HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Update YOLOv3 and YOLOv5 YAMLs (#7574)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-01-14 20:10:32 +01:00 • committed by GitHub
parent 596c068b18
commit d762496989
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
51 changed files with 284 additions and 304 deletions
Download patch file Download diff file Expand all files Collapse all files

18
docs/en/yolov5/tutorials/architecture_description.md
View file

@ -161,8 +161,8 @@ The objectness losses of the three prediction layers (`P3`, `P4`, `P5`) are weig
The YOLOv5 architecture makes some important changes to the box prediction strategy compared to earlier versions of YOLO. In YOLOv2 and YOLOv3, the box coordinates were directly predicted using the activation of the last layer.
![b_x](https://latex.codecogs.com/svg.image?b_x=\sigma(t_x)+c_x)
![b_y](https://latex.codecogs.com/svg.image?b_y=\sigma(t_y)+c_y)
![b_x](<https://latex.codecogs.com/svg.image?b_x=\sigma(t_x)+c_x>)
![b_y](<https://latex.codecogs.com/svg.image?b_y=\sigma(t_y)+c_y>)
![b_w](https://latex.codecogs.com/svg.image?b_w=p_w\cdot&space;e^{t_w})
![b_h](https://latex.codecogs.com/svg.image?b_h=p_h\cdot&space;e^{t_h})
@ -172,10 +172,10 @@ However, in YOLOv5, the formula for predicting the box coordinates has been upda
The revised formulas for calculating the predicted bounding box are as follows:
![bx](https://latex.codecogs.com/svg.image?b_x=(2\cdot\sigma(t_x)-0.5)+c_x)
![by](https://latex.codecogs.com/svg.image?b_y=(2\cdot\sigma(t_y)-0.5)+c_y)
![bw](https://latex.codecogs.com/svg.image?b_w=p_w\cdot(2\cdot\sigma(t_w))^2)
![bh](https://latex.codecogs.com/svg.image?b_h=p_h\cdot(2\cdot\sigma(t_h))^2)
![bx](<https://latex.codecogs.com/svg.image?b_x=(2\cdot\sigma(t_x)-0.5)+c_x>)
![by](<https://latex.codecogs.com/svg.image?b_y=(2\cdot\sigma(t_y)-0.5)+c_y>)
![bw](<https://latex.codecogs.com/svg.image?b_w=p_w\cdot(2\cdot\sigma(t_w))^2>)
![bh](<https://latex.codecogs.com/svg.image?b_h=p_h\cdot(2\cdot\sigma(t_h))^2>)
Compare the center point offset before and after scaling. The center point offset range is adjusted from (0, 1) to (-0.5, 1.5). Therefore, offset can easily get 0 or 1.
@ -197,11 +197,11 @@ This process follows these steps:
![rh](https://latex.codecogs.com/svg.image?r_h=h_{gt}/h_{at})
![rwmax](https://latex.codecogs.com/svg.image?r_w^{max}=max(r_w,1/r_w))
![rwmax](<https://latex.codecogs.com/svg.image?r_w^{max}=max(r_w,1/r_w)>)
![rhmax](https://latex.codecogs.com/svg.image?r_h^{max}=max(r_h,1/r_h))
![rhmax](<https://latex.codecogs.com/svg.image?r_h^{max}=max(r_h,1/r_h)>)
![rmax](https://latex.codecogs.com/svg.image?r^{max}=max(r_w^{max},r_h^{max}))
![rmax](<https://latex.codecogs.com/svg.image?r^{max}=max(r_w^{max},r_h^{max})>)
![match](https://latex.codecogs.com/svg.image?r^{max}<{\rm&space;anchor_t})

4
docs/en/yolov5/tutorials/train_custom_data.md
View file

@ -77,7 +77,7 @@ Export in `YOLOv5 Pytorch` format, then copy the snippet into your training scri
### 2.1 Create `dataset.yaml`
[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](https://cocodataset.org/) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of overfitting. [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or *.txt files with image paths) and 2) a class `names` dictionary:
[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](https://cocodataset.org/) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of overfitting. [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or `*.txt` files with image paths) and 2) a class `names` dictionary:
```yaml
# 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, ..]
@ -114,7 +114,7 @@ The label file corresponding to the above image contains 2 persons (class `0`) a
### 2.3 Organize Directories
Organize your train and val images and labels according to the example below. YOLOv5 assumes `/coco128` is inside a `/datasets` directory **next to** the `/yolov5` directory. **YOLOv5 locates labels automatically for each image** by replacing the last instance of `/images/` in each image path with `/labels/`. For example:
Organize your train and val images and labels according to the example below. YOLOv5 assumes `/coco128` is inside a `/datasets` directory **next to** the `/yolov5` directory. **YOLOv5 locates labels automatically for each image** by replacing the last instance of `/images/` in each image path with `/labels/`. For example:
```bash
../datasets/coco128/images/im0.jpg # image

57
docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md
View file

@ -60,43 +60,42 @@ model.24.m.2.bias
Looking at the model architecture we can see that the model backbone is layers 0-9:
```yaml
# YOLOv5 backbone
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, BottleneckCSP, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
- [-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 head
# 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, BottleneckCSP, [512, False]], # 13
- [-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, BottleneckCSP, [256, False]], # 17 (P3/8-small)
- [-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, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
- [-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, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
- [-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)
]
- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)
```
so we can define the freeze list to contain all modules with 'model.0.' - 'model.9.' in their names: