Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
magicwindyyd
mindspore
提交
06ed9ffd
M
mindspore
项目概览
magicwindyyd
/
mindspore
与 Fork 源项目一致
Fork自
MindSpore / mindspore
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
mindspore
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
06ed9ffd
编写于
7月 24, 2020
作者:
M
mindspore-ci-bot
提交者:
Gitee
7月 24, 2020
浏览文件
操作
浏览文件
下载
差异文件
!3183 Remove files on test fail for test_minddataset*.py
Merge pull request !3183 from tony_liu2/master
上级
60feafd7
1f4251a4
变更
5
显示空白变更内容
内联
并排
Showing
5 changed file
with
1313 addition
and
1090 deletion
+1313
-1090
tests/ut/python/dataset/test_minddataset.py
tests/ut/python/dataset/test_minddataset.py
+1069
-963
tests/ut/python/dataset/test_minddataset_exception.py
tests/ut/python/dataset/test_minddataset_exception.py
+69
-17
tests/ut/python/dataset/test_minddataset_multi_images_and_ndarray.py
...thon/dataset/test_minddataset_multi_images_and_ndarray.py
+59
-49
tests/ut/python/dataset/test_minddataset_padded.py
tests/ut/python/dataset/test_minddataset_padded.py
+71
-43
tests/ut/python/dataset/test_minddataset_sampler.py
tests/ut/python/dataset/test_minddataset_sampler.py
+45
-18
未找到文件。
tests/ut/python/dataset/test_minddataset.py
浏览文件 @
06ed9ffd
...
...
@@ -46,6 +46,7 @@ def add_and_remove_cv_file():
"""add/remove cv file"""
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -62,16 +63,22 @@ def add_and_remove_cv_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_cv_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
@
pytest
.
fixture
def
add_and_remove_nlp_file
():
"""add/remove nlp file"""
paths
=
[
"{}{}"
.
format
(
NLP_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -95,6 +102,12 @@ def add_and_remove_nlp_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_nlp_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
...
...
@@ -105,6 +118,7 @@ def add_and_remove_nlp_compress_file():
"""add/remove nlp file"""
paths
=
[
"{}{}"
.
format
(
NLP_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -140,6 +154,12 @@ def add_and_remove_nlp_compress_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_nlp_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
...
...
@@ -199,6 +219,7 @@ def test_cv_minddataset_writer_tutorial():
"""tutorial for cv dataset writer."""
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -212,6 +233,12 @@ def test_cv_minddataset_writer_tutorial():
writer
.
add_index
([
"file_name"
,
"label"
])
writer
.
write_raw_data
(
data
)
writer
.
commit
()
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
...
...
@@ -654,6 +681,7 @@ def test_cv_minddataset_reader_one_partition(add_and_remove_cv_file):
def
test_cv_minddataset_reader_two_dataset
(
add_and_remove_cv_file
):
"""tutorial for cv minderdataset."""
try
:
if
os
.
path
.
exists
(
CV1_FILE_NAME
):
os
.
remove
(
CV1_FILE_NAME
)
if
os
.
path
.
exists
(
"{}.db"
.
format
(
CV1_FILE_NAME
)):
...
...
@@ -702,6 +730,17 @@ def test_cv_minddataset_reader_two_dataset(add_and_remove_cv_file):
"-------------- item[label]: {} ----------------------------"
.
format
(
item
[
"label"
]))
num_iter
+=
1
assert
num_iter
==
30
except
Exception
as
error
:
if
os
.
path
.
exists
(
CV1_FILE_NAME
):
os
.
remove
(
CV1_FILE_NAME
)
if
os
.
path
.
exists
(
"{}.db"
.
format
(
CV1_FILE_NAME
)):
os
.
remove
(
"{}.db"
.
format
(
CV1_FILE_NAME
))
if
os
.
path
.
exists
(
CV2_FILE_NAME
):
os
.
remove
(
CV2_FILE_NAME
)
if
os
.
path
.
exists
(
"{}.db"
.
format
(
CV2_FILE_NAME
)):
os
.
remove
(
"{}.db"
.
format
(
CV2_FILE_NAME
))
raise
error
else
:
if
os
.
path
.
exists
(
CV1_FILE_NAME
):
os
.
remove
(
CV1_FILE_NAME
)
if
os
.
path
.
exists
(
"{}.db"
.
format
(
CV1_FILE_NAME
)):
...
...
