train.py

#Change the parameters to whatever suits you
batch_size = 512 
epochs = 100
labels = [0 for _ in benign_images] + [1 for _ in malicious_images]
model.fit(benign_images+malicious_images, labels,
              batch_size = batch_size,
              epochs = epochs,
              validation_split = 0.25,
              shuffle = True)

Check out my medium post: https://medium.com/analytics-vidhya/cnn-based-malware-detection-python-and-tensorflow-717f8de84ee , section EXE file to Image. Using the gist in that section you are supposed to extract images for both benign and malicious exe_files. The variable in that gist is called images, but once you extract images of an exe you should either put the images in benign_images (initially an empty list) or malicious_images (also initially an empty list).

Hello Islem,

I try this code, but the benign_images and malicious_images aren't defined, and couldn't see the gist that you mention above. Can you please provide the full script?