SSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN
Distributed training (multi-node) of a Transformer model
🎯 Gradient Accumulation for TensorFlow 2
TorchHandle makes your PyTorch development more efficient and make you use PyTorch more comfortable
Gradient accumulation on tf.estimator
🎯 Production-ready implementation of video prediction models using PyTorch. Features Enhanced ConvLSTM with temporal attention, PredRNN with spatiotemporal memory, and Transformer-based architecture.
A simple implementation of Multi-passage BERT
This project aims to help people implement tensorflow model pipelines quickly for different nlp tasks.
tensorflow2-keras gradient accumulation
Corso web gratuito in italiano, con repository open source, per costruire da zero un modello GPT decoder-only in PyTorch in 42 lezioni con spiegazioni, matematica, codice eseguibile e snapshot progressivi.
Minimal PyTorch training framework — implement three methods, get a full training loop: composable phases, checkpointing, early stopping, metrics, and a live web dashboard.
Gradient Accumulation with Tensorflow2.x
Hands-on PyTorch Lightning 2.x curriculum: 20 notebooks from LightningModule basics to manual optimization, DDP, profiling and ONNX export, backed by lmpro, a tested library of modules, datamodules, callbacks and a LightningCLI for vision, NLP, tabular and time-series tasks. Runs on CPU with synthetic data.
AlzMRI-Net: Classify Alzheimer's stages from MRI scans.
Research code implementing the "Attention Is All You Need" architecture. Engineers a stable training loop for a 163M LLM using reduced-precision techniques on free-tier compute.
Implementation of Gradient Accumulation for low-memory language modelling transformer fine tuning.
Classifying images of flowers into 17 categories using EfficientNet-B0 and PyTorch.
A lightweight PyTorch library for verifying training parity across resume, gradient accumulation, and sample coverage, with first-divergence localization.
To associate your repository with the gradient-accumulation topic, visit your repo's landing page and select "manage topics."