@@ -710,11 +749,11 @@ def test_cv_minddataset_reader_two_dataset(add_and_remove_cv_file):
os
.
remove
(
CV2_FILE_NAME
)
if
os
.
path
.
exists
(
"{}.db"
.
format
(
CV2_FILE_NAME
)):
os
.
remove
(
"{}.db"
.
format
(
CV2_FILE_NAME
))
def
test_cv_minddataset_reader_two_dataset_partition
(
add_and_remove_cv_file
):
paths
=
[
"{}{}"
.
format
(
CV1_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -733,7 +772,8 @@ def test_cv_minddataset_reader_two_dataset_partition(add_and_remove_cv_file):
columns_list
=
[
"data"
,
"file_name"
,
"label"
]
num_readers
=
4
data_set
=
ds
.
MindDataset
([
CV_FILE_NAME
+
str
(
x
)
for
x
in
range
(
2
)]
+
[
CV1_FILE_NAME
+
str
(
x
)
for
x
in
range
(
2
,
4
)],
data_set
=
ds
.
MindDataset
([
CV_FILE_NAME
+
str
(
x
)
for
x
in
range
(
2
)]
+
[
CV1_FILE_NAME
+
str
(
x
)
for
x
in
range
(
2
,
4
)],
columns_list
,
num_readers
)
assert
data_set
.
get_dataset_size
()
<
20
num_iter
=
0
...
...
@@ -750,10 +790,15 @@ def test_cv_minddataset_reader_two_dataset_partition(add_and_remove_cv_file):
"-------------- item[label]: {} ----------------------------"
.
format
(
item
[
"label"
]))
num_iter
+=
1
assert
num_iter
<
20
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
def
test_cv_minddataset_reader_basic_tutorial
(
add_and_remove_cv_file
):
"""tutorial for cv minderdataset."""
...
...
@@ -1086,6 +1131,7 @@ def inputs(vectors, maxlen=50):
def
test_write_with_multi_bytes_and_array_and_read_by_MindDataset
():
mindrecord_file_name
=
"test.mindrecord"
try
:
if
os
.
path
.
exists
(
"{}"
.
format
(
mindrecord_file_name
)):
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
if
os
.
path
.
exists
(
"{}.db"
.
format
(
mindrecord_file_name
)):
...
...
@@ -1238,8 +1284,7 @@ def test_write_with_multi_bytes_and_array_and_read_by_MindDataset():
num_readers
=
1
data_set
=
ds
.
MindDataset
(
dataset_file
=
mindrecord_file_name
,
columns_list
=
[
"image2"
,
"source_sos_mask"
,
"image3"
,
"target_sos_ids"
],
columns_list
=
[
"image2"
,
"source_sos_mask"
,
"image3"
,
"target_sos_ids"
],
num_parallel_workers
=
num_readers
,
shuffle
=
False
)
assert
data_set
.
get_dataset_size
()
==
6
...
...
@@ -1314,8 +1359,9 @@ def test_write_with_multi_bytes_and_array_and_read_by_MindDataset():
num_readers
=
2
data_set
=
ds
.
MindDataset
(
dataset_file
=
mindrecord_file_name
,
columns_list
=
[
"label"
,
"target_eos_mask"
,
"image1"
,
"target_eos_ids"
,
"source_sos_mask"
,
"image2"
,
"image4"
,
"image3"
,
"source_sos_ids"
,
"image5"
,
"file_name"
],
columns_list
=
[
"label"
,
"target_eos_mask"
,
"image1"
,
"target_eos_ids"
,
"source_sos_mask"
,
"image2"
,
"image4"
,
"image3"
,
"source_sos_ids"
,
"image5"
,
"file_name"
],
num_parallel_workers
=
num_readers
,
shuffle
=
False
)
assert
data_set
.
get_dataset_size
()
==
6
...
...
@@ -1330,13 +1376,18 @@ def test_write_with_multi_bytes_and_array_and_read_by_MindDataset():
assert
item
[
field
]
==
data_value_to_list
[
num_iter
][
field
]
num_iter
+=
1
assert
num_iter
==
6
except
Exception
as
error
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
raise
error
else
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
def
test_write_with_multi_bytes_and_MindDataset
():
mindrecord_file_name
=
"test.mindrecord"
try
:
data
=
[{
"file_name"
:
"001.jpg"
,
"label"
:
43
,
"image1"
:
bytes
(
"image1 bytes abc"
,
encoding
=
'UTF-8'
),
"image2"
:
bytes
(
"image1 bytes def"
,
encoding
=
'UTF-8'
),
...
...
