input_image (numpy.ndarray): image to be process, format: (h, w, c), BGR 62 | Returns: process result 63 | ''' 64 | 65 | # Process image here 66 | fake_result = { 67 | 'objects': [] 68 | } 69 | 70 | # Padded resize 71 | net = handle 72 | device = '' 73 | device = select_device(device) 74 | half = False 75 | augment = True 76 | visualize = False 77 | img_size = (640, 640) 78 | img0 = input_image 79 | stride = net.stride 80 | names = net.names 81 | img = letterbox(img0, img_size, stride=stride)[0] 82 | # Convert 83 | img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB 84 | img = np.ascontiguousarray(img) 85 | 86 | # pred 87 | im = torch.from_numpy(img).to(device) 88 | im = im.half() if half else im.float() # uint8 to fp16/32 89 | im /= 255 # 0 - 255 to 0.0 - 1.0 90 | if len(im.shape) == 3: 91 | im = im[None] # expand for batch dim 92 | # Inference 93 | 94 | pred = net(im, augment=augment, visualize=visualize) 95 | conf_thres = 0.25 96 | iou_thres = 0.45 97 | classes = None 98 | max_det = 1000 99 | agnostic_nms = False 100 | save_crop = False 101 | 102 | pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) 103 | 104 | for i, det in enumerate(pred): # per image 105 | # seen += 1 106 | # if webcam: # batch_size >= 1 107 | # p, im0, frame = path[i], im0s[i].copy(), dataset.count 108 | # s += f'{i}: ' 109 | # else: 110 | # p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) 111 | im0 = img0.copy() 112 | 113 | # p = Path(p) # to Path 114 | # save_path = str(save_dir / p.name) # im.jpg 115 | # txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt 116 | # s += '%gx%g ' % im.shape[2:] # print string 117 | gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh 118 | imc = im0.copy() if save_crop else im0 # for save_crop 119 | annotator = Annotator(im0, line_width=3, example=str(names)) 120 | if len(det): 121 | # Rescale boxes from img_size to im0 size 122 | det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round() 123 | 124 | # Print results 125 | for c in det[:, -1].unique(): 126 | n = (det[:, -1] == c).sum() # detections per class 127 | # s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string 128 | 129 | # Write results 130 | for *xyxy, conf, cls in reversed(det): 131 | # if save_txt: # Write to file 132 | xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh 133 | c = int(cls) # integer class 134 | label = f'{names[c]} {conf:.2f}' 135 | annotator.box_label(xyxy, label, color=colors(c, True)) 136 | 137 | xyxy = [x.cpu().numpy().item() for x in xyxy] 138 | conf = conf.cpu().numpy() 139 | name = names[c] 140 | # print(cls) 141 | # print(conf) 142 | # print(xyxy) 143 | # print(xywh) 144 | fake_result['objects'].append({ 145 | 'xmin': int(xyxy[0]), 146 | 'ymin': int(xyxy[1]), 147 | 'xmax': int(xyxy[2]), 148 | 'ymax': int(xyxy[3]), 149 | 'name': str(name), 150 | 'confidence': float(conf) 151 | }) 152 | # line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format 153 | # with open(txt_path + '.txt', 'a') as f: 154 | # f.write(('%g ' * len(line)).rstrip() % line + '\n') 155 | # if save_img or save_crop or view_img: # Add bbox to image 156 | # 157 | # 158 | # im0 = annotator.result() 159 | # # print(im0) 160 | # # if view_img: 161 | # cv2.imshow("test", im0) 162 | # cv2.waitKey(0) # 1 millisecond 163 | # cv2.destroyAllWindows() 164 | return json.dumps(fake_result, indent=4) 165 | 166 | # 现在的任务就是走通训练的流程，包括使用cpu进行训练和将日志文件以及模型输出到对应的位置中去 167 | if __name__ == '__main__': 168 | """Test python api 169 | """ 170 | img = cv2.imread('data/images/phone/phone_419.jpg') 171 | predictor = init() 172 | result = process_image(predictor, img) 173 | print(result) 174 | -------------------------------------------------------------------------------- /ui/server_main.