Haoli Bai comments

Results 7 comments of


                                            Haoli Bai

Code and model of mobilenetv2 in Network Pruning via Transformable Architecture Search?

Also would you mind sharing the search script for resnet18 on imagenet? Thanks!

Hyper-parameters about learners on Resnet-50

Make sure that you first pretrain a full-precision model, based on which you perform quantization and fine-tuning.

Hyper-parameters about learners on Resnet-50

@hzhyhx1117 What are the configurations for the uniform quantization learner and channel-prune learner?

LayoutLMv3 document layout train error

Same here, interesting.. I am using PyTorch 1.8.0 and I suspect there can be issues with this version. This problem happens inside gradient checkpointing function in Torch. In PyTorch 1.8.0,...

Lost my content 我的文本内容都丢失了

+1. 偶尔会发生这种问题，认命

[QUESTION] Adding new parameters in ColumnParallelLinear/RowParallelLinear raises AssertionError (Communication call has not been issued for this bucket) when using overlap-grad-reduce

Not yet. But I found more colleagues around me also meet this problem.

[QUESTION] Adding new parameters in ColumnParallelLinear/RowParallelLinear raises AssertionError (Communication call has not been issued for this bucket) when using overlap-grad-reduce

> same issue when using --overlap-param-gather --overlap-grad-reduce \ Some quick update. I can avoid this issue and start training by removing these configs. Hope this can help more people. But...