@@ -1506,13 +1557,17 @@ def test_write_with_multi_bytes_and_MindDataset():
assert
item
[
field
]
==
data_value_to_list
[
num_iter
][
field
]
num_iter
+=
1
assert
num_iter
==
6
except
Exception
as
error
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
raise
error
else
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
def
test_write_with_multi_array_and_MindDataset
():
mindrecord_file_name
=
"test.mindrecord"
try
:
data
=
[{
"source_sos_ids"
:
np
.
array
([
1
,
2
,
3
,
4
,
5
],
dtype
=
np
.
int64
),
"source_sos_mask"
:
np
.
array
([
6
,
7
,
8
,
9
,
10
,
11
,
12
],
dtype
=
np
.
int64
),
"source_eos_ids"
:
np
.
array
([
13
,
14
,
15
,
16
,
17
,
18
],
dtype
=
np
.
int64
),
...
...
@@ -1704,12 +1759,64 @@ def test_write_with_multi_array_and_MindDataset():
assert
item
[
field
]
==
data_value_to_list
[
num_iter
][
field
]
num_iter
+=
1
assert
num_iter
==
6
except
Exception
as
error
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
raise
error
else
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
def
test_numpy_generic
():
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
if
os
.
path
.
exists
(
"{}.db"
.
format
(
x
)):
os
.
remove
(
"{}.db"
.
format
(
x
))
writer
=
FileWriter
(
CV_FILE_NAME
,
FILES_NUM
)
cv_schema_json
=
{
"label1"
:
{
"type"
:
"int32"
},
"label2"
:
{
"type"
:
"int64"
},
"label3"
:
{
"type"
:
"float32"
},
"label4"
:
{
"type"
:
"float64"
}}
data
=
[]
for
idx
in
range
(
10
):
row
=
{}
row
[
'label1'
]
=
np
.
int32
(
idx
)
row
[
'label2'
]
=
np
.
int64
(
idx
*
10
)
row
[
'label3'
]
=
np
.
float32
(
idx
+
0.12345
)
row
[
'label4'
]
=
np
.
float64
(
idx
+
0.12345789
)
data
.
append
(
row
)
writer
.
add_schema
(
cv_schema_json
,
"img_schema"
)
writer
.
write_raw_data
(
data
)
writer
.
commit
()
num_readers
=
4
data_set
=
ds
.
MindDataset
(
CV_FILE_NAME
+
"0"
,
None
,
num_readers
,
shuffle
=
False
)
assert
data_set
.
get_dataset_size
()
==
10
idx
=
0
for
item
in
data_set
.
create_dict_iterator
():
assert
item
[
'label1'
]
==
item
[
'label1'
]
assert
item
[
'label2'
]
==
item
[
'label2'
]
assert
item
[
'label3'
]
==
item
[
'label3'
]
assert
item
[
'label4'
]
==
item
[
'label4'
]
idx
+=
1
assert
idx
==
10
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
def
test_write_with_float32_float64_float32_array_float64_array_and_MindDataset
():
mindrecord_file_name
=
"test.mindrecord"
try
:
data
=
[{
"float32_array"
:
np
.
array
([
1.2
,
2.78
,
3.1234
,
4.9871
,
5.12341
],
dtype
=
np
.
float32
),
"float64_array"
:
np
.
array
([
48.1234556789
,
49.3251241431
,
50.13514312414
,
51.8971298471
,
123414314.2141243
,
87.1212122
],
dtype
=
np
.
float64
),
...
...
@@ -1842,7 +1949,8 @@ def test_write_with_float32_float64_float32_array_float64_array_and_MindDataset(
np
.
array
(
data_value_to_list
[
num_iter
][
field
],
np
.
float32
)).
all
()
elif
item
[
field
].
dtype
==
np
.
float64
:
assert
math
.
isclose
(
item
[
field
],
np
.
array
(
data_value_to_list
[
num_iter
][
field
],
np
.
float64
),
rel_tol
=
1e-14
)
np
.
array
(
data_value_to_list
[
num_iter
][
field
],
np
.
float64
),
rel_tol
=
1e-14
)
else
:
assert
(
item
[
field
]
==
data_value_to_list
[
num_iter
][
field
]).
all
()
...
...
