Hector Mao

I faced the performance issue as well. I modified original code to ``` # ResNet_CAM.py mat_for_mult = tf.image.resize(last_conv_output, (224, 224)) amp_layer_weights = all_amp_layer_weights[:, pred:pred+1] final_output = tf.matmul(mat_for_mult, amp_layer_weights)[:,:,0] ``` It...

For me, two steps: 1. Use Anaconda(4.8.3) to create the environment `conda env create -f environment.yaml` (remove this line `- openssl=1.1.1=h7b6447c_0`) 2. Modify all `setup.py` files according to your GPU...