creafz / kaggle-carvana
Solution for the Carvana Image Masking Challenge on Kaggle. It uses a custom version of RefineNet with Squeeze-and-Excitation modules implemented in PyTorch. It was a part of the final ensemble that was ranked 23 out of 735 teams (top 4%).
☆10Updated 7 years ago
Alternatives and similar repositories for kaggle-carvana:
Users that are interested in kaggle-carvana are comparing it to the libraries listed below
- Carvana Boundaries Refinement☆7Updated 7 years ago
- Investigation of focal and dice loss for the Kaggle 2018 data science bowl.☆18Updated 6 years ago
- Evaluation framework for testing segmentation networks in Keras☆36Updated 5 years ago
- semantic segmentation using pytorch☆11Updated 7 years ago
- Code for MICCAI 2017 paper on binary sparse convolutions for semantic segmentation of medical images☆11Updated 7 years ago
- WIP☆21Updated 7 years ago
- Dilated DenseNets☆15Updated 7 years ago
- Pytorch implementation of different edge detection networks, such as Holistically-Nested Edge Detection and PixelNet☆33Updated 7 years ago
- ☆35Updated 7 years ago
- Several networks for segmentation like VNet or RefineNet implemented by PyTorch and Visdom☆32Updated 7 years ago
- BiSeNet in pytorch☆10Updated 6 years ago
- Keras Fully Convolutional Neural Network MSCOCO Food Segmentation☆11Updated 7 years ago
- ☆15Updated 7 years ago
- A mxnet implementation of CheXNet☆8Updated 6 years ago
- an implementation of path aggregation network based on mattport mask-rcnn☆34Updated 6 years ago
- ☆15Updated 7 years ago
- U-Net: Convolutional Networks for Image Segmentation by TensorFlow☆19Updated 7 years ago
- A good example of deformable convolutional network for mnist classification☆21Updated 5 years ago
- 4th place solution for 2018 Data Science Bowl kaggle competition☆47Updated 6 years ago
- ☆14Updated 7 years ago
- Implementations of different variations of U-net - adding deconv layers, dense net variant and including skip connections☆9Updated 7 years ago
- ☆53Updated 7 years ago
- ☆7Updated 7 years ago
- Tensorflow☆9Updated 6 years ago
- Convert torch model to/from caffe model easily☆12Updated 8 years ago
- ☆29Updated 8 years ago
- Train fully convonlutional neural networks for brain segmentation.☆10Updated 7 years ago
- Combining FCN (U-net, DeepEM-net) with CRNN(convolution LSTM and GRU, deconvolution one) for EM image segmentation☆11Updated 7 years ago