@@ -1850,45 +1958,43 @@ def test_write_with_float32_float64_float32_array_float64_array_and_MindDataset(
assert
item
[
field
]
==
data_value_to_list
[
num_iter
][
field
]
num_iter
+=
1
assert
num_iter
==
5
except
Exception
as
error
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
raise
error
else
:
os
.
remove
(
"{}"
.
format
(
mindrecord_file_name
))
os
.
remove
(
"{}.db"
.
format
(
mindrecord_file_name
))
def
test_numpy_generic
():
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
if
os
.
path
.
exists
(
"{}.db"
.
format
(
x
)):
os
.
remove
(
"{}.db"
.
format
(
x
))
writer
=
FileWriter
(
CV_FILE_NAME
,
FILES_NUM
)
cv_schema_json
=
{
"label1"
:
{
"type"
:
"int32"
},
"label2"
:
{
"type"
:
"int64"
},
"label3"
:
{
"type"
:
"float32"
},
"label4"
:
{
"type"
:
"float64"
}}
data
=
[]
for
idx
in
range
(
10
):
row
=
{}
row
[
'label1'
]
=
np
.
int32
(
idx
)
row
[
'label2'
]
=
np
.
int64
(
idx
*
10
)
row
[
'label3'
]
=
np
.
float32
(
idx
+
0.12345
)
row
[
'label4'
]
=
np
.
float64
(
idx
+
0.12345789
)
data
.
append
(
row
)
writer
.
add_schema
(
cv_schema_json
,
"img_schema"
)
writer
.
write_raw_data
(
data
)
writer
.
commit
()
num_readers
=
4
data_set
=
ds
.
MindDataset
(
CV_FILE_NAME
+
"0"
,
None
,
num_readers
,
shuffle
=
False
)
assert
data_set
.
get_dataset_size
()
==
10
idx
=
0
for
item
in
data_set
.
create_dict_iterator
():
assert
item
[
'label1'
]
==
item
[
'label1'
]
assert
item
[
'label2'
]
==
item
[
'label2'
]
assert
item
[
'label3'
]
==
item
[
'label3'
]
assert
item
[
'label4'
]
==
item
[
'label4'
]
idx
+=
1
assert
idx
==
10
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
if
__name__
==
'__main__'
:
test_nlp_compress_data
(
add_and_remove_nlp_compress_file
)
test_nlp_compress_data_old_version
(
add_and_remove_nlp_compress_file
)
test_cv_minddataset_writer_tutorial
()
test_cv_minddataset_partition_tutorial
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_num_samples_0
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_num_samples_1
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_num_samples_2
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_tutorial_check_shuffle_result
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_tutorial_check_whole_reshuffle_result_per_epoch
(
add_and_remove_cv_file
)
test_cv_minddataset_check_shuffle_result
(
add_and_remove_cv_file
)
test_cv_minddataset_dataset_size
(
add_and_remove_cv_file
)
test_cv_minddataset_repeat_reshuffle
(
add_and_remove_cv_file
)
test_cv_minddataset_batch_size_larger_than_records
(
add_and_remove_cv_file
)
test_cv_minddataset_issue_888
(
add_and_remove_cv_file
)
test_cv_minddataset_blockreader_tutorial
(
add_and_remove_cv_file
)
test_cv_minddataset_blockreader_some_field_not_in_index_tutorial
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_file_list
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_one_partition
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_two_dataset
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_two_dataset_partition
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_basic_tutorial
(
add_and_remove_cv_file
)
test_nlp_minddataset_reader_basic_tutorial
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_basic_tutorial_5_epoch
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_basic_tutorial_5_epoch_with_batch
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_no_columns
(
add_and_remove_cv_file
)
test_cv_minddataset_reader_repeat_tutorial
(
add_and_remove_cv_file
)
test_write_with_multi_bytes_and_array_and_read_by_MindDataset
()
test_write_with_multi_bytes_and_MindDataset
()
test_write_with_multi_array_and_MindDataset
()
test_numpy_generic
()
test_write_with_float32_float64_float32_array_float64_array_and_MindDataset
()
tests/ut/python/dataset/test_minddataset_exception.py
浏览文件 @
06ed9ffd
...
...
@@ -99,7 +99,12 @@ def test_invalid_mindrecord():
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
num_iter
==
0
except
Exception
as
error
:
os
.
remove
(
'dummy.mindrecord'
)
raise
error
else
:
os
.
remove
(
'dummy.mindrecord'
)
...
...
@@ -113,7 +118,12 @@ def test_minddataset_lack_db():
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
num_iter
==
0
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
raise
error
else
:
os
.
remove
(
CV_FILE_NAME
)
...
...
