TypeError when training with custom data

[grantrosario]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

Training

Bug

Commit #9347 caused my Colab runs to start failing. They're unable to begin training due to the below type error. Conv2d is now expecting a different set of args.

Environment

Google colab

YOLOv5 🚀 v6.2-109-g23701ea Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla P100-PCIE-16GB, 16281MiB)

Minimal Reproducible Example

!git clone https://github.com/ultralytics/yolov5/

%cd yolov5/

!pip install -r requirements.txt
!pip install gdown -q
!pip install ipython-autotime
!pip install ipyplot

import torch
import utils
import gdown
import yaml
import glob
import ipyplot

from utils.plots import plot_results

display = utils.notebook_init()

%load_ext autotime
!python train.py --imgsz 416 --image-weights --device 0 --batch-size 16 --epochs 1 --data /content/data.yaml --cfg /content/data.yaml --weights /content/yolov5/models/yolov5.pt --name s400_1

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[github-actions]

👋 Hello @grantrosario, 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://ultralytics.com or email [email protected].

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

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), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@grantrosario thanks for the bug report!

I'm unable to reproduce an issue. I tried a related command with COCO128 training in Colab and everything works correctly with current master.

If you use Conv() modules directly in a custom model yaml you may need to update to the new arguments however.

[River-Cold]

Bug

I meet the same problem when I train COCO128 in Google Colab.
When I use the cfg "models/hub/yolov5s-ghost.yaml", it will throw an error as the following picture:

But everything works correctly when I use other cfgs.

Minimal Reproducible Example

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

import torch
import utils
display = utils.notebook_init() # checks

#Train YOLOv5s on COCO128 for 3 epochs
!python train.py --img 640 --batch 16 --epochs 3 --cfg /content/yolov5/models/hub/yolov5s-ghost.yaml --data coco128.yaml --weights yolov5s.pt

[glenn-jocher]

@River-Cold thanks for the code to reproduce. I see the same error. I'll add a TODO to resolve.

[glenn-jocher]

@grantrosario good news 😃! Your original issue may now be fixed ✅ in PR #9466. 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 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 🚀!

[River-Cold]

@glenn-jocher I solve this problem but met another problem：#9059
It happens when I use yolov5s-ghost.yaml to train on coco128.
Between epoch 0 and 17，the P, R and mAP are all 0.0, just as the following picture：

I am not sure whether it is caused by the network itself or a bug.

[glenn-jocher]

@River-Cold train 300 epochs.