gunchagarg / learning-rate-techniques-kerasLinks
Exploring learning rates to improve model performance
☆19Updated 6 years ago
Alternatives and similar repositories for learning-rate-techniques-keras
Users that are interested in learning-rate-techniques-keras are comparing it to the libraries listed below
Sorting:
- This repository contains notebooks showing how to perform mixed precision training in tf.keras 2.0☆12Updated 5 years ago
- Implementation of Differential Learning Rate in Keras☆11Updated 6 years ago
- Implementation of Rectified Adam in Keras☆70Updated 5 years ago
- Attention based sequence to sequence neural machine translation model built in keras.☆30Updated 7 years ago
- Minimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.☆38Updated 2 years ago
- Notebooks to accompany the blog posts about the 2nd place Kaggle RSNA winners: https://github.com/darraghdog/rsna☆30Updated 5 years ago
- Keras wikipedia-based Language Model☆21Updated 7 years ago
- Gradient accumulation for Keras☆35Updated 4 years ago
- Demonstrates knowledge distillation for image-based models in Keras.☆53Updated 4 years ago
- RAdam optimizer for keras☆71Updated 5 years ago
- ☆34Updated 5 years ago
- The code used fine-tuning of BERT(Transformer Neural Network Architecture)to accurately pick the correct answer among ten choices that be…☆12Updated 5 years ago
- Seq2seq using LSTM with attention from Luong et al☆10Updated 6 years ago
- Large Scale BERT Distillation☆33Updated 2 years ago
- SNAIL Attention Block for Keras.☆16Updated 5 years ago
- Multi-class classification with focal loss for imbalanced datasets☆82Updated 5 years ago
- Implementing activation functions from scratch in Tensorflow.☆36Updated 3 years ago
- Tensorflow implementation of transformer network from "Attention is all you need" Paper. Also use cases of it!☆16Updated 5 years ago
- ☆43Updated 6 years ago
- Position embedding layers in Keras☆58Updated 3 years ago
- This repository contains the winning solution (2nd place) of the Macrosoft Maleware Prediction Challenge on Kaggle.☆34Updated 6 years ago
- bert on Jigsaw Unintended Bias in Toxicity Classification☆50Updated 6 years ago
- Tensorflow port implementation of Single Headed Attention RNN☆16Updated 5 years ago
- Adaptive embedding and softmax☆17Updated 3 years ago
- My projects for fast.ai's Deep Learning from the Foundations course (fast.ai part2v3)☆39Updated 5 years ago
- Code repository for Rakuten Data Challenge: Multimodal Product Classification and Retrieval.☆26Updated 4 years ago
- ☆8Updated 5 years ago
- Deep Learning and Natural Language Processing using PyTorch (O'Reilly AI - NYC, 2019)☆11Updated 6 years ago
- Tensorflow NCE loss in Keras☆34Updated 6 years ago
- Source code for "Training Generative Adversarial Networks Via Turing Test".☆13Updated 5 years ago