Skip to content

Conversation

@cbwces
Copy link

@cbwces cbwces commented Nov 10, 2020

修改Caffe/caffe.proto文件并生成新的caffe_pb2.py,修复pooling层转化后,caffe无法读取ceil_mode参数问题
添加avgpool层return_indices参数以修复AvgPool2d在正向传递时参数个数不足的错误
修改example/resnet_pytorch_2_caffe.py,使用model/resnet.py中的模型而不是torchvision中的resnet模型,将model/resnet.py中ResNet类使用的AvgPool2d替换为AdaptiveAvgPool2dflatten算子替换为view

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant