Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!3302 Fix the cifar10 data processing issues for training and evaluating GoogLeNet 

Merge pull request !3302 from dessyang/master
This commit is contained in:
mindspore-ci-bot 2020-07-22 09:22:03 +08:00 committed by Gitee
parent 5f10417b9f 0c1761322f
commit 6561303b13
1 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
model_zoo/googlenet/src/dataset.py
View File

@ -32,7 +32,10 @@ def create_dataset(data_home, repeat_num=1, training=True):
data_dir = os.path.join(data_home, "cifar-10-verify-bin")
rank_size, rank_id = _get_rank_info()
data_set = ds.Cifar10Dataset(data_dir, num_shards=rank_size, shard_id=rank_id)
if training:
data_set = ds.Cifar10Dataset(data_dir, num_shards=rank_size, shard_id=rank_id, shuffle=True)
else:
data_set = ds.Cifar10Dataset(data_dir, num_shards=rank_size, shard_id=rank_id, shuffle=False)
resize_height = cfg.image_height
resize_width = cfg.image_width
@ -41,6 +44,7 @@ def create_dataset(data_home, repeat_num=1, training=True):
random_crop_op = vision.RandomCrop((32, 32), (4, 4, 4, 4)) # padding_mode default CONSTANT
random_horizontal_op = vision.RandomHorizontalFlip()
resize_op = vision.Resize((resize_height, resize_width)) # interpolation default BILINEAR
rescale_op = vision.Rescale(1.0/255.0, 0.0)
normalize_op = vision.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
changeswap_op = vision.HWC2CHW()
type_cast_op = C.TypeCast(mstype.int32)
@ -48,21 +52,18 @@ def create_dataset(data_home, repeat_num=1, training=True):
c_trans = []
if training:
c_trans = [random_crop_op, random_horizontal_op]
c_trans += [resize_op, normalize_op, changeswap_op]
c_trans += [resize_op, rescale_op, normalize_op, changeswap_op]
# apply map operations on images
data_set = data_set.map(input_columns="label", operations=type_cast_op)
data_set = data_set.map(input_columns="image", operations=c_trans)
# apply repeat operations
data_set = data_set.repeat(repeat_num)
# apply shuffle operations
data_set = data_set.shuffle(buffer_size=10)
# apply batch operations
data_set = data_set.batch(batch_size=cfg.batch_size, drop_remainder=True)
# apply repeat operations
data_set = data_set.repeat(repeat_num)
return data_set