@@ -189,11 +199,17 @@ def test_minddataset_invalidate_num_shards():
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
'Input shard_id is not within the required interval of (0 to 0).'
in
str
(
error_info
.
value
)
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
raise
error
else
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
def
test_minddataset_invalidate_shard_id
():
create_cv_mindrecord
(
1
)
columns_list
=
[
"data"
,
"label"
]
...
...
@@ -203,7 +219,13 @@ def test_minddataset_invalidate_shard_id():
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
'Input shard_id is not within the required interval of (0 to 0).'
in
str
(
error_info
.
value
)
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
raise
error
else
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
...
...
@@ -217,17 +239,28 @@ def test_minddataset_shard_id_bigger_than_num_shard():
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
'Input shard_id is not within the required interval of (0 to 1).'
in
str
(
error_info
.
value
)
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
raise
error
with
pytest
.
raises
(
Exception
)
as
error_info
:
data_set
=
ds
.
MindDataset
(
CV_FILE_NAME
,
columns_list
,
num_readers
,
True
,
2
,
5
)
num_iter
=
0
for
_
in
data_set
.
create_dict_iterator
():
num_iter
+=
1
try
:
assert
'Input shard_id is not within the required interval of (0 to 1).'
in
str
(
error_info
.
value
)
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
raise
error
else
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
def
test_cv_minddataset_partition_num_samples_equals_0
():
"""tutorial for cv minddataset."""
...
...
@@ -245,7 +278,26 @@ def test_cv_minddataset_partition_num_samples_equals_0():
num_iter
+=
1
with
pytest
.
raises
(
Exception
)
as
error_info
:
partitions
(
5
)
try
:
assert
'num_samples should be a positive integer value, but got num_samples=0'
in
str
(
error_info
.
value
)
except
Exception
as
error
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
raise
error
else
:
os
.
remove
(
CV_FILE_NAME
)
os
.
remove
(
"{}.db"
.
format
(
CV_FILE_NAME
))
if
__name__
==
'__main__'
:
test_cv_lack_json
()
test_cv_lack_mindrecord
()
test_invalid_mindrecord
()
test_minddataset_lack_db
()
test_cv_minddataset_pk_sample_error_class_column
()
test_cv_minddataset_pk_sample_exclusive_shuffle
()
test_cv_minddataset_reader_different_schema
()
test_cv_minddataset_reader_different_page_size
()
test_minddataset_invalidate_num_shards
()
test_minddataset_invalidate_shard_id
()
test_minddataset_shard_id_bigger_than_num_shard
()
test_cv_minddataset_partition_num_samples_equals_0
()
tests/ut/python/dataset/test_minddataset_multi_images_and_ndarray.py
浏览文件 @
06ed9ffd
...
...
@@ -27,6 +27,7 @@ CV_FILE_NAME = "./complex.mindrecord"
def
test_cv_minddataset_reader_multi_image_and_ndarray_tutorial
():
try
:
writer
=
FileWriter
(
CV_FILE_NAME
,
FILES_NUM
)
cv_schema_json
=
{
"id"
:
{
"type"
:
"int32"
},
"image_0"
:
{
"type"
:
"bytes"
},
...
...
@@ -73,8 +74,17 @@ def test_cv_minddataset_reader_multi_image_and_ndarray_tutorial():
assert
item
[
"segments"
].
dtype
==
np
.
float32
num_iter
+=
1
assert
num_iter
==
5
except
Exception
as
error
:
if
os
.
path
.
exists
(
"{}"
.
format
(
CV_FILE_NAME
+
".db"
)):
os
.
remove
(
CV_FILE_NAME
+
".db"
)
if
os
.
path
.
exists
(
"{}"
.
format
(
CV_FILE_NAME
)):
os
.
remove
(
CV_FILE_NAME
)
raise
error
else
:
if
os
.
path
.
exists
(
"{}"
.
format
(
CV_FILE_NAME
+
".db"
)):
os
.
remove
(
CV_FILE_NAME
+
".db"
)
if
os
.
path
.
exists
(
"{}"
.
format
(
CV_FILE_NAME
)):
os
.
remove
(
CV_FILE_NAME
)
if
__name__
==
'__main__'
:
test_cv_minddataset_reader_multi_image_and_ndarray_tutorial
()
tests/ut/python/dataset/test_minddataset_padded.py
浏览文件 @
06ed9ffd
...
...
@@ -44,6 +44,7 @@ def add_and_remove_cv_file():
"""add/remove cv file"""
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
if
os
.
path
.
exists
(
"{}"
.
format
(
x
))
else
None
os
.
remove
(
"{}.db"
.
format
(
x
))
if
os
.
path
.
exists
(
...
