pytorch-yolo-v3 icon indicating copy to clipboard operation
pytorch-yolo-v3 copied to clipboard

Published 20 hours ago • verified publisher icon ayooshkathuria

How to load pre-trained model

Open liliangqi opened this issue 7 years ago • 3 comments

Hi, I do like your code which help me understand the YOLO framework. But it is regretful that there are no training process. Now I'm trying to write the training codes by myself but I don't know how to load the pre-trained model given by the official YOLO authors darknet53.conv.74. I tried straightly use the load_weights() method of Darknet but failed. The error reports as RuntimeEroor: the given numpy array has zero-sized dimensions. Zero-sized dimensions are not supported in Pytorch. I guess this error happens when loading step encounter BN layer. Can you help me with this? Thanks.

liliangqi avatar May 03 '18 08:05 liliangqi

Well, I find that deleting the codes here and replacing with continue do work. But I'm not sure if it is the right way.

liliangqi avatar May 03 '18 09:05 liliangqi

I'll try to solve your issue when I'll start working on the training code, which is soon. Sorry for the late reply. Been very busy this month.

ayooshkathuria avatar May 18 '18 10:05 ayooshkathuria

https://github.com/YunYang1994/tensorflow-yolov3

YunYang1994 avatar Dec 02 '18 16:12 YunYang1994