Skip to content

run error in regnet with GPU #27

@tongshiyuan

Description

@tongshiyuan

我在使用GPU进行RegNet训练的时候,报错了

UnimplementedError:  Fused conv implementation does not support grouped convolutions for now.
	 [[node reg_net/any_stage/res_bottleneck_block/bottleneck_transform/conv2d_3/BiasAdd (defined at /filepath/anynet.py:119) ]] [Op:__inference_train_function_10336]

Function call stack:
train_function

但是CPU下是正常的,我检查了一下代码,GPU和CPU模式下,get_group_conv是不一样的,但我不知道怎么debug
希望能得到您的回复

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions