In mmdetection，applying DCNv2 in the Res2Net code will cause errors, while DCN will not? #30
Comments
|
Add contiguous() in line 180 of file： https://github.com/Res2Net/mmdetection/blob/master/mmdet/models/backbones/res2net.py will solve this problem.
|
Thank you very much for taking the time to answer my questions，the issue has been solved. |
|
Thank you very much for taking the time to answer my questions，the issue has been solved^_^
…------------------ 原始邮件 ------------------
发件人: "Shanghua Gao"<notifications@github.com>;
发送时间: 2020年4月17日(星期五) 中午11:00
收件人: "Res2Net/Res2Net-PretrainedModels"<Res2Net-PretrainedModels@noreply.github.com>;
抄送: "夏铭阳"<646711351@qq.com>;"Author"<author@noreply.github.com>;
主题: Re: [Res2Net/Res2Net-PretrainedModels] In mmdetection，applying DCNv2 in the Res2Net code will cause errors, while DCN will not? (#30)
Add contiguous() in line 180 of file： https://github.com/Res2Net/mmdetection/blob/master/mmdet/models/backbones/res2net.py
will solve this problem.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
|
I got 47.6 mAP on val2017 with cascade_rcnn_res2net101_dcnv2_fpn_1x. |
|
@panjianning 你好，请问下如何添加dcn到res2net中呢，我直接在backbone中添加配置好像不行，报错：AttributeError: 'Bottle2neck' object has no attribute 'conv2'。 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
File "/data/xmy/mmdet_new/mmdetection/mmdet/models/backbones/res2net.py", line 211, in forward
out = _inner_forward(x)
File "/data/xmy/mmdet_new/mmdetection/mmdet/models/backbones/res2net.py", line 181, in _inner_forward
main() sp = self.convsi
File "/home/l547/anaconda3/envs/MMDET_xmy1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
File "./tools/train.py", line 138, in main
meta=meta)
File "/data/xmy/mmdet_new/mmdetection/mmdet/apis/train.py", line 102, in train_detector
result = self.forward(*input, **kwargs)
File "/data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv.py", line 403, in forward
meta=meta)
File "/data/xmy/mmdet_new/mmdetection/mmdet/apis/train.py", line 177, in _dist_train
self.groups, self.deformable_groups)
File "/data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv.py", line 148, in forward
ctx.groups, ctx.deformable_groups, ctx.with_bias)
input tensor has to be contiguous (modulated_deform_conv_cuda_forward at mmdet/ops/dcn/src/deform_conv_cuda.cpp:497)
frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) + 0x6d (0x7ff852af333d in /home/l547/anaconda3/envs/MMDET_xmy1/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: modulated_deform_conv_cuda_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, bool) + 0x1285 (0x7ff81a84ceb5 in /data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv_cuda.cpython-37m-x86_64-linux-gnu.so)
frame #2: + 0x26fed (0x7ff81a85cfed in /data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv_cuda.cpython-37m-x86_64-linux-gnu.so)
frame #3: + 0x2722e (0x7ff81a85d22e in /data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv_cuda.cpython-37m-x86_64-linux-gnu.so)
frame #4: + 0x22f9c (0x7ff81a858f9c in /data/xmy/mmdet_new/mmdetection/mmdet/ops/dcn/deform_conv_cuda.cpython-37m-x86_64-linux-gnu.so)
.......
The text was updated successfully, but these errors were encountered: