pytorch-domain-adaptation

pytorch-domain-adaptation copied to clipboard

Acc on target

1

Hi, I have some questions about my results. Is that right the discriminator_acc is growing increasingly not decreasing? This is from adda. ``` EPOCH:001, discriminator_loss:0.2972, discriminator_accuracy:0.8953 EPOCH:002, discriminator_loss:0.0260, discriminator_accuracy:0.9923 EPOCH:003,...

omg777

in wdgrl.py I put "trained_models/source.pt" in MODEL_FILE , but it is no work. i don't know why. arg_parser.add_argument('MODEL_FILE', help='trained_models/source.pt')

123dukangning

Question wdgrl.py - gradient_penalty(critic, h_s, h_t)

1

In wdgrl.py - gradient_penalty(critic, h_s, h_t): The interpolates created in line 29 are of size _(3 x batch_size x feature_size)_. Following that the gradients are also of size (3 x...

fschmid56

I'm following the script and use exactly the same parameters as the script used. However, the best I can get for WDGRL is 0.6786. Can you specify what parameters you...

yilingmialiu

NameError: name 'k_disc' is not defined, File "adda.py", line 125

1

Hello all, I have done the according steps as said in README.md file, and as I was running the adda.py file with the specified argument as followed: `python adda.py trained_models/source.pt`...

sangin-fatemeh

ValueError: a must be greater than 0 unless no samples are taken

3

Hello! guys. Has anyone ever encountered such mistakes? How the errors fix？ Traceback (most recent call last): File "wdgrl.py", line 134, in main(args) File "wdgrl.py", line 76, in main (source_x,...

magnum-zx

questions about loss？

2

Dr-Zhou