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

[fix] Fix compilation bug in windows and add instruction for windows #540

Merged
merged 2 commits into from
Sep 4, 2020
Merged

[fix] Fix compilation bug in windows and add instruction for windows #540

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ad0f5b3
Add windows instruction and fix compilation bug
ZwwWayne Sep 4, 2020
aaa7e72
reformat codebase
ZwwWayne Sep 4, 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
13 changes: 13 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,6 +131,19 @@ e.g.,
CC=clang CXX=clang++ CFLAGS='-stdlib=libc++' MMCV_WITH_OPS=1 pip install -e .
```

If you are on Windows10, set the following environment variable before the installing command.

```bash
set MMCV_WITH_OPS=1
```

e.g.,

```bash
set MMCV_WITH_OPS=1
pip install -e .
```

Note: If you would like to use `opencv-python-headless` instead of `opencv-python`,
e.g., in a minimum container environment or servers without GUI,
you can first install it before installing MMCV to skip the installation of `opencv-python`.
Expand Down
12 changes: 8 additions & 4 deletions mmcv/ops/csrc/pytorch/focal_loss_cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ void SigmoidFocalLossForwardCUDAKernelLauncher(Tensor input, Tensor target,
const float alpha) {
int output_size = output.numel();
int num_classes = input.size(1);
AT_ASSERTM(target.max().item<long>() <= (long)num_classes,
AT_ASSERTM(target.max().item<int64_t>() <= (int64_t)num_classes,
"target label should smaller or equal than num classes");
at::cuda::CUDAGuard device_guard(input.device());
cudaStream_t stream = at::cuda::getCurrentCUDAStream();
Expand Down Expand Up @@ -53,7 +53,7 @@ void SoftmaxFocalLossForwardCUDAKernelLauncher(Tensor softmax, Tensor target,
int output_size = output.numel();
int num_classes = softmax.size(1);

AT_ASSERTM(target.max().item<long>() <= (long)num_classes,
AT_ASSERTM(target.max().item<int64_t>() <= (int64_t)num_classes,
"target label should smaller or equal than num classes");
at::cuda::CUDAGuard device_guard(softmax.device());
cudaStream_t stream = at::cuda::getCurrentCUDAStream();
Expand All @@ -80,7 +80,9 @@ void SoftmaxFocalLossBackwardCUDAKernelLauncher(Tensor softmax, Tensor target,
at::cuda::CUDAGuard device_guard(grad_input.device());
cudaStream_t stream = at::cuda::getCurrentCUDAStream();
AT_DISPATCH_FLOATING_TYPES_AND_HALF(
grad_input.scalar_type(), "softmax_focal_loss_backward_cuda1_kernel",
grad_input.scalar_type(),
"softmax_focal_loss_backward_cuda1_"
"kernel",
[&] {
softmax_focal_loss_backward_cuda1_kernel<scalar_t>
<<<GET_BLOCKS(output_size), THREADS_PER_BLOCK, 0, stream>>>(
Expand All @@ -93,7 +95,9 @@ void SoftmaxFocalLossBackwardCUDAKernelLauncher(Tensor softmax, Tensor target,

output_size = grad_input.numel();
AT_DISPATCH_FLOATING_TYPES_AND_HALF(
grad_input.scalar_type(), "softmax_focal_loss_backward_cuda2_kernel",
grad_input.scalar_type(),
"softmax_focal_loss_backward_cuda2_"
"kernel",
[&] {
softmax_focal_loss_backward_cuda2_kernel<scalar_t>
<<<GET_BLOCKS(output_size), THREADS_PER_BLOCK, 0, stream>>>(
Expand Down