YOLOv3_PyTorch

YOLOv3_PyTorch copied to clipboard

thanks for your work. do you have the plan to support the VOC dataset?

Hsintao

Thank you for your sharing. I want to change the batch size to. But the memory is out of size. In the Darknet, there's a parameter called "subdivisions". Do you...

Yanxingang

Why eval_coco.py the result is so low??

2

the result AP0.5 =0.262,AP0.5-0.95=0.119

yanxp

A possible bug in training.py

2

Dear @BobLiu20 , thanks for sharing your code. It's wonderful, however I think there might be a bug in the loss related block of training.py: ```losses_name = ["total_loss", "x", "y",...

lee2430

Confused with your mAP computing!

4

@BobLiu20 Thanks for your code, but your mAP computing is actually recall at specific confidence threshold, which is totally different from mAP. Here is my test results on your models...

fighting-liu

想在VOC上进行训练，不知怎么操作？

LewX

Ran some profiling on a GTX1080Ti

4

Hey, I modified the eval script a bit to run some predictions and test the FPS a bit. I was getting much lower FPS than what is quoted in https://github.com/eriklindernoren/PyTorch-YOLOv3...

joaqo

Thank you for your great code, when I run python test_images.py params.py, I encountered the error below, my matplotlib's version is 2.0.0. After I changed tab20b to Vega20b arbitrarily, I...

djshu

What's the meaning of w and h in your loss function?

1

When you calculate loss, the code about `tw` and `th` like this: ``` # Width and height tw[b, best_n, gj, gi] = math.log(gw/anchors[best_n][0] + 1e-16) th[b, best_n, gj, gi] =...

XiaXuehai

CUDA driver version is insufficient.

3

I get this when I try to run the evals.py file. I have tried this on both the CUDA 8.0 and the CUDA 9.0 versions of pytorch, no dice. >...

momenabdelkarim