!2087 data aug changes from c to py

Merge pull request !2087 from panfengfeng/mobilenetv2_data_aug_change

example/mobilenetv2/eval.py

@@ -23,7 +23,7 @@ from mindspore.train.model import Model
 from mindspore.train.serialization import load_checkpoint, load_param_into_net
 from mindspore.common import dtype as mstype
 from mindspore.model_zoo.mobilenetV2 import mobilenet_v2
-from src.dataset import create_dataset
+from src.dataset import create_dataset_py
 from src.config import config_ascend, config_gpu
 
 
@@ -60,11 +60,11 @@ if __name__ == '__main__':
             if isinstance(cell, nn.Dense):
                 cell.to_float(mstype.float32)
 
-    dataset = create_dataset(dataset_path=args_opt.dataset_path,
-                             do_train=False,
-                             config=config_platform,
-                             platform=args_opt.platform,
-                             batch_size=config_platform.batch_size)
+    dataset = create_dataset_py(dataset_path=args_opt.dataset_path,
+                                do_train=False,
+                                config=config_platform,
+                                platform=args_opt.platform,
+                                batch_size=config_platform.batch_size)
     step_size = dataset.get_dataset_size()
 
     if args_opt.checkpoint_path:

example/mobilenetv2/src/dataset.py

@@ -20,6 +20,7 @@ import mindspore.common.dtype as mstype
 import mindspore.dataset.engine as de
 import mindspore.dataset.transforms.vision.c_transforms as C
 import mindspore.dataset.transforms.c_transforms as C2
+import mindspore.dataset.transforms.vision.py_transforms as P
 
 def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch_size=32):
     """
@@ -56,7 +57,6 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
         raise ValueError("Unsupport platform.")
 
     resize_height = config.image_height
-    resize_width = config.image_width
 
     if do_train:
         buffer_size = 20480
@@ -65,20 +65,16 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
 
     # define map operations
     decode_op = C.Decode()
-    resize_crop_op = C.RandomCropDecodeResize(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
+    resize_crop_decode_op = C.RandomCropDecodeResize(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
     horizontal_flip_op = C.RandomHorizontalFlip(prob=0.5)
 
-    resize_op = C.Resize((256, 256))
-    center_crop = C.CenterCrop(resize_width)
-    random_color_op = C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
+    resize_op = C.Resize(256)
+    center_crop = C.CenterCrop(resize_height)
     normalize_op = C.Normalize(mean=[0.485*255, 0.456*255, 0.406*255], std=[0.229*255, 0.224*255, 0.225*255])
     change_swap_op = C.HWC2CHW()
 
-    transform_uniform = [horizontal_flip_op, random_color_op]
-    uni_aug = C.UniformAugment(operations=transform_uniform, num_ops=2)
-
     if do_train:
-        trans = [resize_crop_op, uni_aug, normalize_op, change_swap_op]
+        trans = [resize_crop_decode_op, horizontal_flip_op, normalize_op, change_swap_op]
     else:
         trans = [decode_op, resize_op, center_crop, normalize_op, change_swap_op]
 
@@ -94,3 +90,71 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
     ds = ds.repeat(repeat_num)
 
     return ds
+
+def create_dataset_py(dataset_path, do_train, config, platform, repeat_num=1, batch_size=32):
+    """
+    create a train or eval dataset
+
+    Args:
+        dataset_path(string): the path of dataset.
+        do_train(bool): whether dataset is used for train or eval.
+        repeat_num(int): the repeat times of dataset. Default: 1.
+        batch_size(int): the batch size of dataset. Default: 32.
+
+    Returns:
+        dataset
+    """
+    if platform == "Ascend":
+        rank_size = int(os.getenv("RANK_SIZE"))
+        rank_id = int(os.getenv("RANK_ID"))
+        if do_train:
+            if rank_size == 1:
+                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
+            else:
+                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
+                                             num_shards=rank_size, shard_id=rank_id)
+        else:
+            ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
+    elif platform == "GPU":
+        if do_train:
+            from mindspore.communication.management import get_rank, get_group_size
+            ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
+                                         num_shards=get_group_size(), shard_id=get_rank())
+        else:
+            ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
+    else:
+        raise ValueError("Unsupport platform.")
+
+    resize_height = config.image_height
+
+    if do_train:
+        buffer_size = 20480
+        # apply shuffle operations
+        ds = ds.shuffle(buffer_size=buffer_size)
+
+    # define map operations
+    decode_op = P.Decode()
+    resize_crop_op = P.RandomResizedCrop(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
+    horizontal_flip_op = P.RandomHorizontalFlip(prob=0.5)
+
+    resize_op = P.Resize(256)
+    center_crop = P.CenterCrop(resize_height)
+    to_tensor = P.ToTensor()
+    normalize_op = P.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+
+    if do_train:
+        trans = [decode_op, resize_crop_op, horizontal_flip_op, to_tensor, normalize_op]
+    else:
+        trans = [decode_op, resize_op, center_crop, to_tensor, normalize_op]
+
+    compose = P.ComposeOp(trans)
+
+    ds = ds.map(input_columns="image", operations=compose(), num_parallel_workers=8, python_multiprocessing=True)
+
+    # apply batch operations
+    ds = ds.batch(batch_size, drop_remainder=True)
+
+    # apply dataset repeat operation
+    ds = ds.repeat(repeat_num)
+
+    return ds

