diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index a22df3e06..db0af456e 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -37,7 +37,7 @@ jobs: pip install "Pillow==9.1.1" # MindSpore must be installed following the instruction from official web, but not from pypi. # That's why we exclude mindspore from requirements.txt. Does this work? - pip install "mindspore>=1.8,<=1.10" + pip install "mindspore>=1.8" - name: Lint with pre-commit uses: pre-commit/action@v3.0.0 - name: Test with pytest (UT) diff --git a/configs/vit/README.md b/configs/vit/README.md index dc02cdf2d..bdf225d67 100644 --- a/configs/vit/README.md +++ b/configs/vit/README.md @@ -75,7 +75,7 @@ For detailed illustration of all hyper-parameters, please refer to [config.py](h **Note:** 1) As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size. -2) The current configuration with a batch_size of 512, was initially set for a machine with 64GB of VRAM. To avoid running out of memory (OOM) on machines with smaller VRAM, consider reducing the batch_size to 256 or lower. +2) The current configuration with a batch_size of 512, was initially set for a machine with 64GB of VRAM. To avoid running out of memory (OOM) on machines with smaller VRAM, consider reducing the batch_size to 256 or lower. Simultaneously, to maintain the consistency of training results, please scale the learning rate down proportionally with decreasing batch_size. * Standalone Training diff --git a/tests/modules/parallel/test_parallel_dataset.py b/tests/modules/parallel/test_parallel_dataset.py index 75a3a9652..f676f2fcb 100644 --- a/tests/modules/parallel/test_parallel_dataset.py +++ b/tests/modules/parallel/test_parallel_dataset.py @@ -62,7 +62,7 @@ def test_create_dataset_distribute_imagenet(mode, name, split, shuffle, num_para @pytest.mark.parametrize("mode", [0, 1]) -@pytest.mark.parametrize("name", ["MNIST", "CIFAR10"]) +@pytest.mark.parametrize("name", ["CIFAR10"]) @pytest.mark.parametrize("split", ["train", "val"]) @pytest.mark.parametrize("shuffle", [True, False]) @pytest.mark.parametrize("num_parallel_workers", [2, 4, 8, 16]) diff --git a/tests/modules/parallel/test_parallel_transforms.py b/tests/modules/parallel/test_parallel_transforms.py index 07fc367aa..aded80305 100644 --- a/tests/modules/parallel/test_parallel_transforms.py +++ b/tests/modules/parallel/test_parallel_transforms.py @@ -71,7 +71,7 @@ def test_transforms_distribute_imagenet(mode, name, image_resize, is_training): @pytest.mark.parametrize("mode", [0, 1]) -@pytest.mark.parametrize("name", ["MNIST", "CIFAR10"]) +@pytest.mark.parametrize("name", ["CIFAR10"]) @pytest.mark.parametrize("image_resize", [224, 256, 320]) @pytest.mark.parametrize("is_training", [True, False]) @pytest.mark.parametrize("download", [True, False]) diff --git a/tests/modules/test_config.py b/tests/modules/test_config.py index af556af27..0a7b3e8db 100644 --- a/tests/modules/test_config.py +++ b/tests/modules/test_config.py @@ -36,7 +36,7 @@ def test_checker_invalid(): @pytest.mark.parametrize("mode", [0, 1]) -@pytest.mark.parametrize("dataset", ["mnist", "imagenet"]) +@pytest.mark.parametrize("dataset", ["imagenet"]) def test_parse_args_without_yaml(mode, dataset): args = parse_args([f"--mode={mode}", f"--dataset={dataset}"]) assert args.mode == mode @@ -46,7 +46,7 @@ def test_parse_args_without_yaml(mode, dataset): @pytest.mark.parametrize("cfg_yaml", ["configs/resnet/resnet_18_ascend.yaml"]) @pytest.mark.parametrize("mode", [1]) -@pytest.mark.parametrize("dataset", ["mnist"]) +@pytest.mark.parametrize("dataset", ["imagenet"]) def test_parse_args_with_yaml(cfg_yaml, mode, dataset): args = parse_args([f"--config={cfg_yaml}", f"--mode={mode}", f"--dataset={dataset}"]) assert args.mode == mode diff --git a/tests/modules/test_dataset.py b/tests/modules/test_dataset.py index 6a3181d21..7f692e756 100644 --- a/tests/modules/test_dataset.py +++ b/tests/modules/test_dataset.py @@ -58,7 +58,7 @@ def test_create_dataset_standalone_imagenet(mode, name, split, shuffle, num_samp assert dataset is not None -# test MNIST CIFAR10 +# test CIFAR10 @pytest.mark.parametrize("mode", [0, 1]) @pytest.mark.parametrize("name", ["CIFAR10"]) @pytest.mark.parametrize("split", ["train", "test"]) @@ -95,8 +95,5 @@ def test_create_dataset_standalone_mc(mode, name, split, shuffle, num_samples, n download=download, ) - assert ( - type(dataset) == ms.dataset.engine.datasets_vision.MnistDataset - or type(dataset) == ms.dataset.engine.datasets_vision.Cifar10Dataset - ) + assert type(dataset) == ms.dataset.engine.datasets_vision.Cifar10Dataset assert dataset is not None diff --git a/tests/modules/test_transforms.py b/tests/modules/test_transforms.py index c8ac9a964..8c5cc5189 100644 --- a/tests/modules/test_transforms.py +++ b/tests/modules/test_transforms.py @@ -83,7 +83,7 @@ def test_transforms_standalone_imagenet(mode, name, image_resize, is_training, a assert output_shape[0][0] == 3 * batch_size and output_shape[1][0] == 3 * batch_size, "augment splits error!" -# test mnist cifar10 +# test cifar10 @pytest.mark.parametrize("mode", [0, 1]) @pytest.mark.parametrize("name", ["CIFAR10"]) @pytest.mark.parametrize("image_resize", [224, 256]) diff --git a/tests/tasks/test_train_mnist.py b/tests/tasks/test_train_mnist.py deleted file mode 100644 index 0faeb9486..000000000 --- a/tests/tasks/test_train_mnist.py +++ /dev/null @@ -1,105 +0,0 @@ -import sys - -sys.path.append(".") - -import pytest - -import mindspore as ms -from mindspore import nn - -from mindcv.data import create_dataset, create_loader, create_transforms -from mindcv.loss import create_loss -from mindcv.models import create_model -from mindcv.optim import create_optimizer -from mindcv.scheduler import create_scheduler - - -@pytest.mark.parametrize("mode", [ms.GRAPH_MODE, ms.PYNATIVE_MODE]) -def test_train_mnist(mode): - """ - test mobilenet_v1_train_gpu(single) - """ - num_workers = 2 - num_classes = 10 - batch_size = 16 - num_epochs = 1 # noqa: F841 - - set_sink_mode = True # noqa: F841 - - dataset_name = "mnist" - model_name = "resnet18" - scheduler_name = "constant" - lr = 1e-3 - loss_name = "CE" - opt_name = "adam" - - ms.set_seed(1) - ms.set_context(mode=mode) - - device_num = None - rank_id = None - - dataset_train = create_dataset( - name=dataset_name, - num_samples=100, - num_shards=device_num, - shard_id=rank_id, - download=True, - ) - - transform_train = create_transforms(dataset_name=dataset_name) - - loader_train = create_loader( - dataset=dataset_train, - batch_size=batch_size, - is_training=True, - num_classes=num_classes, - transform=transform_train, - num_parallel_workers=num_workers, - drop_remainder=True, - ) - - network = create_model( - model_name=model_name, - in_channels=1, - num_classes=num_classes, - ) - - loss = create_loss(name=loss_name) - - net_with_criterion = nn.WithLossCell(network, loss) - - steps_per_epoch = loader_train.get_dataset_size() - print("Steps per epoch: ", steps_per_epoch) - - lr_scheduler = create_scheduler( - steps_per_epoch=steps_per_epoch, - scheduler=scheduler_name, - lr=lr, - ) - - opt = create_optimizer( - network.trainable_params(), - opt=opt_name, - lr=lr_scheduler, - ) - - train_network = nn.TrainOneStepCell(network=net_with_criterion, optimizer=opt) - train_network.set_train() - losses = [] - - num_steps = 0 - max_steps = 10 - while num_steps < max_steps: - for batch, (data, label) in enumerate(loader_train.create_tuple_iterator()): - loss = train_network(data, label) - losses.append(loss) - print(loss) - - num_steps += 1 - - assert losses[num_steps - 1] < losses[0], "Loss does NOT decrease" - - -if __name__ == "__main__": - test_train_mnist(ms.GRAPH_MODE)