CyberZHG / keras-gradient-accumulationLinks
Gradient accumulation for Keras
☆35Updated 4 years ago
Alternatives and similar repositories for keras-gradient-accumulation
Users that are interested in keras-gradient-accumulation are comparing it to the libraries listed below
Sorting:
- Implementation of Rectified Adam in Keras☆70Updated 6 years ago
- Learning rate multiplier☆46Updated 4 years ago
- Lookahead mechanism for optimizers in Keras.☆50Updated 4 years ago
- AdamW optimizer for Keras☆116Updated 6 years ago
- ☆44Updated 7 years ago
- Keras/TF implementation of AdamW, SGDW, NadamW, Warm Restarts, and Learning Rate multipliers☆169Updated 4 years ago
- Keras implementation of Global Context Attention blocks☆46Updated 6 years ago
- 5th place solution for: RSNA Intracranial Hemorrhage Detection☆41Updated 6 years ago
- AdaBound optimizer in Keras☆56Updated 5 years ago
- ☆23Updated 6 years ago
- keras implementation of AdamW from Fixing Weight Decay Regularization in Adam (https://arxiv.org/abs/1711.05101)☆71Updated 7 years ago
- SNAIL Attention Block for Keras.☆16Updated 5 years ago
- Switch Normalization implementation for Keras 2+☆30Updated 7 years ago
- 8th place solution for SIIM-ACR Pneumothorax Segmentation competition on Kaggle☆22Updated 4 years ago
- 3rd place solution for RSNA pneumonia detection challenge☆84Updated 6 years ago
- Keras implementation of AdaBound☆130Updated 6 years ago
- ☆86Updated 2 years ago
- Keras implementation of layer which performs augmentations of images using GPU.☆49Updated 4 years ago
- This repository contains notebooks showing how to perform mixed precision training in tf.keras 2.0☆12Updated 6 years ago
- ☆26Updated 3 years ago
- Kaggle Kuzushiji Recognition: 2nd place solution☆84Updated 6 years ago
- Exploring learning rates to improve model performance☆19Updated 6 years ago
- Corrupted labels and label smoothing☆129Updated 8 years ago
- Unsupervised Data Augmentation experiments in PyTorch☆59Updated 6 years ago
- Minimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.☆38Updated 2 years ago
- Multi-class classification with focal loss for imbalanced datasets☆82Updated 6 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 5 years ago
- Attention based sequence to sequence neural machine translation model built in keras.☆30Updated 7 years ago
- Provides a systematic and extensible way to build, train, evaluate, and tune deep learning models using PyTorch.☆95Updated last year
- Radam+lookahead implemented by tensorflow☆11Updated 6 years ago