Closed arcus99 closed 2 years ago
The layer name is InceptionV3/InceptionV3/Mixed_5b/concat for IneceptionV3 and resnet_v1_152/block2/unit_8/bottleneck_v1/add for Resnet_v1_152. I didn't do experiments on InceptionV4 and Resnet_v1_50, so I can't give the optimal layer name. If you still get poor results, please check whether other parameters are wrong.
Thanks for sharing the code! I've tried to run attack.py on InceptionV3(using layer InceptionV3/InceptionV3/Mixed_5b/concat), InceptionV4(using layer InceptionV4/InceptionV4/Mixed_6f/concat) and Resnet_v1_50(using layer resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/Relu), but got poor results, so could you please share the EXACT LAYER NAME you used to attack?