Training crash on first validation: Error in processing validate dataset path

[thanhminhmr]

The tool crash while training from scratch, the trace point to this line in test.py.

Traceback (most recent call last):
  File "train.py", line 541, in <module>
    train(hyp, opt, device, tb_writer)
  File "train.py", line 367, in train
    compute_loss=compute_loss)
  File "/usr/local/lib/python3.7/dist-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/content/yolov5/test.py", line 81, in test
    is_coco = data['val'].endswith('coco/val2017.txt')  # COCO dataset
AttributeError: 'list' object has no attribute 'endswith'

yolov5/test.py

Line 81 in d808855

is_coco = data['val'].endswith('coco/val2017.txt') # COCO dataset

This is most likely an oversight in the code:
While the dataset file allows list of train/validation data sources (for example in coco128.yaml), the portion of code from above doesn't accept list.

yolov5/data/coco128.yaml

Line 12 in d808855

# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]

This is the related part of the dataset.yaml.

train: [/train/images/1/, /train/images/2/]
val: [/val/images/1/]

I'm unfamiliar with python so I cannot create a patch, but this should be a simple fix. (By adding type check before the endswith call)

[github-actions]

👋 Hello @thanhminhmr, 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 glenn.jocher@ultralytics.com.

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.

[glenn-jocher]

@thanhminhmr thanks for the bug report! Yes this looks like a problem. This should be fixable by updating this line to:

is_coco = type(data['val']) is str and data['val'].endswith('coco/val2017.txt')  # COCO dataset

If this fix works well in your use case can you please submit a PR with it to help everyone else in the future? Thank you!