ed-fish / data-efficient-video-transformers
Three experiments for data efficient video transformers.
☆8Updated 2 years ago
Related projects: ⓘ
- Adam with minor modifications which give significant improvement☆19Updated 3 years ago
- Official PyTorch code for U-Noise: Learnable Noise Masks for Interpretable Image Segmentation (ICIP 2021)☆39Updated 2 years ago
- ☆12Updated this week
- Utilities for working with videos☆13Updated 2 years ago
- CoaT: Co-Scale Conv-Attentional Image Transformers☆16Updated 3 years ago
- (unofficial) - customized fork of DETR, optimized for intelligent obj detection on 'real world' custom datasets☆12Updated 4 years ago
- Various test models in WNNX format. It can view with `pip install wnetron && wnetron`☆12Updated 2 years ago
- Includes additional materials for the following keras.io blog post.☆12Updated 3 years ago
- Experiments with the ideas presented in https://arxiv.org/abs/2003.00152 by Frankle et al.☆28Updated 4 years ago
- ☆14Updated this week
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆36Updated 2 years ago
- My solution to the Global Data Science Challenge☆36Updated 4 years ago
- ☆15Updated this week
- ☆15Updated this week
- Implementing DropPath/StochasticDepth in PyTorch☆16Updated 2 years ago
- TF 2 implementation Learning to Resize Images for Computer Vision Tasks (https://arxiv.org/abs/2103.09950v1).☆51Updated 2 years ago
- A simple implementation of a deep linear Pytorch module☆18Updated 3 years ago
- Library for converting from RGB / GrayScale image to base64 and back.☆19Updated 2 years ago
- Official PyTorch implementation of RIO☆18Updated 3 years ago
- Implementation for NATv2.☆23Updated 3 years ago
- Packaged TResNet based on Official PyTorch Implementation☆15Updated 3 years ago
- Simple Tensorflow implementation of "SRM : A Style-based Recalibration Module for Convolutional Neural Networks"☆18Updated 5 years ago
- batchboost is a variation on MixUp that instead of mixing just two images, mixes many images together.☆43Updated 4 years ago
- A disciplined approach to neural network parameters - Reviewing the approach for setting Hyper parameters by Leslie Smith☆11Updated 6 years ago
- ☆14Updated 3 years ago
- ☆21Updated this week
- Task Agnostic Unsupervised Learning☆15Updated 2 years ago
- Official implementation for "Minimax Active Learning" in PyTorch.☆9Updated 3 years ago
- Directed masked autoencoders☆13Updated last year
- Implementation of Spectral Leakage and Rethinking the Kernel Size in CNNs in Pytorch☆14Updated 3 years ago