...
@@ -59,6 +60,12 @@ def add_and_remove_cv_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_cv_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
...
...
@@ -69,6 +76,7 @@ def add_and_remove_nlp_file():
"""add/remove nlp file"""
paths
=
[
"{}{}"
.
format
(
NLP_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -92,6 +100,12 @@ def add_and_remove_nlp_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_nlp_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
...
...
@@ -636,3 +650,17 @@ def inputs(vectors, maxlen=50):
mask
=
[
1
]
*
length
+
[
0
]
*
(
maxlen
-
length
)
segment
=
[
0
]
*
maxlen
return
input_
,
mask
,
segment
if
__name__
==
'__main__'
:
test_cv_minddataset_reader_basic_padded_samples
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_multi_epoch
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_no_dividsible
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_dataset_size_no_divisible
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_no_equal_column_list
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_no_column_list
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_no_num_padded
(
add_and_remove_cv_file
)
test_cv_minddataset_partition_padded_samples_no_padded_samples
(
add_and_remove_cv_file
)
test_nlp_minddataset_reader_basic_padded_samples
(
add_and_remove_nlp_file
)
test_nlp_minddataset_reader_basic_padded_samples_multi_epoch
(
add_and_remove_nlp_file
)
test_nlp_minddataset_reader_basic_padded_samples_check_whole_reshuffle_result_per_epoch
(
add_and_remove_nlp_file
)
tests/ut/python/dataset/test_minddataset_sampler.py
浏览文件 @
06ed9ffd
...
...
@@ -34,6 +34,7 @@ def add_and_remove_cv_file():
"""add/remove cv file"""
paths
=
[
"{}{}"
.
format
(
CV_FILE_NAME
,
str
(
x
).
rjust
(
1
,
'0'
))
for
x
in
range
(
FILES_NUM
)]
try
:
for
x
in
paths
:
if
os
.
path
.
exists
(
"{}"
.
format
(
x
)):
os
.
remove
(
"{}"
.
format
(
x
))
...
...
@@ -50,10 +51,15 @@ def add_and_remove_cv_file():
writer
.
write_raw_data
(
data
)
writer
.
commit
()
yield
"yield_cv_data"
except
Exception
as
error
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
raise
error
else
:
for
x
in
paths
:
os
.
remove
(
"{}"
.
format
(
x
))
os
.
remove
(
"{}.db"
.
format
(
x
))
def
test_cv_minddataset_pk_sample_no_column
(
add_and_remove_cv_file
):
"""tutorial for cv minderdataset."""
...
...
@@ -626,3 +632,24 @@ def get_data(dir_name, sampler=False):
except
FileNotFoundError
:
continue
return
data_list
if
__name__
==
'__main__'
:
test_cv_minddataset_pk_sample_no_column
(
add_and_remove_cv_file
)
test_cv_minddataset_pk_sample_basic
(
add_and_remove_cv_file
)
test_cv_minddataset_pk_sample_shuffle
(
add_and_remove_cv_file
)
test_cv_minddataset_pk_sample_out_of_range
(
add_and_remove_cv_file
)
test_cv_minddataset_subset_random_sample_basic
(
add_and_remove_cv_file
)
test_cv_minddataset_subset_random_sample_replica
(
add_and_remove_cv_file
)
test_cv_minddataset_subset_random_sample_empty
(
add_and_remove_cv_file
)
test_cv_minddataset_subset_random_sample_out_of_range
(
add_and_remove_cv_file
)
test_cv_minddataset_subset_random_sample_negative
(
add_and_remove_cv_file
)
test_cv_minddataset_random_sampler_basic
(
add_and_remove_cv_file
)
test_cv_minddataset_random_sampler_repeat
(
add_and_remove_cv_file
)
test_cv_minddataset_random_sampler_replacement
(
add_and_remove_cv_file
)
test_cv_minddataset_sequential_sampler_basic
(
add_and_remove_cv_file
)
test_cv_minddataset_sequential_sampler_exceed_size
(
add_and_remove_cv_file
)
test_cv_minddataset_split_basic
(
add_and_remove_cv_file
)
test_cv_minddataset_split_exact_percent
(
add_and_remove_cv_file
)
test_cv_minddataset_split_fuzzy_percent
(
add_and_remove_cv_file
)
test_cv_minddataset_split_deterministic
(
add_and_remove_cv_file
)
test_cv_minddataset_split_sharding
(
add_and_remove_cv_file
)
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录