Pytorch Hub inference returns different results than detect.py

[Aoobi]

Hi,
I trained Yolov5x on my custom dataset using this notebook from roboflow: https://colab.research.google.com/drive/1gDZ2xcTOgR39tGGs-EZ6i3RTs16wmzZQ
In the notebook when I do inference I am getting good results, with confidence about 0.8 for basically every image, but when i downloaded the weights and used them in the hub locally, the results are different - if I set the threshold for 0.4 I am getting almost no results.
Also, the class names are not displayed when inferring with torchhub. I am using this code to run inference with pytorch hub:

model = torch.hub.load('ultralytics/yolov5', 'custom', path_or_model="path_to_my_weight_file.pt")
model.conf = 0.4
results = model(list_of_paths_to_my_images)
results.save("path_to_save_files")

Thanks

[github-actions]

👋 Hello @Aoobi, 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]

@Aoobi we don't support 3rd party training tools. If you'd like to train and deploy correctly simply follow the official Custom Training Tutorial and the Pytorch Hub Tutorials below, and if you'd like a notebook environment we recommend the notebooks below. Good luck!

Tutorials

• Train Custom Data  🚀 RECOMMENDED
• PyTorch Hub  ⭐ NEW

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

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.