Closed haoaZ closed 7 months ago
👋 Hello @haoaZ, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.
If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.
If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.
Python>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. To get started:
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install
YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.
We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!
Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.
Check out our YOLOv8 Docs for details and get started with:
pip install ultralytics
@haoaZ hi there! Thanks for reaching out. It looks like you're encountering an issue related to ECA-attention during training. The error message suggests an out-of-bounds index issue. Although the issue appears complex, it might be arising from the environment or the way the ECA-attention module is integrated into YOLOv5.
To troubleshoot, I recommend checking if the ECA-attention module is properly supported for training and if there are any compatibility issues with your specific environment. Additionally, reviewing the index manipulation and ensuring that it aligns with YOLOv5's requirements might also be helpful.
I appreciate your willingness to improve YOLOv5 and encourage you to keep at it - the YOLO community and the Ultralytics team are grateful for contributions of all kinds. If you're able to identify a resolution, feel free to submit a PR – it would be much appreciated!
Thanks for your reply, i have found the problem, the eca attention code in common.py is based on bath size=1, but the training is not 1. I will try to adjust the code to fit all bath sizes. If you have any suggestions for adjustment, I hope to receive your reply.
@haoaZ great to hear that you've identified the issue! Adapting the ECA attention code to accommodate varying batch sizes is a good approach. You may want to consider using dynamic tensor manipulations that can handle different batch sizes. Additionally, reviewing PyTorch's documentation on tensor operations for batched inputs could provide valuable insights.
Your dedication to improving the YOLOv5 framework is commendable. If you encounter specific challenges while making the adjustments, feel free to ask for help or guidance. Keep up the excellent work!
👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.
For additional resources and information, please see the links below:
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!
Thank you for your contributions to YOLO 🚀 and Vision AI ⭐
Search before asking
YOLOv5 Component
Training, Detection
Bug
I want to improve ECA-attention, but there have same bug, which i cant not solve, i want your help@glenn-jocher . When i run yolo.py it work, but run train.py, there have been some issues. `class EfficientChannelAttention(nn.Module): # Efficient Channel Attention module def init(self, c, b=1, gamma=2): super(EfficientChannelAttention, self).init() t = int(abs((math.log(c, 2) + b) / gamma)) k = t if t % 2 else t + 1
`# parameters nc: 80 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # layer channel multiple
anchors
anchors:
YOLOv5 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, C3, [128]], [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 [-1, 9, 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, 1, SPP, [1024, [5, 9, 13]]], [-1, 3, C3, [1024, False]], # 9 ]
YOLOv5 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, 1, EfficientChannelAttention, [512]], [[-1, 10], 1, Concat, [1]], # cat head P5 [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ])
sorted_indices为:tensor([ 27, 84, 107, ..., 539, 596, 706])
Traceback (most recent call last):
File "/home/wjh/learning/1/yolov5-5.0/train.py", line 543, in
train(hyp, opt, device, tb_writer)
File "/home/wjh/learning/1/yolov5-5.0/train.py", line 303, in train
pred = model(imgs) # forward
File "/home/wjh/.conda/envs/Yolov5/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "/home/wjh/learning/1/yolov5-5.0/models/yolo.py", line 123, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "/home/wjh/learning/1/yolov5-5.0/models/yolo.py", line 139, in forward_once
x = m(x) # run
File "/home/wjh/.conda/envs/Yolov5/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, **kwargs)
File "/home/wjh/learning/1/yolov5-5.0/models/common.py", line 411, in forward
sorted_x = torch.index_select(x, dim = 1, index =sorted_indices)
RuntimeError: INDICES element is out of DATA bounds, id=918 axis_dim=256
When i use cpu the follow problem appear:
Epoch gpu_mem box obj cls total labels img_size 0%| | 0/11049 [00:00<?, ?it/s] out_flat:tensor([ 0.13989, 0.01097, 0.67497, ..., 0.14956, 0.13888, -0.00238], grad_fn=进程已结束,退出代码` The display exceeds the index, but I have checked the index during yolo. py runtime and everything is fine,
Environment
No response
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?