-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcode.py
240 lines (197 loc) · 9.15 KB
/
code.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
import os
import sys
import random
import warnings
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tqdm import tqdm
from itertools import chain
from skimage.io import imread, imshow, imread_collection, concatenate_images
from skimage.transform import resize
from skimage.morphology import label
from keras.models import Model, load_model
from keras.layers import Input
from keras.layers.core import Dropout, Lambda
from keras.layers.convolutional import Conv2D, Conv2DTranspose
from keras.layers.pooling import MaxPooling2D
from keras.layers.merge import concatenate
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras import backend as K
import tensorflow as tf
'''
------------------------------------------------------------------------------
set some parameters
------------------------------------------------------------------------------
'''
IMG_WIDTH = 256
IMG_HEIGHT = 256
IMG_CHANNELS = 3
TRAIN_PATH = '../stage1_train/'
TEST_PATH = '../stage1_test/'
warnings.filterwarnings('ignore', category=UserWarning, module='skimage')
seed = 42
random.seed = seed
np.random.seed = seed
'''
------------------------------------------------------------------------------
Reading train and test data
------------------------------------------------------------------------------
'''
# Get train and test IDs
train_ids = next(os.walk(TRAIN_PATH))[1]
test_ids = next(os.walk(TEST_PATH))[1]
# Get and resize train images and masks
X_train = np.zeros((len(train_ids), IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS), dtype=np.uint8)
Y_train = np.zeros((len(train_ids), IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)
print('Getting and resizing train images and masks ... ')
sys.stdout.flush()
for n, id_ in tqdm(enumerate(train_ids), total=len(train_ids)):
path = TRAIN_PATH + id_
img = imread(path + '/images/' + id_ + '.png')[:,:,:IMG_CHANNELS]
img = resize(img, (IMG_HEIGHT, IMG_WIDTH), mode='constant', preserve_range=True)
X_train[n] = img
mask = np.zeros((IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)
for mask_file in next(os.walk(path + '/masks/'))[2]:
mask_ = imread(path + '/masks/' + mask_file)
mask_ = np.expand_dims(resize(mask_, (IMG_HEIGHT, IMG_WIDTH), mode='constant',
preserve_range=True), axis=-1)
mask = np.maximum(mask, mask_)
Y_train[n] = mask
# Get and resize test images
X_test = np.zeros((len(test_ids), IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS), dtype=np.uint8)
sizes_test = []
print('Getting and resizing test images ... ')
sys.stdout.flush()
for n, id_ in tqdm(enumerate(test_ids), total=len(test_ids)):
path = TEST_PATH + id_
img = imread(path + '/images/' + id_ + '.png')[:,:,:IMG_CHANNELS]
sizes_test.append([img.shape[0], img.shape[1]])
img = resize(img, (IMG_HEIGHT, IMG_WIDTH), mode='constant', preserve_range=True)
X_test[n] = img
print('Done!')
'''
------------------------------------------------------------------------------
result metric
------------------------------------------------------------------------------
'''
# Define IoU metric
def mean_iou(y_true, y_pred):
prec = []
for t in np.arange(0.5, 1.0, 0.05):
y_pred_ = tf.to_int32(y_pred > t)
score, up_opt = tf.metrics.mean_iou(y_true, y_pred_, 2)
K.get_session().run(tf.local_variables_initializer())
with tf.control_dependencies([up_opt]):
score = tf.identity(score)
prec.append(score)
return K.mean(K.stack(prec), axis=0)
'''
------------------------------------------------------------------------------
Making network
------------------------------------------------------------------------------
'''
# Build U-Net model
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))
s = Lambda(lambda x: x / 255) (inputs)
baseLayerSize = 64
c1 = Conv2D(baseLayerSize, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (s)
c1 = Dropout(0.1) (c1)
c1 = Conv2D(baseLayerSize, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c1)
p1 = MaxPooling2D((2, 2)) (c1)
c2 = Conv2D(baseLayerSize*2, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p1)
c2 = Dropout(0.1) (c2)
c2 = Conv2D(baseLayerSize*2, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c2)
p2 = MaxPooling2D((2, 2)) (c2)
c3 = Conv2D(baseLayerSize*4, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p2)
