PyTorch-YOLOv3 issues

very low mAP on coco val2014 when training from scratch

18

The code is elegant and concise, but the training performance on coco val2014 is poor. The mAP is only 0.00912 after 24 epochs when I train the model from scratch.

fyw1999

mAP nearly zero?

3

## What I'm trying to do I tried to train on the VOC2007 dataset. However, I failed. After many epochs, the mAP is zero. ## What I've tried 1. Loaded...

Chenyaoyi1998

Bump tensorboard from 2.12.2 to 2.14.0

Bumps [tensorboard](https://github.com/tensorflow/tensorboard) from 2.12.2 to 2.14.0. Release notes Sourced from tensorboard's releases. TensorBoard 2.14.0 The 2.14 minor series tracks TensorFlow 2.14. Features Small data table and step selector usability and...

dependabot[bot]

dependencies

is woring in 3090,lower fps!

2

inference video in RTX 3090,max fps is 16, and my computer GPU is 1050ti, max fps is 10 what should i do?

827379852

Bump numpy from 1.23.4 to 1.24.4

Bumps [numpy](https://github.com/numpy/numpy) from 1.23.4 to 1.24.4. Release notes Sourced from numpy's releases. v1.24.4 NumPy 1.24.4 Release Notes NumPy 1.24.4 is a maintenance release that fixes a few bugs discovered after...

dependabot[bot]

dependencies

Bump requests from 2.28.1 to 2.31.0

Bumps [requests](https://github.com/psf/requests) from 2.28.1 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...

dependabot[bot]

dependencies

how to adjust learning rates or something to be better when using a pretrained model to train my dataset?please give me some advice

5

I'm trying to train my own data set using pretrained weights, BDD100K. Can you give me some advice? (All parameters unchanged, e.g. learning rate and step of learning rate decay)...

J-LINC

Tune for COCO

1

## Proposed changes - tune hyperparams - scale based on mini batch size - linear instead of step wise decay - use sgd - only log once per optimizer step...

Flova