Glenn Jocher

Results 67 issues of Glenn Jocher

## 🐛 Bug Google Colab is not compatible with latest version of Albumentations. ## To Reproduce Open any Colab notebook and then: ```python %pip install -U albumentations import albumentations as...

I'm super excited to announce our new [YOLOv5](https://github.com/ultralytics/yolov5) 🚀 + [Albumentations](https://github.com/albumentations-team/albumentations) integration!! Now you can train the world's best Vision AI models even better with custom Albumentations automatically applied 😃!...

- [x] I have marked all applicable categories: + [ ] exception-raising bug + [x] visual output bug - [x] I have visited the [source website], and in particular read...

need-feedback 📢
p2-bug-warning ⚠

Per recent partner feedback for clearer UX.

📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 25 November 2021. * [About Weights & Biases](#about-weights-&-biases) * [First-Time Setup](#first-time-setup) * [Viewing runs](#viewing-runs) *...

documentation
enhancement

📚 This guide explains how to train your own **custom dataset** with YOLOv5 🚀. UPDATED 6 August 2022. Use this guide with the [YOLOv5 Custom Training Notebook](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb). ## Before You...

documentation

📚 This guide explains how to train your own **custom dataset** with YOLOv5 🚀. See YOLOv5 [Docs](https://docs.ultralytics.com/yolov5) for additional details. UPDATED 29 March 2023. ## Before You Start Clone repo...

enhancement
tutorial

⭐ This guide explains how to use **Weights & Biases** (W&B) with YOLOv3. ## About Weights & Biases Think of [W&B](https://www.wandb.com/) like GitHub for machine learning models. With a few...

enhancement
tutorial

Ultralytics has open-sourced YOLOv5 at https://github.com/ultralytics/yolov5, featuring faster, lighter and more accurate object detection. YOLOv5 is recommended for all new projects. &nbsp ** GPU Speed measures end-to-end time per image...

enhancement
tutorial

I noticed you use code for custom weight initialization: https://github.com/iamhankai/ghostnet.pytorch/blob/2c90e67d8c33c44ec1bad12c9686f645b0d4de08/ghost_net.py#L162-L169 I've not seen this before. Is there a reason behind this specific strategy? Do you know the effect this has...