Mohammed Alali

Hi @polaschwoebel , I faced the same problem and was able to load the data using python's h5py library. The code goes like this: ``` x_filename = "camelyonpatch_level_2_split_train_x.h5" y_filename =...

You can run all scripts on a conda environment. What is your Keras version? Are you using TF.Keras or only Keras? What error do you get when running Listing 2.1...

Hi @AleCx4 Make sure you install TensorFlow correctly and it's running without error. Then you can use the code in this book

I'm assuming you're referring to Listing 9.11 on page 265, which is here: [https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter09_part03_interpreting-what-convnets-learn.ipynb](https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter09_part03_interpreting-what-convnets-learn.ipynb)

Hi @MasLiang Thanks for pointing this out. I think there is another line that needs to be changed. For resnet, this [line](https://github.com/zzzxxxttt/pytorch_DoReFaNet/blob/a12b6171555b8aba4d45e7dba6aeeab46be5480e/nets/cifar_resnet.py#L45) needs use_bias to be True as it is...

maybe you need to run extract_features_fp.py

I'm also interested in reproducing the paper's results. The paper reported a use of batch_size=64, not 32. What optimizer and learning rate did you use? It will be very helpful...

This is a great question. I'd like to know the answer as well.