dataset-distillation icon indicating copy to clipboard operation
dataset-distillation copied to clipboard
verified publisher icon ssnl

Question about weights update in network of phase test

Open Firegreat123 opened this issue 3 years ago • 4 comments

  • Hi, after training 10 distilled images, how does these 10 distilled images update the weights of the neural network in phase test?

Firegreat123 avatar May 09 '22 01:05 Firegreat123

the entire testing code is here https://github.com/SsnL/dataset-distillation/blob/master/main.py#L244-L356

ssnl avatar May 09 '22 20:05 ssnl

Hi, I have read codes and have a little question. Does the code below used to train test network with distilled images? image

Firegreat123 avatar May 10 '22 01:05 Firegreat123

yes that is correct!

ssnl avatar May 10 '22 03:05 ssnl

Thank you. After running the codes below, in the output.log I can see that Test accuracy is 79.8% image image But after I run the test code below, the accuracy will be dropped into 23.1868%. Why is this happen?

python main.py --mode distill_adapt --source_dataset MNIST_RGB --dataset SVHN --arch LeNet --phase test
--train_nets_type loaded --test_nets_type same_as_train
--test_distilled_images loaded --test_distilled_lrs loaded

image

Firegreat123 avatar May 10 '22 05:05 Firegreat123