https://github.com/deepsense-ai/Keras-PyTorch-AvP-transfer-learning

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!
https://github.com/deepsense-ai/Keras-PyTorch-AvP-transfer-learning

alien keras keras-classification-models keras-models keras-neural-networks keras-tutorials predator pytorch pytorch-cnn pytorch-implementation pytorch-tutorial pytorch-tutorials

Last synced: 3 months ago
JSON representation

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!

• Host: GitHub
• URL: https://github.com/deepsense-ai/Keras-PyTorch-AvP-transfer-learning
• Owner: deepsense-ai
• Created: 2018-09-28T09:08:54.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-03-12T07:03:07.000Z (over 5 years ago)
• Last Synced: 2024-04-13T12:06:16.545Z (7 months ago)
• Topics: alien, keras, keras-classification-models, keras-models, keras-neural-networks, keras-tutorials, predator, pytorch, pytorch-cnn, pytorch-implementation, pytorch-tutorial, pytorch-tutorials
• Language: Jupyter Notebook
• Homepage: https://deepsense.ai/keras-vs-pytorch-avp-transfer-learning/
• Size: 7.85 MB
• Stars: 47
• Watchers: 9
• Forks: 33
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

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

![](images/transfer_learning.png)

Featured in [deepsense.ai](https://deepsense.ai/) blog post [Keras vs. PyTorch: Alien vs. Predator recognition with transfer learning](https://deepsense.ai/keras-vs-pytorch-avp-transfer-learning), in which we discuss the differences. Code is in two Jupyter Notebooks:

* [Transfer learning with ResNet-50 in Keras](Keras-Resnet50.ipynb)

* [Transfer learning with ResNet-50 in PyTorch](PyTorch-Resnet50.ipynb)

See also the [upcoming webinar (10 Oct 2018)](https://www.crowdcast.io/e/KerasVersusPyTorch/register), in which we walk trough the code.

For plug&play interactive code, see the [Neptune versions with fancy charts](https://app.neptune.ml/deepsense-ai/Keras-vs-PyTorch) or these Kaggle Kernels:

* [Transfer learning with ResNet-50 in Keras - Kaggle Kernel](https://www.kaggle.com/pmigdal/transfer-learning-with-resnet-50-in-keras)

* [Transfer learning with ResNet-50 in PyTorch - Kaggle Kernel](https://www.kaggle.com/pmigdal/transfer-learning-with-resnet-50-in-pytorch)

# Data

See also: [Alien vs. Predator images | Kaggle](https://www.kaggle.com/pmigdal/alien-vs-predator-images).

In general, there are 447 images for each class, split into two classes. Examples:

![](images/example.png)

# 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

* [Link to the webinar (10 Oct 2018, 5 PM CEST)](https://www.crowdcast.io/e/KerasVersusPyTorch/register)

* [Slides from the webinar](https://docs.google.com/presentation/d/1y6KBgVtvZ26afCbIbCoGZoEdT6-eoUqPc9U4cJ3X1Gw)

* deepsense.ai's articles about Keras and PyTorch:

  * [Keras or PyTorch as your first deep learning framework ](https://deepsense.ai/keras-or-pytorch/)

  * [Keras vs. PyTorch: Alien vs. Predator recognition with transfer learning](https://deepsense.ai/keras-vs-pytorch-avp-transfer-learning/)

* [Notebooks in Neptune](https://app.neptune.ml/deepsense-ai/Keras-vs-PyTorch)

* Workshops:

  * [open workshops at deepsense.ai's HQ](https://deepsense.ai/machine-learning-and-deep-learning-training/)

  * [on-site workshops](https://deepsense.ai/machine-learning-training/)