-
Notifications
You must be signed in to change notification settings - Fork 6
/
oilseg_sgan.py
490 lines (397 loc) · 22 KB
/
oilseg_sgan.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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import cv2
import math
import time
import json
import random
import argparse
import collections
import numpy as np
import tensorflow as tf
from utils import append_index, load_examples, preprocess, deprocess, save_images, augment, create_generator_Unet
from utils import CROP_SIZE, conv, lrelu, batchnorm
from utils import discrim_loss_sgan, gen_loss_sgan
import time
from compare_results import calculate_accuracy, region_fitting_error
import pdb
parser = argparse.ArgumentParser()
parser.add_argument("--input_dir", default='Simulation/train', help="path to folder containing images")
parser.add_argument("--mode", default='train', choices=["train", "test", "export"])
parser.add_argument("--output_dir", default='test', help="where to put output files")
parser.add_argument("--seed", type=int)
parser.add_argument("--checkpoint", default=None,
help="directory with checkpoint to resume training from or use for testing")
parser.add_argument("--max_steps", type=int, help="number of training steps (0 to disable)")
parser.add_argument("--max_epochs", type=int, help="number of training epochs")
parser.add_argument("--summary_freq", type=int, default=100, help="update summaries every summary_freq steps")
parser.add_argument("--progress_freq", type=int, default=50, help="display progress every progress_freq steps")
parser.add_argument("--trace_freq", type=int, default=0, help="trace execution every trace_freq steps")
parser.add_argument("--display_freq", type=int, default=0,
help="write current training images every display_freq steps")
parser.add_argument("--save_freq", type=int, default=50, help="save model every save_freq steps, 0 to disable")
parser.add_argument("--test_freq", type=int, default=0, help="test model every test_freq steps, 0 to disable")
parser.add_argument("--aspect_ratio", type=float, default=1.0, help="aspect ratio of output images (width/height)")
parser.add_argument("--lab_colorization", action="store_true",
help="split input image into brightness (A) and color (B)")
parser.add_argument("--batch_size", type=int, default=1, help="number of images in batch")
parser.add_argument("--which_direction", type=str, default="AtoB", choices=["AtoB", "BtoA"])
parser.add_argument("--ngf", type=int, default=64, help="number of generator filters in first conv layer")
parser.add_argument("--ndf", type=int, default=64, help="number of discriminator filters in first conv layer")
parser.add_argument("--scale_size", type=int, default=286, help="scale images to this size before cropping to 256x256")
parser.add_argument("--flip", dest="flip", action="store_true", help="flip images horizontally")
parser.add_argument("--no_flip", dest="flip", action="store_false", help="don't flip images horizontally")
parser.set_defaults(flip=True)
parser.add_argument("--lr", type=float, default=0.0002, help="initial learning rate for adam")
parser.add_argument("--beta1", type=float, default=0.5, help="momentum term of adam")
parser.add_argument("--gan_weight", type=float, default=1.0, help="weight on GAN term for generator gradient")
parser.add_argument("--f_type", type=str, default='helinger', help="[f_type choices: [alt, rkl, kl, alpha] ]")
a = parser.parse_args()
EPS = 1e-12
Model = collections.namedtuple("Model", "outputs, predict_real, predict_fake, discrim_loss, discrim_grads_and_vars, "
"gen_loss, gen_loss_GAN, gen_grads_and_vars, train")
def create_model(inputs, targets):
def create_discriminator(discrim_inputs, discrim_targets):
n_layers = 3
layers = []
# 2x [batch, height, width, in_channels] => [batch, height, width, in_channels * 2]
input = tf.concat([discrim_inputs, discrim_targets], axis=3)
# layer_1: [batch, 256, 256, in_channels * 2] => [batch, 128, 128, ndf]
with tf.variable_scope("layer_1"):
convolved = conv(input, a.ndf, stride=2)
rectified = lrelu(convolved, 0.2)
layers.append(rectified)
# layer_2: [batch, 128, 128, ndf] => [batch, 64, 64, ndf * 2]
# layer_3: [batch, 64, 64, ndf * 2] => [batch, 32, 32, ndf * 4]
# layer_4: [batch, 32, 32, ndf * 4] => [batch, 31, 31, ndf * 8]
for i in range(n_layers):
with tf.variable_scope("layer_%d" % (len(layers) + 1)):
out_channels = a.ndf * min(2 ** (i + 1), 8)
stride = 1 if i == n_layers - 1 else 2 # last layer here has stride 1
convolved = conv(layers[-1], out_channels, stride=stride)
normalized = batchnorm(convolved) # BN
rectified = lrelu(normalized, 0.2)
# rectified = lrelu(convolved, 0.2)#no BN
layers.append(rectified)
# layer_5: [batch, 31, 31, ndf * 8] => [batch, 30, 30, 1]
with tf.variable_scope("layer_%d" % (len(layers) + 1)):
convolved = conv(rectified, out_channels=1, stride=1)
#output = tf.sigmoid(convolved)
#output = convolved# ossgan # not work for most f-divergence except for Total Variation and Pearson
output = tf.tanh(convolved) # it works
#output = tf.nn.relu(convolved)
layers.append(output)
return layers[-1]
with tf.variable_scope("generator") as scope:
out_channels = int(targets.get_shape()[-1])
outputs = create_generator_Unet(a, inputs, out_channels)
# create two copies of discriminator, one for real pairs and one for fake pairs
# they share the same underlying variables
with tf.name_scope("real_discriminator"):
with tf.variable_scope("discriminator"):
# 2x [batch, height, width, channels] => [batch, 30, 30, 1]
predict_real = create_discriminator(inputs, targets)
with tf.name_scope("fake_discriminator"):
with tf.variable_scope("discriminator", reuse=True):
# 2x [batch, height, width, channels] => [batch, 30, 30, 1]
predict_fake = create_discriminator(inputs, outputs)
with tf.name_scope("discriminator_loss"):
discrim_loss = discrim_loss_sgan((predict_real + EPS), (predict_fake+EPS), a)
with tf.name_scope("generator_loss"):
# predict_fake => 1
# abs(targets - outputs) => 0
size_image=256
tv_y_size = size_image
tv_x_size = size_image
gen_loss_GAN = gen_loss_sgan(tf.abs(targets-outputs),a)
gen_loss = gen_loss_GAN * a.gan_weight
with tf.name_scope("discriminator_train"):
discrim_tvars = [var for var in tf.trainable_variables() if var.name.startswith("discriminator")]
discrim_optim = tf.train.AdamOptimizer(a.lr, a.beta1)
discrim_grads_and_vars = discrim_optim.compute_gradients(discrim_loss, var_list=discrim_tvars)
discrim_train = discrim_optim.apply_gradients(discrim_grads_and_vars)
with tf.name_scope("generator_train"):
with tf.control_dependencies([discrim_train]):
gen_tvars = [var for var in tf.trainable_variables() if var.name.startswith("generator")]
gen_optim = tf.train.AdamOptimizer(a.lr, a.beta1)
gen_grads_and_vars = gen_optim.compute_gradients(gen_loss, var_list=gen_tvars)
gen_train = gen_optim.apply_gradients(gen_grads_and_vars)
ema = tf.train.ExponentialMovingAverage(decay=0.99)
update_losses = ema.apply(
[discrim_loss, gen_loss, gen_loss_GAN ])
global_step = tf.contrib.framework.get_or_create_global_step()
incr_global_step = tf.assign(global_step, global_step + 1)
return Model(
predict_real=predict_real,
predict_fake=predict_fake,
discrim_loss=ema.average(discrim_loss),
discrim_grads_and_vars=discrim_grads_and_vars,
gen_loss=ema.average(gen_loss),
gen_loss_GAN=ema.average(gen_loss_GAN),
gen_grads_and_vars=gen_grads_and_vars,
outputs=outputs,
train=tf.group(update_losses, incr_global_step, gen_train),
)
def main():
if tf.__version__ != "1.0.0":
raise Exception("Tensorflow version 1.0.0 required")
if a.seed is None:
a.seed = random.randint(0, 2 ** 31 - 1)
tf.set_random_seed(a.seed)
np.random.seed(a.seed)
random.seed(a.seed)
if not os.path.exists(a.output_dir):
os.makedirs(a.output_dir)
if a.mode == "test" or a.mode == "export":
if a.checkpoint is None:
raise Exception("checkpoint required for test mode")
# load some options from the checkpoint
options = {"which_direction", "ngf", "ndf", "lab_colorization"}
with open(os.path.join(a.checkpoint, "options.json")) as f:
for key, val in json.loads(f.read()).items():
if key in options:
print("loaded", key, "=", val)
setattr(a, key, val)
# disable these features in test mode
a.scale_size = CROP_SIZE
a.flip = False
for k, v in a._get_kwargs():
print(k, "=", v)
with open(os.path.join(a.output_dir, "options.json"), "w") as f:
f.write(json.dumps(vars(a), sort_keys=True, indent=4))
if a.mode == "export":
# export the generator to a meta graph that can be imported later for standalone generation
if a.lab_colorization:
raise Exception("export not supported for lab_colorization")
input = tf.placeholder(tf.string, shape=[1])
input_data = tf.decode_base64(input[0])
input_image = tf.image.decode_png(input_data)
# remove alpha channel if present
input_image = input_image[:, :, :3]
input_image = tf.image.convert_image_dtype(input_image, dtype=tf.float32)
input_image.set_shape([CROP_SIZE, CROP_SIZE, 3])
batch_input = tf.expand_dims(input_image, axis=0)
with tf.variable_scope("generator") as scope:
