Merge branch 'main' into check-rotate-autodiff

Author: vfdev-5

.circleci/unittest/linux/scripts/environment.yml

@@ -9,8 +9,6 @@ dependencies:
   - libpng
   - jpeg
   - ca-certificates
-  # TODO: remove this after https://github.com/pytorch/pytorch/issues/69905 is resolved
-  - pyyaml
   - pip:
     - future
     - pillow >=5.3.0, !=8.3.*

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

@@ -9,8 +9,6 @@ dependencies:
   - libpng
   - jpeg
   - ca-certificates
-  # TODO: remove this after https://github.com/pytorch/pytorch/issues/69905 is resolved
-  - pyyaml
   - pip:
     - future
     - pillow >=5.3.0, !=8.3.*

references/classification/sampler.py

@@ -15,7 +15,7 @@ class RASampler(torch.utils.data.Sampler):
     https://github.com/facebookresearch/deit/blob/main/samplers.py
     """
 
-    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, seed=0):
+    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, seed=0, repetitions=3):
         if num_replicas is None:
             if not dist.is_available():
                 raise RuntimeError("Requires distributed package to be available!")
@@ -28,11 +28,12 @@ def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, seed=0):
         self.num_replicas = num_replicas
         self.rank = rank
         self.epoch = 0
-        self.num_samples = int(math.ceil(len(self.dataset) * 3.0 / self.num_replicas))
+        self.num_samples = int(math.ceil(len(self.dataset) * float(repetitions) / self.num_replicas))
         self.total_size = self.num_samples * self.num_replicas
         self.num_selected_samples = int(math.floor(len(self.dataset) // 256 * 256 / self.num_replicas))
         self.shuffle = shuffle
         self.seed = seed
+        self.repetitions = repetitions
 
     def __iter__(self):
         # Deterministically shuffle based on epoch
@@ -44,7 +45,7 @@ def __iter__(self):
             indices = list(range(len(self.dataset)))
 
         # Add extra samples to make it evenly divisible
-        indices = [ele for ele in indices for i in range(3)]
+        indices = [ele for ele in indices for i in range(self.repetitions)]
         indices += indices[: (self.total_size - len(indices))]
         assert len(indices) == self.total_size
 

references/classification/train.py

@@ -174,7 +174,7 @@ def load_data(traindir, valdir, args):
     print("Creating data loaders")
     if args.distributed:
         if args.ra_sampler:
-            train_sampler = RASampler(dataset, shuffle=True)
+            train_sampler = RASampler(dataset, shuffle=True, repetitions=args.ra_reps)
         else:
             train_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
         test_sampler = torch.utils.data.distributed.DistributedSampler(dataset_test, shuffle=False)
@@ -485,7 +485,10 @@ def get_args_parser(add_help=True):
         "--train-crop-size", default=224, type=int, help="the random crop size used for training (default: 224)"
     )
     parser.add_argument("--clip-grad-norm", default=None, type=float, help="the maximum gradient norm (default None)")
-    parser.add_argument("--ra-sampler", action="store_true", help="whether to use ra_sampler in training")
+    parser.add_argument("--ra-sampler", action="store_true", help="whether to use Repeated Augmentation in training")
+    parser.add_argument(
+        "--ra-reps", default=3, type=int, help="number of repetitions for Repeated Augmentation (default: 3)"
+    )
 
     # Prototype models only
     parser.add_argument("--weights", default=None, type=str, help="the weights enum name to load")

torchvision/csrc/io/image/cpu/decode_jpeg.cpp

@@ -70,6 +70,8 @@ static void torch_jpeg_set_source_mgr(
 } // namespace
 
 torch::Tensor decode_jpeg(const torch::Tensor& data, ImageReadMode mode) {
+  C10_LOG_API_USAGE_ONCE(
+      "torchvision.csrc.io.image.cpu.decode_jpeg.decode_jpeg");
   // Check that the input tensor dtype is uint8
   TORCH_CHECK(data.dtype() == torch::kU8, "Expected a torch.uint8 tensor");
   // Check that the input tensor is 1-dimensional

torchvision/csrc/io/image/cpu/decode_png.cpp

@@ -23,6 +23,7 @@ torch::Tensor decode_png(
     const torch::Tensor& data,
     ImageReadMode mode,
     bool allow_16_bits) {
+  C10_LOG_API_USAGE_ONCE("torchvision.csrc.io.image.cpu.decode_png.decode_png");
   // Check that the input tensor dtype is uint8
   TORCH_CHECK(data.dtype() == torch::kU8, "Expected a torch.uint8 tensor");
   // Check that the input tensor is 1-dimensional

torchvision/csrc/io/image/cpu/encode_jpeg.cpp

@@ -25,6 +25,8 @@ using JpegSizeType = size_t;
 using namespace detail;
 
 torch::Tensor encode_jpeg(const torch::Tensor& data, int64_t quality) {
+  C10_LOG_API_USAGE_ONCE(
+      "torchvision.csrc.io.image.cpu.encode_jpeg.encode_jpeg");
   // Define compression structures and error handling
   struct jpeg_compress_struct cinfo {};
   struct torch_jpeg_error_mgr jerr {};

torchvision/csrc/io/image/cpu/encode_png.cpp

@@ -63,6 +63,7 @@ void torch_png_write_data(
 } // namespace
 
 torch::Tensor encode_png(const torch::Tensor& data, int64_t compression_level) {
+  C10_LOG_API_USAGE_ONCE("torchvision.csrc.io.image.cpu.encode_png.encode_png");
   // Define compression structures and error handling
   png_structp png_write;
   png_infop info_ptr;

torchvision/csrc/io/image/cpu/read_write_file.cpp

@@ -33,6 +33,8 @@ std::wstring utf8_decode(const std::string& str) {
 #endif
 
 torch::Tensor read_file(const std::string& filename) {
+  C10_LOG_API_USAGE_ONCE(
+      "torchvision.csrc.io.image.cpu.read_write_file.read_file");
 #ifdef _WIN32
   // According to
   // https://docs.microsoft.com/en-us/cpp/c-runtime-library/reference/stat-functions?view=vs-2019,
@@ -76,6 +78,8 @@ torch::Tensor read_file(const std::string& filename) {
 }
 
 void write_file(const std::string& filename, torch::Tensor& data) {
+  C10_LOG_API_USAGE_ONCE(
+      "torchvision.csrc.io.image.cpu.read_write_file.write_file");
   // Check that the input tensor is on CPU
   TORCH_CHECK(data.device() == torch::kCPU, "Input tensor should be on CPU");
 

torchvision/csrc/io/image/cuda/decode_jpeg_cuda.cpp

@@ -33,6 +33,8 @@ torch::Tensor decode_jpeg_cuda(
     const torch::Tensor& data,
     ImageReadMode mode,
     torch::Device device) {
+  C10_LOG_API_USAGE_ONCE(
+      "torchvision.csrc.io.image.cuda.decode_jpeg_cuda.decode_jpeg_cuda");
   TORCH_CHECK(data.dtype() == torch::kU8, "Expected a torch.uint8 tensor");
 
   TORCH_CHECK(