Fix windows build (#953)

* #944
  MSBuild Compile time casting Error

* #944
 MSBuild Error  static_cast<Long> to static_cast<int64_t>

* Add eval.py
 Not Work find_contours

* Remove unnecessary file

* Lint

torchvision/csrc/cuda/ROIAlign_cuda.cu

@@ -326,7 +326,10 @@ at::Tensor ROIAlign_forward_cuda(
   auto output_size = num_rois * pooled_height * pooled_width * channels;
   cudaStream_t stream = at::cuda::getCurrentCUDAStream();
 
-  dim3 grid(std::min(at::cuda::ATenCeilDiv(output_size, 512L), 4096L));
+  dim3 grid(std::min(
+      at::cuda::ATenCeilDiv(
+          static_cast<int64_t>(output_size), static_cast<int64_t>(512)),
+      static_cast<int64_t>(4096)));
   dim3 block(512);
 
   if (output.numel() == 0) {
@@ -379,7 +382,10 @@ at::Tensor ROIAlign_backward_cuda(
 
   cudaStream_t stream = at::cuda::getCurrentCUDAStream();
 
-  dim3 grid(std::min(at::cuda::ATenCeilDiv(grad.numel(), 512L), 4096L));
+  dim3 grid(std::min(
+      at::cuda::ATenCeilDiv(
+          static_cast<int64_t>(grad.numel()), static_cast<int64_t>(512)),
+      static_cast<int64_t>(4096)));
   dim3 block(512);
 
   // handle possibly empty gradients

torchvision/csrc/cuda/ROIPool_cuda.cu

@@ -146,7 +146,10 @@ std::tuple<at::Tensor, at::Tensor> ROIPool_forward_cuda(
   auto output_size = num_rois * pooled_height * pooled_width * channels;
   cudaStream_t stream = at::cuda::getCurrentCUDAStream();
 
-  dim3 grid(std::min(at::cuda::ATenCeilDiv(output_size, 512L), 4096L));
+  dim3 grid(std::min(
+      at::cuda::ATenCeilDiv(
+          static_cast<int64_t>(output_size), static_cast<int64_t>(512)),
+      static_cast<int64_t>(4096)));
   dim3 block(512);
 
   if (output.numel() == 0) {
@@ -204,7 +207,10 @@ at::Tensor ROIPool_backward_cuda(
 
   cudaStream_t stream = at::cuda::getCurrentCUDAStream();
 
-  dim3 grid(std::min(at::cuda::ATenCeilDiv(grad.numel(), 512L), 4096L));
+  dim3 grid(std::min(
+      at::cuda::ATenCeilDiv(
+          static_cast<int64_t>(grad.numel()), static_cast<int64_t>(512)),
+      static_cast<int64_t>(4096)));
   dim3 block(512);
 
   // handle possibly empty gradients

torchvision/csrc/cuda/nms_cuda.cu

@@ -125,8 +125,7 @@ at::Tensor nms_cuda(const at::Tensor& dets,
   }
 
   AT_CUDA_CHECK(cudaGetLastError());
-  return
-      order_t
-          .index({keep.narrow(/*dim=*/0, /*start=*/0, /*length=*/num_to_keep)
+  return order_t.index(
+      {keep.narrow(/*dim=*/0, /*start=*/0, /*length=*/num_to_keep)
            .to(order_t.device(), keep.scalar_type())});
 }