c3 = Dropout(0.2) (c3)
c3 = Conv2D(baseLayerSize*4, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c3)
p3 = MaxPooling2D((2, 2)) (c3)
c4 = Conv2D(baseLayerSize*8, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p3)
c4 = Dropout(0.2) (c4)
c4 = Conv2D(baseLayerSize*8, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c4)
p4 = MaxPooling2D(pool_size=(2, 2)) (c4)
c5 = Conv2D(baseLayerSize*16, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p4)
c5 = Dropout(0.3) (c5)
c5 = Conv2D(baseLayerSize*16, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c5)
u6 = Conv2DTranspose(baseLayerSize*8, (2, 2), strides=(2, 2), padding='same') (c5)
u6 = concatenate([u6, c4])
c6 = Conv2D(baseLayerSize*8, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u6)
c6 = Dropout(0.2) (c6)
c6 = Conv2D(baseLayerSize*8, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c6)
u7 = Conv2DTranspose(baseLayerSize*4, (2, 2), strides=(2, 2), padding='same') (c6)
u7 = concatenate([u7, c3])
c7 = Conv2D(baseLayerSize*4, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u7)
c7 = Dropout(0.2) (c7)
c7 = Conv2D(baseLayerSize*4, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c7)
u8 = Conv2DTranspose(baseLayerSize*2, (2, 2), strides=(2, 2), padding='same') (c7)
u8 = concatenate([u8, c2])
c8 = Conv2D(baseLayerSize*2, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u8)
c8 = Dropout(0.1) (c8)
c8 = Conv2D(baseLayerSize*2, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c8)
u9 = Conv2DTranspose(baseLayerSize, (2, 2), strides=(2, 2), padding='same') (c8)
u9 = concatenate([u9, c1], axis=3)
c9 = Conv2D(baseLayerSize, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u9)
c9 = Dropout(0.1) (c9)
c9 = Conv2D(baseLayerSize, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c9)
outputs = Conv2D(1, (1, 1), activation='sigmoid') (c9)
model = Model(inputs=[inputs], outputs=[outputs])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=[mean_iou])
model.summary()
'''
------------------------------------------------------------------------------
Training
------------------------------------------------------------------------------
'''
# Fit model
earlystopper = EarlyStopping(patience=5, verbose=1)
checkpointer = ModelCheckpoint('model-dsbowl2018-1.h5', verbose=1, save_best_only=True)
results = model.fit(X_train, Y_train, validation_split=0.1, batch_size=16, epochs=50, callbacks=[earlystopper, checkpointer])
'''
------------------------------------------------------------------------------
prediction
------------------------------------------------------------------------------
'''
# Predict on train, val and test
model = load_model('model-dsbowl2018-1.h5', custom_objects={'mean_iou': mean_iou})
preds_train = model.predict(X_train[:int(X_train.shape[0]*0.9)], verbose=1)
preds_val = model.predict(X_train[int(X_train.shape[0]*0.9):], verbose=1)
preds_test = model.predict(X_test, verbose=1)
# Threshold predictions
preds_train_t = (preds_train > 0.5).astype(np.uint8)
preds_val_t = (preds_val > 0.5).astype(np.uint8)
preds_test_t = (preds_test > 0.5).astype(np.uint8)
# Create list of upsampled test masks
preds_test_upsampled = []
for i in range(len(preds_test)):
preds_test_upsampled.append(resize(np.squeeze(preds_test[i]), (sizes_test[i][0], sizes_test[i][1]), mode='constant', preserve_range=True))
'''
------------------------------------------------------------------------------
To be done on own
------------------------------------------------------------------------------
'''
# Run-length encoding stolen from https://www.kaggle.com/rakhlin/fast-run-length-encoding-python
def rle_encoding(x):
dots = np.where(x.T.flatten() == 1)[0]
run_lengths = []
prev = -2
for b in dots:
if (b>prev+1): run_lengths.extend((b + 1, 0))
run_lengths[-1] += 1
prev = b
return run_lengths
def prob_to_rles(x, cutoff=0.5):
lab_img = label(x > cutoff)
for i in range(1, lab_img.max() + 1):
yield rle_encoding(lab_img == i)
new_test_ids = []
rles = []
for n, id_ in enumerate(test_ids):
rle = list(prob_to_rles(preds_test_upsampled[n]))
rles.extend(rle)
new_test_ids.extend([id_] * len(rle))
# Create submission DataFrame
sub = pd.DataFrame()
sub['ImageId'] = new_test_ids
sub['EncodedPixels'] = pd.Series(rles).apply(lambda x: ' '.join(str(y) for y in x))
sub.to_csv('sub-dsbowl2018-1.csv', index=False)