gradient-accumulation 13 deep-learning 6 pytorch 5 keras 4 machine-learning 3 image-classification 2 distributed-training 2 python 2 gpu 2 transformer 2 tf2 2 tensorflow2 2 mixed-precision 2 multi-gpu 2 tensorflow 2 notebooks 1 tensorboard 1 crnn 1 densnet-seglink 1 densnet-textboxespp 1 deep-learning-library 1 deep-learning-framework 1 custom-metrics 1 cross-validation 1 language-model 1 transfer-learning 1 efficientnet 1 accumulated-batch-normalization 1 distance-iou-loss 1 dsod 1 focal-loss 1 seglink 1 shrikage-loss 1 ssd 1 textboxes 1 textboxespp 1 virtual-batch-size 1 bert 1 multi-passage-bert 1 openqa 1 nlp-pipeline 1 tensorflow-framework 1 optimizer 1 accumulated-gradients 1 adaptive-gradient-clipping 1 batch-size 1 float16 1 hacktoberfest 1 huggingface 1 memory-constraints 1 tpu 1 lazy-evaluation 1 memory-management 1 neural-network 1 out-of-memory 1 collective-communication 1 data-parallelism 1 distributed-data-parallel 1 model-parallelism 1 tutorial 1 attention-mechanism 1 convlstm 1 lstm 1 predrnn 1 spatiotemporal-memory 1 temporal-attention 1 ucf101 1 video-prediction 1 computer-vision 1 cnn 1