Deformable-ConvNets-caffe
Deformable-ConvNets-caffe copied to clipboard
unsky
Deformable Convolutional Networks on caffe
Actually, I am confused about the conv op for `deformable ROI pooling`. Can you provide one train.prototxt with deformable ROI pooling? Thanks.
thx for your great work, in readme: bottom[1] (offset): (batch_size, deformable_group * kernel[0] * kernel[1]*2, height, width) according to your code (im2col) and the pytorch version, i think the last...
I have used the deformable conv in training my own model, but the offsets predicted in several iters reach over 1000. Solution provided by MSRA of paddding has been tried...
deformable_col2im_gpu函数里： `this->col_buffer_.shape(0)`应该改为`this->col_buffer_.count()` `bottom_diff+n*this->input_offset_dim_`应该改为‘bottom_diff+n*this->bottom_dim_’
hello, could I use Deformable-ConvNets-caffe by pycaffe to write the python conv code, and then generate the *.prototxt?
https://github.com/unsky/Deformable-ConvNets-caffe/blob/e0f7abd58e166398d3695871769108f03e547786/deformable_conv_cxx/deformable_im2col.cu#L395 Should be `int num_kernels = height_col * width_col * 2 * kernel_h * kernel_w * deformable_group; `?
Hi, my friend , according to your work ,I modify the yolo to deform-yolo, but the loss always are 3~4 whatever what I adjust lr and batchsize and so on...
In mnist network given,why used dilation convolution in offset layer? For the offset have a lager search area in feature map or not?
After I train the network you provide and obtain the Resnet_dcn.caffemodel, I compiled the matlab interface and try to load the caffemodel. However, an error appeared (caffe.layerparameter has no field...
