Merge branch 'main' into fix-docstring-fill-param

Author: abhitorch81

.github/workflows/build-cmake.yml

@@ -58,30 +58,30 @@ jobs:
 
         ${CONDA_RUN} ./.github/scripts/cmake.sh
 
-  windows:
-    strategy:
-      matrix:
-        include:
-          - runner: windows.4xlarge
-            gpu-arch-type: cpu
-          - runner: windows.g5.4xlarge.nvidia.gpu
-            gpu-arch-type: cuda
-            gpu-arch-version: "12.6"
-      fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/windows_job.yml@main
-    with:
-      repository: pytorch/vision
-      runner: ${{ matrix.runner }}
-      gpu-arch-type: ${{ matrix.gpu-arch-type }}
-      gpu-arch-version: ${{ matrix.gpu-arch-version }}
-      test-infra-ref: main
-      script: |
-        set -euo pipefail
+  # windows:
+  #   strategy:
+  #     matrix:
+  #       include:
+  #         - runner: windows.4xlarge
+  #           gpu-arch-type: cpu
+  #         - runner: windows.g5.4xlarge.nvidia.gpu
+  #           gpu-arch-type: cuda
+  #           gpu-arch-version: "12.6"
+  #     fail-fast: false
+  #   uses: pytorch/test-infra/.github/workflows/windows_job.yml@main
+  #   with:
+  #     repository: pytorch/vision
+  #     runner: ${{ matrix.runner }}
+  #     gpu-arch-type: ${{ matrix.gpu-arch-type }}
+  #     gpu-arch-version: ${{ matrix.gpu-arch-version }}
+  #     test-infra-ref: main
+  #     script: |
+  #       set -euo pipefail
 
-        export PYTHON_VERSION=3.9
-        export VC_YEAR=2022
-        export VSDEVCMD_ARGS=""
-        export GPU_ARCH_TYPE=${{ matrix.gpu-arch-type }}
-        export GPU_ARCH_VERSION=${{ matrix.gpu-arch-version }}
+  #       export PYTHON_VERSION=3.9
+  #       export VC_YEAR=2022
+  #       export VSDEVCMD_ARGS=""
+  #       export GPU_ARCH_TYPE=${{ matrix.gpu-arch-type }}
+  #       export GPU_ARCH_VERSION=${{ matrix.gpu-arch-version }}
 
-        ./.github/scripts/cmake.sh
+  #       ./.github/scripts/cmake.sh

torchvision/csrc/io/decoder/audio_sampler.cpp

@@ -49,12 +49,11 @@ bool AudioSampler::init(const SamplerParameters& params) {
   }
 
 #if LIBAVUTIL_VERSION_INT >= AV_VERSION_INT(57, 28, 100)
-  SwrContext* swrContext_ = NULL;
   AVChannelLayout channel_out;
   AVChannelLayout channel_in;
   av_channel_layout_default(&channel_out, params.out.audio.channels);
   av_channel_layout_default(&channel_in, params.in.audio.channels);
-  swr_alloc_set_opts2(
+  int ret = swr_alloc_set_opts2(
       &swrContext_,
       &channel_out,
       (AVSampleFormat)params.out.audio.format,
@@ -64,6 +63,10 @@ bool AudioSampler::init(const SamplerParameters& params) {
       params.in.audio.samples,
       0,
       logCtx_);
+  if (ret < 0 || swrContext_ == nullptr) {
+    LOG(ERROR) << "Cannot allocate SwrContext";
+    return false;
+  }
 #else
   swrContext_ = swr_alloc_set_opts(
       nullptr,
@@ -75,11 +78,11 @@ bool AudioSampler::init(const SamplerParameters& params) {
       params.in.audio.samples,
       0,
       logCtx_);
-#endif
   if (swrContext_ == nullptr) {
     LOG(ERROR) << "Cannot allocate SwrContext";
     return false;
   }
+#endif
 
   int result;
   if ((result = swr_init(swrContext_)) < 0) {

torchvision/csrc/io/decoder/decoder.cpp

@@ -154,7 +154,8 @@ int Decoder::readFunction(void* opaque, uint8_t* buf, int size) {
   if (decoder == nullptr) {
     return 0;
   }
-  return decoder->readCallback(buf, size);
+  int bytesRead = decoder->readCallback(buf, size);
+  return bytesRead == 0 ? AVERROR_EOF : bytesRead;
 }
 
 /* static */