Efficient-CapsNet
Efficient-CapsNet copied to clipboard
EscVM
Official TensorFlow code for the paper "Efficient-CapsNet: Capsule Network with Self-Attention Routing".
Hi we are very impressed by your article and the improvement you implemented. In the article you wrote: "However, we adopt only two layers of capsules due to the relative...
Hello! I've found a performance issue in /utils: `batch()` should be called before `map()`, which could make your program more efficient. Here is [the tensorflow document](https://tensorflow.google.cn/guide/data_performance?hl=zh_cn#vectorized_mapping) to support it. Detailed...
Dear Author, I am trying to run the code with no luck due to compatibility issues. I used tensorflow 2.* with different versions. I tried different versions of python, ie....
Hi, If you want to make it work in 2025, here's a configuration I finally got to work: machine: Windows 10 Python version == 3.10.16 packages: cudatoolkit==11.2 cudnn==8.1.0 tensorflow==2.10.1 tensorboard==2.10.1...
In model.py, the train method of EfficientCapsNet includes the following line: [dataset_train, dataset_val = dataset.get_tf_data() ](https://github.com/EscVM/Efficient-CapsNet/blob/4b337f5bf79d70a56e4dec8b113fe54b44cfe963/models/model.py#L158) However, get_tf_data() simply calls [generate_tf_data()](https://github.com/EscVM/Efficient-CapsNet/blob/4b337f5bf79d70a56e4dec8b113fe54b44cfe963/utils/pre_process_smallnorb.py#L72), which augments and returns the **test dataset**. Was this...
