ProDA

ProDA copied to clipboard

About the usage of your code with PyTorch>=1.6.0

2

Thanks for sharing your fantastic work! I am using your code with PyTorch version >= 1.6.0. And it seems that the operation of F.affine_grid() & F.grid_sample() has been changed leading...

LinfengYuan1997

Train with custom dataset

2

Hi! The idea is amazing, may I ask how to train it using my own dataset(only with images and labels) ?

zhou-rui1

this amazing performance improvments kill this area!!!!!!!!!!

1

this amazing performance improvements kill this area!!!!!!!!!!

jingzhengli

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

1

when I run tran.py ```txt python train.py --name gta2citylabv2_stage1Denoise --used_save_pseudo --ema --proto_rectify --moving_prototype --path_soft Pseudo/gta2citylabv2_warmup_soft --resume_path ./pretrained/gta2citylabv2_warmup/from_gta5_to_cityscapes_on_deeplabv2_best_model.pkl --proto_consistW 10 --rce --regular_w 0.1 ``` ```txt Traceback (most recent call last): File...

yuheyuan

How many classes have you used in the warmup training of Synthia - > cityscapes? Can you provide the warmup training command of Synthia - > cityscapes as an example?...

TianX1nYu

I changed 19classes to 13classes, but I get the same error as above.

juajua56

Bumps [scipy](https://github.com/scipy/scipy) from 1.1.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]

Hello, may I ask about the S_pseudo and threshold settings during the three stages of training ?

YYByyy

calc_prototype.py

1

The function calc_prototype in calc_prototype.py, why does the program need to run for 4 epochs?

xylzjm

How to create the visualization of the feature space 

yuheyuan