Merge branch 'main' into main

Author: datumbox

.circleci/config.yml

@@ -848,7 +848,7 @@ jobs:
     executor:
       name: windows-gpu
     environment:
-      CUDA_VERSION: "11.1"
+      CUDA_VERSION: "11.3"
       PYTHON_VERSION: << parameters.python_version >>
     steps:
       - checkout

.circleci/config.yml.in

@@ -32,8 +32,8 @@ def build_workflows(prefix="", filter_branch=None, upload=False, indentation=6,
         for os_type in ["linux", "macos", "win"]:
             python_versions = PYTHON_VERSIONS
             cu_versions_dict = {
-                "linux": ["cpu", "cu102", "cu111", "cu113", "cu115", "rocm4.3.1", "rocm4.5.2"],
-                "win": ["cpu", "cu111", "cu113", "cu115"],
+                "linux": ["cpu", "cu102", "cu113", "cu115", "rocm4.3.1", "rocm4.5.2"],
+                "win": ["cpu", "cu113", "cu115"],
                 "macos": ["cpu"],
             }
             cu_versions = cu_versions_dict[os_type]

.circleci/regenerate.py

@@ -9,10 +9,11 @@ dependencies:
   - libpng
   - jpeg
   - ca-certificates
-  - h5py
+  - hdf5
   - pip:
     - future
     - pillow >=5.3.0, !=8.3.*
     - scipy
     - av
     - dataclasses
+    - h5py

.circleci/unittest/windows/scripts/environment.yml

@@ -28,7 +28,7 @@ else
 fi
 
 printf "Installing PyTorch with %s\n" "${cudatoolkit}"
-conda install -y -c "pytorch-${UPLOAD_CHANNEL}" -c conda-forge "pytorch-${UPLOAD_CHANNEL}"::pytorch[build="*${version}*"] "${cudatoolkit}" pytest
+conda install -y -c "pytorch-${UPLOAD_CHANNEL}" -c nvidia "pytorch-${UPLOAD_CHANNEL}"::pytorch[build="*${version}*"] "${cudatoolkit}" pytest
 
 torch_cuda=$(python -c "import torch; print(torch.cuda.is_available())")
 echo torch.cuda.is_available is $torch_cuda

.circleci/unittest/windows/scripts/install.sh

@@ -47,7 +47,8 @@ Operators
     FeaturePyramidNetwork
     StochasticDepth
     FrozenBatchNorm2d
-    ConvNormActivation
+    Conv2dNormActivation
+    Conv3dNormActivation
     SqueezeExcitation
     DropBlock2d
     DropBlock3d

docs/source/ops.rst

@@ -274,6 +274,7 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)
 
 

references/classification/utils.py

@@ -267,6 +267,7 @@ def setup_ddp(args):
         world_size=args.world_size,
         init_method=args.dist_url,
     )
+    torch.distributed.barrier()
 
 
 def reduce_across_processes(val):

references/optical_flow/utils.py

@@ -291,4 +291,5 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)

references/segmentation/utils.py

@@ -250,4 +250,5 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)