/PyTorch-CIFAR-10-autoencoder

This is a reimplementation of the blog post "Building Autoencoders in Keras". Instead of using MNIST, this project uses CIFAR10.

Primary LanguagePythonMIT LicenseMIT

building-autoencoders-in-Pytorch

This is a reimplementation of the blog post "Building Autoencoders in Keras". Instead of using MNIST, this project uses CIFAR10.

Current Results (Trained on Tesla K80 using Google Colab)

First attempt: (BCEloss=~0.57)
decode

Best Predictions so far: (BCEloss=~0.555)
decode decode

Targets:
target target

Previous Results (Trained on GTX1070)

First attempt: (Too much MaxPooling and UpSampling)
decode

Second attempt: (Model architecture is not efficient)
decode

Targets:
decode

License

MIT