Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

support for pytorch 1.5.0 #592

Open
wants to merge 11 commits into
base: master
Choose a base branch
from
Open

support for pytorch 1.5.0 #592

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift click to select a range
7a8ad04
Update nms_cpu.cpp
RodrigoGantier May 26, 2020
f3bfc97
Update nms_cuda.cpp
RodrigoGantier May 26, 2020
dc31e70
Update roi_align_cuda.cpp
RodrigoGantier May 26, 2020
9ff1938
Update nms_kernel.cu
RodrigoGantier May 26, 2020
59d5622
Update roi_align_kernel.cu
RodrigoGantier May 26, 2020
910bf7a
Update deform_conv_cuda.cpp
RodrigoGantier May 26, 2020
264c392
Update deform_conv_cuda_kernel.cu
RodrigoGantier May 26, 2020
356902a
Update deform_pool_cuda.cpp
RodrigoGantier May 26, 2020
ca8fca1
Update deform_pool_cuda_kernel.cu
RodrigoGantier May 26, 2020
4d45d2d
Update README.md
RodrigoGantier May 26, 2020
21c3165
Update README.md
RodrigoGantier May 26, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update deform_conv_cuda_kernel.cu
  • Loading branch information
@RodrigoGantier
RodrigoGantier authored May 26, 2020
commit 264c392a520334269d39398a4d1df5fee9fca095
48 changes: 24 additions & 24 deletions alphapose/models/layers/dcn/src/deform_conv_cuda_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,9 257,9 @@ void deformable_im2col(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_im.scalar_type(), "deformable_im2col_gpu", ([&] {
const scalar_t *data_im_ = data_im.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_im_ = data_im.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
scalar_t *data_col_ = data_col.data_ptr<scalar_t>();

deformable_im2col_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_im_, data_offset_, height, width, ksize_h, ksize_w,
Expand Down Expand Up @@ -351,9 351,9 @@ void deformable_col2im(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_col.scalar_type(), "deformable_col2im_gpu", ([&] {
const scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
scalar_t *grad_im_ = grad_im.data<scalar_t>();
const scalar_t *data_col_ = data_col.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
scalar_t *grad_im_ = grad_im.data_ptr<scalar_t>();

deformable_col2im_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_col_, data_offset_, channels, height, width, ksize_h,
Expand Down Expand Up @@ -449,10 449,10 @@ void deformable_col2im_coord(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_col.scalar_type(), "deformable_col2im_coord_gpu", ([&] {
const scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_im_ = data_im.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
scalar_t *grad_offset_ = grad_offset.data<scalar_t>();
const scalar_t *data_col_ = data_col.data_ptr<scalar_t>();
const scalar_t *data_im_ = data_im.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
scalar_t *grad_offset_ = grad_offset.data_ptr<scalar_t>();

deformable_col2im_coord_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_col_, data_im_, data_offset_, channels, height, width,
Expand Down Expand Up @@ -779,10 779,10 @@ void modulated_deformable_im2col_cuda(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_im.scalar_type(), "modulated_deformable_im2col_gpu", ([&] {
const scalar_t *data_im_ = data_im.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
const scalar_t *data_mask_ = data_mask.data<scalar_t>();
scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_im_ = data_im.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
const scalar_t *data_mask_ = data_mask.data_ptr<scalar_t>();
scalar_t *data_col_ = data_col.data_ptr<scalar_t>();

modulated_deformable_im2col_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_im_, data_offset_, data_mask_, height_im, width_im, kernel_h, kenerl_w,
Expand Down Expand Up @@ -811,10 811,10 @@ void modulated_deformable_col2im_cuda(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_col.scalar_type(), "modulated_deformable_col2im_gpu", ([&] {
const scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
const scalar_t *data_mask_ = data_mask.data<scalar_t>();
scalar_t *grad_im_ = grad_im.data<scalar_t>();
const scalar_t *data_col_ = data_col.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
const scalar_t *data_mask_ = data_mask.data_ptr<scalar_t>();
scalar_t *grad_im_ = grad_im.data_ptr<scalar_t>();

modulated_deformable_col2im_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_col_, data_offset_, data_mask_, channels, height_im, width_im,
Expand Down Expand Up @@ -844,12 844,12 @@ void modulated_deformable_col2im_coord_cuda(

AT_DISPATCH_FLOATING_TYPES_AND_HALF(
data_col.scalar_type(), "modulated_deformable_col2im_coord_gpu", ([&] {
const scalar_t *data_col_ = data_col.data<scalar_t>();
const scalar_t *data_im_ = data_im.data<scalar_t>();
const scalar_t *data_offset_ = data_offset.data<scalar_t>();
const scalar_t *data_mask_ = data_mask.data<scalar_t>();
scalar_t *grad_offset_ = grad_offset.data<scalar_t>();
scalar_t *grad_mask_ = grad_mask.data<scalar_t>();
const scalar_t *data_col_ = data_col.data_ptr<scalar_t>();
const scalar_t *data_im_ = data_im.data_ptr<scalar_t>();
const scalar_t *data_offset_ = data_offset.data_ptr<scalar_t>();
const scalar_t *data_mask_ = data_mask.data_ptr<scalar_t>();
scalar_t *grad_offset_ = grad_offset.data_ptr<scalar_t>();
scalar_t *grad_mask_ = grad_mask.data_ptr<scalar_t>();

modulated_deformable_col2im_coord_gpu_kernel<<<GET_BLOCKS(num_kernels), CUDA_NUM_THREADS>>>(
num_kernels, data_col_, data_im_, data_offset_, data_mask_, channels, height_im, width_im,
Expand Down