example/mobilenetv2/src/launch.py

@@ -18,6 +18,7 @@ import sys
 import json
 import subprocess
 import shutil
+import platform
 from argparse import ArgumentParser
 
 def parse_args():
@@ -79,7 +80,8 @@ def main():
             device_ips[device_id] = device_ip
             print('device_id:{}, device_ip:{}'.format(device_id, device_ip))
     hccn_table = {}
-    hccn_table['board_id'] = '0x0000'
+    arch = platform.processor()
+    hccn_table['board_id'] = {'aarch64': '0x002f', 'x86_64': '0x0000'}[arch]
     hccn_table['chip_info'] = '910'
     hccn_table['deploy_mode'] = 'lab'
     hccn_table['group_count'] = '1'

example/mobilenetv2/train.py

@@ -35,7 +35,7 @@ from mindspore.train.serialization import load_checkpoint, load_param_into_net
 from mindspore.communication.management import init, get_group_size
 from mindspore.model_zoo.mobilenetV2 import mobilenet_v2
 import mindspore.dataset.engine as de
-from src.dataset import create_dataset
+from src.dataset import create_dataset_py
 from src.lr_generator import get_lr
 from src.config import config_gpu, config_ascend
 
@@ -173,12 +173,12 @@ if __name__ == '__main__':
                 is_grad=False, sparse=True, reduction='mean')
         # define dataset
         epoch_size = config_gpu.epoch_size
-        dataset = create_dataset(dataset_path=args_opt.dataset_path,
-                                 do_train=True,
-                                 config=config_gpu,
-                                 platform=args_opt.platform,
-                                 repeat_num=epoch_size,
-                                 batch_size=config_gpu.batch_size)
+        dataset = create_dataset_py(dataset_path=args_opt.dataset_path,
+                                    do_train=True,
+                                    config=config_gpu,
+                                    platform=args_opt.platform,
+                                    repeat_num=epoch_size,
+                                    batch_size=config_gpu.batch_size)
         step_size = dataset.get_dataset_size()
         # resume
         if args_opt.pre_trained:
@@ -232,12 +232,12 @@ if __name__ == '__main__':
         else:
             loss = SoftmaxCrossEntropyWithLogits(
                 is_grad=False, sparse=True, reduction='mean')
-        dataset = create_dataset(dataset_path=args_opt.dataset_path,
-                                 do_train=True,
-                                 config=config_ascend,
-                                 platform=args_opt.platform,
-                                 repeat_num=epoch_size,
-                                 batch_size=config_ascend.batch_size)
+        dataset = create_dataset_py(dataset_path=args_opt.dataset_path,
+                                    do_train=True,
+                                    config=config_ascend,
+                                    platform=args_opt.platform,
+                                    repeat_num=epoch_size,
+                                    batch_size=config_ascend.batch_size)
         step_size = dataset.get_dataset_size()
         if args_opt.pre_trained:
             param_dict = load_checkpoint(args_opt.pre_trained)

example/mobilenetv2_quant/eval.py

@@ -22,7 +22,7 @@ from mindspore import nn
 from mindspore.train.model import Model
 from mindspore.train.serialization import load_checkpoint, load_param_into_net
 from src.mobilenetV2_quant import mobilenet_v2_quant
-from src.dataset import create_dataset
+from src.dataset import create_dataset_py
 from src.config import config_ascend
 
 parser = argparse.ArgumentParser(description='Image classification')
@@ -46,11 +46,11 @@ if __name__ == '__main__':
     loss = nn.SoftmaxCrossEntropyWithLogits(
         is_grad=False, sparse=True, reduction='mean')
 
-    dataset = create_dataset(dataset_path=args_opt.dataset_path,
-                             do_train=False,
-                             config=config_platform,
-                             platform=args_opt.platform,
-                             batch_size=config_platform.batch_size)
+    dataset = create_dataset_py(dataset_path=args_opt.dataset_path,
+                                do_train=False,
+                                config=config_platform,
+                                platform=args_opt.platform,
+                                batch_size=config_platform.batch_size)
     step_size = dataset.get_dataset_size()
 
     if args_opt.checkpoint_path:

example/mobilenetv2_quant/src/dataset.py

@@ -20,6 +20,7 @@ import mindspore.common.dtype as mstype
 import mindspore.dataset.engine as de
 import mindspore.dataset.transforms.vision.c_transforms as C
 import mindspore.dataset.transforms.c_transforms as C2
+import mindspore.dataset.transforms.vision.py_transforms as P
 
 def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch_size=32):
     """
@@ -41,7 +42,7 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
             if rank_size == 1:
                 ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
             else:
-                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False,
+                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
                                              num_shards=rank_size, shard_id=rank_id)
         else:
             ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
@@ -49,7 +50,6 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
         raise ValueError("Unsupport platform.")
 
