The malgan from ccc2876

malgan's People

Contributors

Stargazers

Watchers

malgan's Issues

you forget to put your data in to the cuda

I clone your code，but it doesn't work.The error prompt that model has been sended to cuda，but data was not. And net have error in layers connect, 256 doesn't match 512

Selection of Benign files is not uniform. Only first 64 files are being used.

 # generate batch of benign
idb = np.random.randint(0, xmal_batch.shape[0], batch_size)

should be

 # generate batch of benign
idb = np.random.randint(0, x_train_ben.shape[0], batch_size)

I may be wrong, Please clarify. Thanks

bugs

0.9872029250457038 0.9854014598540146
Traceback (most recent call last):
  File "code/MalGAN.py", line 417, in <module>
    main()
  File "code/MalGAN.py", line 375, in main
    train(200, blackbox, generator, d_optimizer, g_optimizer, TRAIN_TPR, TEST_TPR, sigmoid, isFirst=True)
  File "code/MalGAN.py", line 247, in train
    fake_mal_data, ymal_batch)
  File "code/MalGAN.py", line 139, in train_discriminator
    prediction_real = discriminator(real_data)
  File "/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "code/MalGAN.py", line 60, in forward
    x = self.out(x)
  File "/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "//python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 87, in forward
    return F.linear(input, self.weight, self.bias)
  File "/lib/python3.7/site-packages/torch/nn/functional.py", line 1370, in linear
    ret = torch.addmm(bias, input, weight.t())
RuntimeError: size mismatch, m1: [64 x 512], m2: [256 x 1] at /pytorch/aten/src/TH/generic/THTensorMath.cpp:197

Recommend Projects