model ensembling isn't working

[seven320]

🐛 Bug

When I detect some image by using ensembling, it doesn't work.

To Reproduce (REQUIRED)

Input:

!git clone https://github.com/ultralytics/yolov5  # clone repo
%cd yolov5
%pip install -qr requirements.txt  # install dependencies

import torch
from IPython.display import Image, clear_output  # to display images
import urllib

clear_output()
print(f"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})")

def download_file(url, dst_path):
    try:
        with urllib.request.urlopen(url) as web_file:
            data = web_file.read()
            with open(dst_path, mode='wb') as local_file:
                local_file.write(data)
    except urllib.error.URLError as e:
        print(e)

download_file('https://user-images.githubusercontent.com/26833433/124489091-ea4f9a00-ddb0-11eb-8ef1-d6f335c97f6f.jpg', "zidane.jpg")

!python detect.py --weights yolov5x.pt yolov5s.pt --img 640 --conf 0.25 --source data/images/
Image(filename='zidane.jpg', width=600)

Output:

image 1/2 /content/yolov5/yolov5/yolov5/yolov5/data/images/bus.jpg: Traceback (most recent call last):
  File "detect.py", line 228, in <module>
    main(opt)
  File "detect.py", line 223, in main
    run(**vars(opt))
  File "/usr/local/lib/python3.7/dist-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
    return func(*args, **kwargs)
  File "detect.py", line 106, in run
    visualize=increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False)[0]
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
TypeError: forward() got an unexpected keyword argument 'visualize'

Expected behavior

detect image with ensembling correctly.

Environment

If applicable, add screenshots to help explain your problem.

google colab

https://colab.research.google.com/drive/1rXRjuFTiHdJwbxhSIY8EywwQMrg3zCbV?usp=sharing

• OS: [e.g. Ubuntu]
• GPU Tesla P100

Additional context

I'm trying to fix it now. might be one day from now I will make pull request

[github-actions]

👋 Hello @seven320, 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 screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at [email protected].

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[seven320]

OK, I added screenshot to my bug issues!!

[glenn-jocher]

@seven320 you probably want to update Ensemble() class in models/experimental.py to something like this:

class Ensemble(nn.ModuleList):
    # Ensemble of models
    def __init__(self):
        super(Ensemble, self).__init__()

    def forward(self, x, augment=False, profile=False, visualize=False):
        y = []
        for module in self:
            y.append(module(x, augment, profile, visualize)[0])
        # y = torch.stack(y).max(0)[0]  # max ensemble
        # y = torch.stack(y).mean(0)  # mean ensemble
        y = torch.cat(y, 1)  # nms ensemble
        return y, None  # inference, train output

If this works yes please submit a PR.

[glenn-jocher]

@seven320 good news 😃! Your original issue may now be fixed ✅ in PR #3973. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload with model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[seven320]

thx！