     resize_height = config.image_height
-    resize_width = config.image_width
 
     if do_train:
         buffer_size = 20480
@@ -58,26 +58,22 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
 
     # define map operations
     decode_op = C.Decode()
-    resize_crop_op = C.RandomCropDecodeResize(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
+    resize_crop_decode_op = C.RandomCropDecodeResize(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
     horizontal_flip_op = C.RandomHorizontalFlip(prob=0.5)
 
-    resize_op = C.Resize((256, 256))
-    center_crop = C.CenterCrop(resize_width)
-    random_color_op = C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
+    resize_op = C.Resize(256)
+    center_crop = C.CenterCrop(resize_height)
     normalize_op = C.Normalize(mean=[0.485*255, 0.456*255, 0.406*255], std=[0.229*255, 0.224*255, 0.225*255])
     change_swap_op = C.HWC2CHW()
 
-    transform_uniform = [horizontal_flip_op, random_color_op]
-    uni_aug = C.UniformAugment(operations=transform_uniform, num_ops=2)
-
     if do_train:
-        trans = [resize_crop_op, uni_aug, normalize_op, change_swap_op]
+        trans = [resize_crop_decode_op, horizontal_flip_op, normalize_op, change_swap_op]
     else:
         trans = [decode_op, resize_op, center_crop, normalize_op, change_swap_op]
 
     type_cast_op = C2.TypeCast(mstype.int32)
 
-    ds = ds.map(input_columns="image", operations=trans, num_parallel_workers=8)
+    ds = ds.map(input_columns="image", operations=trans, num_parallel_workers=16)
     ds = ds.map(input_columns="label", operations=type_cast_op, num_parallel_workers=8)
 
     # apply batch operations
@@ -87,3 +83,64 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch
     ds = ds.repeat(repeat_num)
 
     return ds
+
+def create_dataset_py(dataset_path, do_train, config, platform, repeat_num=1, batch_size=32):
+    """
+    create a train or eval dataset
+
+    Args:
+        dataset_path(string): the path of dataset.
+        do_train(bool): whether dataset is used for train or eval.
+        repeat_num(int): the repeat times of dataset. Default: 1.
+        batch_size(int): the batch size of dataset. Default: 32.
+
+    Returns:
+        dataset
+    """
+    if platform == "Ascend":
+        rank_size = int(os.getenv("RANK_SIZE"))
+        rank_id = int(os.getenv("RANK_ID"))
+        if do_train:
+            if rank_size == 1:
+                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
+            else:
+                ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
+                                             num_shards=rank_size, shard_id=rank_id)
+        else:
+            ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
+    else:
+        raise ValueError("Unsupport platform.")
+
+    resize_height = config.image_height
+
+    if do_train:
+        buffer_size = 20480
+        # apply shuffle operations
+        ds = ds.shuffle(buffer_size=buffer_size)
+
+    # define map operations
+    decode_op = P.Decode()
+    resize_crop_op = P.RandomResizedCrop(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
+    horizontal_flip_op = P.RandomHorizontalFlip(prob=0.5)
+
+    resize_op = P.Resize(256)
+    center_crop = P.CenterCrop(resize_height)
+    to_tensor = P.ToTensor()
+    normalize_op = P.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+
+    if do_train:
+        trans = [decode_op, resize_crop_op, horizontal_flip_op, to_tensor, normalize_op]
+    else:
+        trans = [decode_op, resize_op, center_crop, to_tensor, normalize_op]
+
+    compose = P.ComposeOp(trans)
+
+    ds = ds.map(input_columns="image", operations=compose(), num_parallel_workers=8, python_multiprocessing=True)
+
+    # apply batch operations
+    ds = ds.batch(batch_size, drop_remainder=True)
+
+    # apply dataset repeat operation
+    ds = ds.repeat(repeat_num)
+
+    return ds

example/mobilenetv2_quant/train.py

@@ -32,7 +32,7 @@ from mindspore.train.callback import ModelCheckpoint, CheckpointConfig, Callback
 from mindspore.train.serialization import load_checkpoint
 from mindspore.communication.management import init
 import mindspore.dataset.engine as de
-from src.dataset import create_dataset
+from src.dataset import create_dataset_py
 from src.lr_generator import get_lr
 from src.config import config_ascend
 from src.mobilenetV2_quant import mobilenet_v2_quant
@@ -197,12 +197,12 @@ if __name__ == '__main__':
     else:
         loss = SoftmaxCrossEntropyWithLogits(
             is_grad=False, sparse=True, reduction='mean')
-    dataset = create_dataset(dataset_path=args_opt.dataset_path,
-                             do_train=True,
-                             config=config_ascend,
-                             platform=args_opt.platform,
-                             repeat_num=epoch_size,
-                             batch_size=config_ascend.batch_size)
+    dataset = create_dataset_py(dataset_path=args_opt.dataset_path,
+                                do_train=True,
+                                config=config_ascend,
+                                platform=args_opt.platform,
+                                repeat_num=epoch_size,
+                                batch_size=config_ascend.batch_size)
     step_size = dataset.get_dataset_size()
     if args_opt.pre_trained:
         param_dict = load_checkpoint(args_opt.pre_trained)