github2016-yuan

@PanJinquan @aluds123 I have already get pb file but I do not know how to test it. From code above, I select some code. ``` def freeze_graph_test(): image_path = './data/demo_data/dog.jpg'...

@Alloooshe Hi, could you share your solution with more details?same issue with you.

I solved it by using the pb files instead of ckpt file in tf2.x (I am using tf2.2.0) Here is my code and hope it helps someone who has the...

In ubuntu, the same operation, I get the following error: rows, columns = os.popden('stty size','r').read().split() AttributeError:module 'os' has no attribute '**popden**' It seems easy to solve it but I find...

> Have same error here. But I have this error with OID v4 not v5. Am I the only one who can't download any images from OID v4? I've followed...

已确定，是在default_fragment.glsl中实现的美颜。

@maronuu Have you converted yolov5s.pt to yolov5s_trt.pt yet?

@1suancaiyu Hello, I use your repo and it really works. BUT I got nan error in trainning.Below are steps. I choose about 16K images from ntu-d (60 classes) **step1:** `PretrainAIM:...

hello, have you solved it? I have the same error in both Ubuntu 18.04 and win11

mmpose-master works for training my own dataset. SO, something wrong with mmpose-1.x?