pytorch-deform-conv-v2

pytorch-deform-conv-v2 copied to clipboard

deform_conv_3d

5

Hi, I want to use 3D deform_conv in my study, I read you 'deform_conv_v2.py', I try to extend your code to 3D deform_conv, while I no idea how to modify...

WMeixiang

The memory is not fridendly?

1

Firstly thank you for your great work. I have a deeper understanding for deformable convolution after reading this script. But I find this version uses huge memory when runs on...

zhangrong1722

why the gpu memory is rising when training?

1

Finally,the memory explodes

Fateeeeee

hello,is it useful to use dcn on 1x1conv?

kirkzZ

I ran `dcnv2` with `torchvision.ops.deform_conv2d`, and got the same result with `kernel_size=3`. But got different result when `kernel_size>3`. My implementation of `dcnv2` below: ``` def torch_initialize_weights(modules): # weight initialization for...

frotms

Why not use grid_sample?

1

I think the function in PyTorch grid_sample can get the value given the position, and that may be more convenient

SpadeLiu

About the learning rate setting of p_conv and m_conv

7

You set the gradient of p_conv and m_conv to 0.1 times the other layers, but I find the gradient has no change after backward. I use the following code to...

dontLoveBugs

Thanks for your contribution,I want that feature and offset are separated,like forward(self,feature,offset):..... How can i do this?

Jamryxx

bilinear kernel is wrong?

3

``` g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:])) g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 -...

jszgz

I have a question. We used Deformable Conv in classification tasks. We set the training batchsize the same as im2col_step. During the test process, we put different numbers of test...

crocodilegogogo