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | ------------------------------------------------- 4 | Project Name: yolov5-v1.0 5 | File Name: main.py 6 | Author: chenming 7 | Create Date: 2021/11/9 8 | Description： 9 | ------------------------------------------------- 10 | """ 11 | # 首先检查文件，把存在的目录删除 12 | import os 13 | os.chdir("/project/train/src_repo/") 14 | # 启动数据处理 15 | os.system("python server_data_gen.py") 16 | os.system("python train_server.py >> /project/train/log/log.txt") 17 | # 启动训练 18 | -------------------------------------------------------------------------------- /ui/x.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: UTF-8 -*- 3 | ''' 4 | @Project ：yolov5-60 5 | @File ：x.py 6 | @Author ：ChenmingSong 7 | @Date ：2021/12/12 16:04 8 | @Description： 9 | ''' 10 | import cv2 11 | import sys 12 | # import DisplayUI 13 | from PyQt5.QtWidgets import QApplication, QMainWindow 14 | import threading 15 | from PyQt5.QtCore import QFile 16 | from PyQt5.QtWidgets import QFileDialog, QMessageBox 17 | from PyQt5.QtGui import QImage, QPixmap 18 | 19 | 20 | class Display: 21 | def __init__(self, ui, mainWnd): 22 | self.ui = ui 23 | self.mainWnd = mainWnd 24 | 25 | # 默认视频源为相机 26 | self.ui.radioButtonCam.setChecked(True) 27 | self.isCamera = True 28 | 29 | # 信号槽设置 30 | ui.Open.clicked.connect(self.Open) 31 | ui.Close.clicked.connect(self.Close) 32 | ui.radioButtonCam.clicked.connect(self.radioButtonCam) 33 | ui.radioButtonFile.clicked.connect(self.radioButtonFile) 34 | 35 | # 创建一个关闭事件并设为未触发 36 | self.stopEvent = threading.Event() 37 | self.stopEvent.clear() 38 | 39 | def radioButtonCam(self): 40 | self.isCamera = True 41 | 42 | def radioButtonFile(self): 43 | self.isCamera = False 44 | 45 | def Open(self): 46 | if not self.isCamera: 47 | self.fileName, self.fileType = QFileDialog.getOpenFileName(self.mainWnd, 'Choose file', '', '*.mp4') 48 | self.cap = cv2.VideoCapture(self.fileName) 49 | self.frameRate = self.cap.get(cv2.CAP_PROP_FPS) 50 | else: 51 | # 下面两种rtsp格式都是支持的 52 | # cap = cv2.VideoCapture("rtsp://admin:Supcon1304@172.20.1.126/main/Channels/1") 53 | self.cap = cv2.VideoCapture("rtsp://admin:Supcon1304@172.20.1.126:554/h264/ch1/main/av_stream") 54 | 55 | # 创建视频显示线程 56 | th = threading.Thread(target=self.Display) 57 | th.start() 58 | 59 | def Close(self): 60 | # 关闭事件设为触发，关闭视频播放 61 | self.stopEvent.set() 62 | 63 | def Display(self): 64 | self.ui.Open.setEnabled(False) 65 | self.ui.Close.setEnabled(True) 66 | 67 | while self.cap.isOpened(): 68 | success, frame = self.cap.read() 69 | # RGB转BGR 70 | frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR) 71 | img = QImage(frame.data, frame.shape[1], frame.shape[0], QImage.Format_RGB888) 72 | self.ui.DispalyLabel.setPixmap(QPixmap.fromImage(img)) 73 | 74 | if self.isCamera: 75 | cv2.waitKey(1) 76 | else: 77 | cv2.waitKey(int(1000 / self.frameRate)) 78 | 79 | # 判断关闭事件是否已触发 80 | if True == self.stopEvent.is_set(): 81 | # 关闭事件置为未触发，清空显示label 82 | self.stopEvent.clear() 83 | self.ui.DispalyLabel.clear() 84 | self.ui.Close.setEnabled(False) 85 | self.ui.Open.setEnabled(True) 86 | break 87 | 88 | if __name__ == '__main__': 89 | app = QApplication(sys.argv) 90 | mainWnd = QMainWindow() 91 | ui = DisplayUI.Ui_MainWindow() 92 | 93 | # 可以理解成将创建的 ui 绑定到新建的 mainWnd 上 94 | ui.setupUi(mainWnd) 95 | 96 | display = Display(ui, mainWnd) 97 | 98 | mainWnd.show() 99 | 100 | sys.exit(app.exec_()) 101 | -------------------------------------------------------------------------------- /yolov5s.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/usernameisalreadytaKeN1122/yolov5-fire/e35c38ca98ff49e7025daa445d176a15bd9ee401/yolov5s.pt --------------------------------------------------------------------------------