batch_output = deprocess(create_generator_Unet(a, preprocess(batch_input), 3))
output_image = tf.image.convert_image_dtype(batch_output, dtype=tf.uint8)[0]
output_data = tf.image.encode_png(output_image)
output = tf.convert_to_tensor([tf.encode_base64(output_data)])
key = tf.placeholder(tf.string, shape=[1])
inputs = {
"key": key.name,
"input": input.name
}
tf.add_to_collection("inputs", json.dumps(inputs))
outputs = {
"key": tf.identity(key).name,
"output": output.name,
}
tf.add_to_collection("outputs", json.dumps(outputs))
init_op = tf.global_variables_initializer()
restore_saver = tf.train.Saver()
export_saver = tf.train.Saver()
# config = tf.ConfigProto()
# config.allow_soft_placement = False
# config.log_device_placement = True
# config.gpu_options.allow_growth = True
# config.gpu_options.per_process_gpu_memory_fraction = 0.4
with tf.Session() as sess:
sess.run(init_op)
print("loading model from checkpoint")
checkpoint = tf.train.latest_checkpoint(a.checkpoint)
restore_saver.restore(sess, checkpoint)
print("exporting model")
export_saver.export_meta_graph(filename=os.path.join(a.output_dir, "export.meta"))
export_saver.save(sess, os.path.join(a.output_dir, "export"), write_meta_graph=False)
return
examples = load_examples(a)
print("examples count = %d" % examples.count)
# inputs and targets are [batch_size, height, width, channels]
model = create_model(examples.inputs, examples.targets)
# undo colorization splitting on images that we use for display/output
if a.lab_colorization:
if a.which_direction == "AtoB":
# inputs is brightness, this will be handled fine as a grayscale image
# need to augment targets and outputs with brightness
targets = augment(examples.targets, examples.inputs)
outputs = augment(model.outputs, examples.inputs)
# inputs can be deprocessed normally and handled as if they are single channel
# grayscale images
inputs = deprocess(examples.inputs)
elif a.which_direction == "BtoA":
# inputs will be color channels only, get brightness from targets
inputs = augment(examples.inputs, examples.targets)
targets = deprocess(examples.targets)
outputs = deprocess(model.outputs)
else:
raise Exception("invalid direction")
else:
inputs = deprocess(examples.inputs)
targets = deprocess(examples.targets)
outputs = deprocess(model.outputs)
def convert(image):
if a.aspect_ratio != 1.0:
# upscale to correct aspect ratio
size = [CROP_SIZE, int(round(CROP_SIZE * a.aspect_ratio))]
image = tf.image.resize_images(image, size=size, method=tf.image.ResizeMethod.BICUBIC)
return tf.image.convert_image_dtype(image, dtype=tf.uint8, saturate=True)
# reverse any processing on images so they can be written to disk or displayed to user
with tf.name_scope("convert_inputs"):
converted_inputs = convert(inputs)
with tf.name_scope("convert_targets"):
converted_targets = convert(targets)
with tf.name_scope("convert_outputs"):
converted_outputs = convert(outputs)
with tf.name_scope("encode_images"):
display_fetches = {
"paths": examples.paths,
"inputs": tf.map_fn(tf.image.encode_png, converted_inputs, dtype=tf.string, name="input_pngs"),
"targets": tf.map_fn(tf.image.encode_png, converted_targets, dtype=tf.string, name="target_pngs"),
"outputs": tf.map_fn(tf.image.encode_png, converted_outputs, dtype=tf.string, name="output_pngs"),
}
# summaries
with tf.name_scope("inputs_summary"):
tf.summary.image("inputs", converted_inputs)
with tf.name_scope("targets_summary"):
tf.summary.image("targets", converted_targets)
with tf.name_scope("outputs_summary"):
tf.summary.image("outputs", converted_outputs)
with tf.name_scope("predict_real_summary"):
tf.summary.image("predict_real", tf.image.convert_image_dtype(model.predict_real, dtype=tf.uint8))
with tf.name_scope("predict_fake_summary"):
tf.summary.image("predict_fake", tf.image.convert_image_dtype(model.predict_fake, dtype=tf.uint8))
tf.summary.scalar("discriminator_loss", model.discrim_loss)
tf.summary.scalar("gennerator_loss", model.gen_loss)
tf.summary.scalar("generator_loss_GAN", model.gen_loss_GAN)
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name + "/values", var)
for grad, var in model.discrim_grads_and_vars + model.gen_grads_and_vars:
tf.summary.histogram(var.op.name + "/gradients", grad)
with tf.name_scope("parameter_count"):
parameter_count = tf.reduce_sum([tf.reduce_prod(tf.shape(v)) for v in tf.trainable_variables()])
saver = tf.train.Saver(max_to_keep=1)
logdir = a.output_dir if (a.trace_freq > 0 or a.summary_freq > 0) else None
sv = tf.train.Supervisor(logdir=logdir, save_summaries_secs=0, saver=None)
