We pit Keras and PyTorch against each other, showing their strengths and weaknesses in action. We present a real problem, a matter of life-and-death: distinguishing Aliens from Predators!
Switch branches/tags
Nothing to show
Clone or download
Latest commit aafe0c4 Nov 8, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data first commit Sep 28, 2018
images first commit Sep 28, 2018
Keras-ResNet50.ipynb first commit Sep 28, 2018
PyTorch-ResNet50.ipynb detach added Nov 8, 2018
README.md Update README.md Oct 10, 2018
data_prep.ipynb first commit Sep 28, 2018
requirements.txt first commit Sep 28, 2018

README.md

Keras vs. PyTorch: Alien vs. Predator recognition with transfer learning

Featured in deepsense.ai blog post Keras vs. PyTorch: Alien vs. Predator recognition with transfer learning, in which we discuss the differences. Code is in two Jupyter Notebooks:

See also the upcoming webinar (10 Oct 2018), in which we walk trough the code.

For plug&play interactive code, see the Neptune versions with fancy charts or these Kaggle Kernels:

Data

See also: Alien vs. Predator images | Kaggle. In general, there are 447 images for each class, split into two classes. Examples:

Requirements

If you want to run the code, see the requirements:

  • Common:
    • jupyter==1.0.0
    • matplotlib==2.2.3
    • Pillow==5.2.0
    • h5py==2.8.0
  • Keras:
    • tensorflow==1.10.1
    • Keras==2.2.2
  • PyTorch:
    • torch==0.4.1
    • torchvision==0.2.1

Webinar info