ShahariarRabby / Mnist_cnn_Swish
I have a Keras ReLU model that score 0.99457 on kaggle submission. I choose that model and Change all the ReLU activation to Swish. That model achieve 0.99671 .
☆19Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for Mnist_cnn_Swish
- ☆23Updated 6 years ago
- ☆43Updated 6 years ago
- Some notes, tutorials, and some experimentation with the fast.ai library (https://github.com/fastai/fastai)☆58Updated 6 years ago
- 17th place solution in "Google Landmark Retrieval Challenge"☆6Updated 4 years ago
- All My Pytorch projects reside here☆33Updated 6 years ago
- Repo for my blogs explaining swish activation function☆13Updated 6 years ago
- Material for MLT Reinforcement Learning workshops and study sessions☆50Updated 4 years ago
- Implementation of Rectified Adam in Keras☆69Updated 5 years ago
- My classnotes, experiments, reproducible notebooks from fast.ai Deep Learning Class (v2)☆36Updated 6 years ago
- ☆35Updated 7 years ago
- Open solution to the Google AI Object Detection Challenge☆46Updated 2 years ago
- 5th Winning solution for Humpback whale identification☆48Updated 5 years ago
- Programs with word vectors, RNN, NLP stuff, etc☆18Updated 7 years ago
- A high level library on top of machine learning frameworks☆32Updated 2 years ago
- Kaggle Human Protein Atlas Image Classification 73th solution☆19Updated 5 years ago
- A very naive and simple benchmark between dlib and pytorch in terms of space and time☆19Updated 4 years ago
- Multi-GPU training using Keras with a Tensorflow backend.☆20Updated 7 years ago
- 6th place solution for Recruit-Restaurant-Visitor-Forecasting☆17Updated 6 years ago
- Compare outputs between layers written in Tensorflow and layers written in Pytorch☆72Updated 6 years ago
- Mastering PyTorch for Deep Learning, Published by Packt☆14Updated 3 years ago
- keras implementation of AdamW from Fixing Weight Decay Regularization in Adam (https://arxiv.org/abs/1711.05101)☆70Updated 6 years ago
- Wining solution and its further development for MICCAI 2017 Endoscopic Vision Challenge Angiodysplasia Detection and Localization☆78Updated 5 years ago
- Modular and Simple approach to VQA in Keras☆22Updated 7 years ago
- Solution to Kaggle's PLAsTiCC Astronomical Classification Competition☆51Updated 5 years ago
- ☆6Updated 5 years ago
- 10th place solution for the RSNA Pneumonia Detection Challenge☆14Updated 6 years ago
- Team GuYuShiJie~'s 15th (top 2%) solution of cervix type classification in Kaggle 2017 competition, using PyTorch.☆19Updated 7 years ago
- Demo web app for image resolution enhancement using fast.ai☆22Updated 2 years ago