• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2019 Huawei Technologies Co., Ltd
2#
3# Licensed under the Apache License, Version 2.0 (the "License");
4# you may not use this file except in compliance with the License.
5# You may obtain a copy of the License at
6#
7# http://www.apache.org/licenses/LICENSE-2.0
8#
9# Unless required by applicable law or agreed to in writing, software
10# distributed under the License is distributed on an "AS IS" BASIS,
11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12# See the License for the specific language governing permissions and
13# limitations under the License.
14# ==============================================================================
15"""
16Testing CutOut op in DE
17"""
18import numpy as np
19
20import mindspore.dataset as ds
21import mindspore.dataset.transforms.py_transforms
22import mindspore.dataset.vision.c_transforms as c
23import mindspore.dataset.vision.py_transforms as f
24from mindspore import log as logger
25from util import visualize_image, visualize_list, diff_mse, save_and_check_md5, \
26    config_get_set_seed, config_get_set_num_parallel_workers
27
28DATA_DIR = ["../data/dataset/test_tf_file_3_images/train-0000-of-0001.data"]
29SCHEMA_DIR = "../data/dataset/test_tf_file_3_images/datasetSchema.json"
30
31GENERATE_GOLDEN = False
32
33
34def test_cut_out_op(plot=False):
35    """
36    Test Cutout
37    """
38    logger.info("test_cut_out")
39
40    # First dataset
41    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
42
43    transforms_1 = [
44        f.Decode(),
45        f.ToTensor(),
46        f.RandomErasing(value='random')
47    ]
48    transform_1 = mindspore.dataset.transforms.py_transforms.Compose(transforms_1)
49    data1 = data1.map(operations=transform_1, input_columns=["image"])
50
51    # Second dataset
52    data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
53    decode_op = c.Decode()
54    cut_out_op = c.CutOut(80)
55
56    transforms_2 = [
57        decode_op,
58        cut_out_op
59    ]
60
61    data2 = data2.map(operations=transforms_2, input_columns=["image"])
62
63    num_iter = 0
64    for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
65                            data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
66        num_iter += 1
67        image_1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
68        # C image doesn't require transpose
69        image_2 = item2["image"]
70
71        logger.info("shape of image_1: {}".format(image_1.shape))
72        logger.info("shape of image_2: {}".format(image_2.shape))
73
74        logger.info("dtype of image_1: {}".format(image_1.dtype))
75        logger.info("dtype of image_2: {}".format(image_2.dtype))
76
77        mse = diff_mse(image_1, image_2)
78        if plot:
79            visualize_image(image_1, image_2, mse)
80
81
82def test_cut_out_op_multicut(plot=False):
83    """
84    Test Cutout
85    """
86    logger.info("test_cut_out")
87
88    # First dataset
89    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
90
91    transforms_1 = [
92        f.Decode(),
93        f.ToTensor(),
94    ]
95    transform_1 = mindspore.dataset.transforms.py_transforms.Compose(transforms_1)
96    data1 = data1.map(operations=transform_1, input_columns=["image"])
97
98    # Second dataset
99    data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
100    decode_op = c.Decode()
101    cut_out_op = c.CutOut(80, num_patches=10)
102
103    transforms_2 = [
104        decode_op,
105        cut_out_op
106    ]
107
108    data2 = data2.map(operations=transforms_2, input_columns=["image"])
109
110    num_iter = 0
111    image_list_1, image_list_2 = [], []
112    for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
113                            data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
114        num_iter += 1
115        image_1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
116        # C image doesn't require transpose
117        image_2 = item2["image"]
118        image_list_1.append(image_1)
119        image_list_2.append(image_2)
120
121        logger.info("shape of image_1: {}".format(image_1.shape))
122        logger.info("shape of image_2: {}".format(image_2.shape))
123
124        logger.info("dtype of image_1: {}".format(image_1.dtype))
125        logger.info("dtype of image_2: {}".format(image_2.dtype))
126    if plot:
127        visualize_list(image_list_1, image_list_2)
128
129
130def test_cut_out_md5():
131    """
132    Test Cutout with md5 check
133    """
134    logger.info("test_cut_out_md5")
135    original_seed = config_get_set_seed(2)
136    original_num_parallel_workers = config_get_set_num_parallel_workers(1)
137
138    # First dataset
139    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
140    decode_op = c.Decode()
141    cut_out_op = c.CutOut(100)
142    data1 = data1.map(operations=decode_op, input_columns=["image"])
143    data1 = data1.map(operations=cut_out_op, input_columns=["image"])
144
145    data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
146    transforms = [
147        f.Decode(),
148        f.ToTensor(),
149        f.Cutout(100)
150    ]
151    transform = mindspore.dataset.transforms.py_transforms.Compose(transforms)
152    data2 = data2.map(operations=transform, input_columns=["image"])
153
154    # Compare with expected md5 from images
155    filename1 = "cut_out_01_c_result.npz"
156    save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
157    filename2 = "cut_out_01_py_result.npz"
158    save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN)
159
160    # Restore config
161    ds.config.set_seed(original_seed)
162    ds.config.set_num_parallel_workers(original_num_parallel_workers)
163
164
165def test_cut_out_comp(plot=False):
166    """
167    Test Cutout with c++ and python op comparison
168    """
169    logger.info("test_cut_out_comp")
170
171    # First dataset
172    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
173
174    transforms_1 = [
175        f.Decode(),
176        f.ToTensor(),
177        f.Cutout(200)
178    ]
179    transform_1 = mindspore.dataset.transforms.py_transforms.Compose(transforms_1)
180    data1 = data1.map(operations=transform_1, input_columns=["image"])
181
182    # Second dataset
183    data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
184
185    transforms_2 = [
186        c.Decode(),
187        c.CutOut(200)
188    ]
189
190    data2 = data2.map(operations=transforms_2, input_columns=["image"])
191
192    num_iter = 0
193    image_list_1, image_list_2 = [], []
194    for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
195                            data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
196        num_iter += 1
197        image_1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
198        # C image doesn't require transpose
199        image_2 = item2["image"]
200        image_list_1.append(image_1)
201        image_list_2.append(image_2)
202
203        logger.info("shape of image_1: {}".format(image_1.shape))
204        logger.info("shape of image_2: {}".format(image_2.shape))
205
206        logger.info("dtype of image_1: {}".format(image_1.dtype))
207        logger.info("dtype of image_2: {}".format(image_2.dtype))
208    if plot:
209        visualize_list(image_list_1, image_list_2, visualize_mode=2)
210
211
212if __name__ == "__main__":
213    test_cut_out_op(plot=True)
214    test_cut_out_op_multicut(plot=True)
215    test_cut_out_md5()
216    test_cut_out_comp(plot=True)
217