参考:YOLOv5-5.0v-yaml 解析及模型构建(第二篇)_星魂非梦的博客-CSDN博客
前文:YOLOv5-v6.0-yolov5s网络架构详解(第一篇)_星魂非梦的博客-CSDN博客_yolov5s网络结构
本文目的是画出更规范的架构图。前文的不太规范。
1. v6.0相比v5.0的重要更新:Releases · ultralytics/yolov5 · GitHub-
Roboflow Integration ⭐ NEW: Train YOLOv5 models directly on any Roboflow dataset with our new integration(集成)! (#4975 by @Jacobsolawetz)
-
YOLOv5n 'Nano' models ⭐ NEW: New smaller YOLOv5n (1.9M params) model below YOLOv5s (7.5M params), exports to 2.1 MB INT8 size, ideal for ultralight(超轻量级) mobile(移动端) solutions. (#5027 by @glenn-jocher)
-
TensorFlow and Keras Export: TensorFlow, Keras, TFLite, TF.js model export now fully integrated(集成的) using
python export.py --include saved_model pb tflite tfjs
(#1127 by @zldrobit) -
OpenCV DNN: YOLOv5 ONNX models are now compatible(兼容) with both OpenCV DNN and ONNX Runtime (#4833 by @SamFC10).
-
Model Architecture: Updated backbones are slightly smaller, faster and more accurate.
- Replacement of
Focus()
with an equivalent(等同的)Conv(k=6, s=2, p=2)
layer (#4825 by @thomasbi1) for improved exportability(可移植性) - New
SPPF()
replacement forSPP()
layer for reduced ops (#4420 by @glenn-jocher) - Reduction in P3 backbone layer
C3()
repeats from 9 to 6 for improved speeds - Reorder(重新排序) places
SPPF()
at end of backbone - Reintroduction of shortcut in the last
C3()
backbone layer - Updated hyperparameters with increased mixup and copy-paste augmentation
- Replacement of
本文只关注Model Architecture的改变。
2. 配置文件:models/yolov5s.yaml# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
2.1 Replacement of Focus()
with an equivalent(等同的) Conv(k=6, s=2, p=2)
layer (#4825 by @thomasbi1) for improved exportability(可移植性)
2.2 New SPPF()
replacement for SPP()
layer for reduced ops (#4420 by @glenn-jocher)
2.3 Reduction in P3 backbone layer C3()
repeats from 9 to 6 for improved speeds
yolov5-5.0 架构图
yolov5-6.0 架构图
- Reorder(重新排序) places
SPPF()
at end of backbone - Reintroduction of shortcut in the last
C3()
backbone layer
从两个图可知:6.0 将SPPF()放在
backbone的最后;8模块为C3_1 引进了 shortcut。
补充:数据增强部分:increased mixup and copy-paste augmentation
4. 推理以上架构图为模型训练时候的图,在模型推理时候,models/yolo.py--Detect类中,会把3个head的输出进行 cat。
解释参考:YOLOv5-5.0v-yaml 解析及模型构建(第二篇)_星魂非梦的博客-CSDN博客
if not self.training: # inference
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
y = x[i].sigmoid()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
y = torch.cat((xy, wh, y[..., 4:]), -1)
z.append(y.view(bs, -1, self.no))
然后再进行后处理。
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)