with sv.managed_session() as sess:
print("parameter_count =", sess.run(parameter_count))
if a.checkpoint is not None:
print("loading model from checkpoint")
checkpoint = tf.train.latest_checkpoint(a.checkpoint)
saver.restore(sess, checkpoint)
max_steps = 2 ** 32
if a.max_epochs is not None:
max_steps = examples.steps_per_epoch * a.max_epochs
if a.max_steps is not None:
max_steps = a.max_steps
if a.mode == "test":
# testing
# at most, process the test data once
test_start = time.time()
max_steps = min(examples.steps_per_epoch, max_steps)
for step in range(max_steps):
results = sess.run(display_fetches)
filesets = save_images(a, results)
for i, f in enumerate(filesets):
print("evaluated image", f["name"])
index_path = append_index(a, filesets)
with open(a.output_dir + '/test.time', 'w') as f:
f.write(str(time.time() - test_start)+'\n')
print("wrote index at", index_path)
else:
# training
start = time.time()
with open(a.output_dir + '/train.precession', 'a') as f:
f.write('step RFE ACC \n')
for step in range(max_steps):
def should(freq):
return freq > 0 and ((step + 1) % freq == 0 or step == max_steps - 1)
options = None
run_metadata = None
if should(a.trace_freq):
options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
fetches = {
"train": model.train,
"global_step": sv.global_step,
}
if should(a.progress_freq):
fetches["discrim_loss"] = model.discrim_loss
fetches["gen_loss"] = model.gen_loss
fetches["gen_loss_GAN"] = model.gen_loss_GAN
if should(a.summary_freq):
fetches["summary"] = sv.summary_op
if should(a.display_freq):
fetches["display"] = display_fetches
results = sess.run(fetches, options=options, run_metadata=run_metadata)
if should(a.summary_freq):
print("recording summary")
sv.summary_writer.add_summary(results["summary"], results["global_step"])
if should(a.display_freq):
print("saving display images")
filesets = save_images(a, results["display"], step=results["global_step"])
append_index(a, filesets, step=True)
if should(a.trace_freq):
print("recording trace")
sv.summary_writer.add_run_metadata(run_metadata, "step_%d" % results["global_step"])
if should(a.progress_freq):
# global_step will have the correct step count if we resume from a checkpoint
train_epoch = math.ceil(results["global_step"] / examples.steps_per_epoch)
train_step = (results["global_step"] - 1) % examples.steps_per_epoch + 1
rate = (step + 1) * a.batch_size / (time.time() - start)
remaining = (max_steps - step) * a.batch_size / rate
print("progress epoch %d step %d image/sec %0.1f remaining %dm" % (
train_epoch, train_step, rate, remaining / 60))
print("discrim_loss", results["discrim_loss"])
print("gen_loss", results["gen_loss"])
print("gen_loss_GAN", results["gen_loss_GAN"])
#with open(a.output_dir + '/train.log', 'a') as f:
# f.write('step gen_loss discrim_loss')
if should(a.save_freq):
print("saving model")
saver.save(sess, os.path.join(a.output_dir, "model"), global_step=sv.global_step)
line_str = '%s %s %s\n' % (results["global_step"], results["gen_loss"], results["discrim_loss"])
with open(a.output_dir + '/train.log', 'a') as f:
f.write(line_str)
if should(a.test_freq):
if a.output_dir is None:
raise Exception("checkpoint required for test mode")
# load some options from the checkpoint
options = {"which_direction", "ngf", "ndf", "lab_colorization"}
with open(os.path.join(a.output_dir, "options.json")) as f:
for key, val in json.loads(f.read()).items():
if key in options:
print("loaded", key, "=", val)
setattr(a, key, val)
# disable these features in test mode
a.scale_size = CROP_SIZE
a.flip = False
# testing
# at most, process the test data once
max_steps = min(examples.steps_per_epoch, max_steps)
for step in range(max_steps):
test_results = sess.run(display_fetches)
test_filesets = save_images(a, test_results, step=results["global_step"])
index_path = append_index(a, test_filesets)
if 'ThreeObj_gamma_1.0' in test_filesets[0]['outputs']:
#pdb.set_trace()
print('file','checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'%(a.lr,a.f_type,test_filesets[0]['outputs']))
outp = cv2.imread('checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'%(a.lr,a.f_type,test_filesets[0]['outputs']))
targ = cv2.imread('checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s' % (
a.lr, a.f_type, test_filesets[0]['targets']))
inp = cv2.imread('checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s' % (
a.lr, a.f_type, test_filesets[0]['inputs']))
rfe = region_fitting_error(outp,targ)
acc = calculate_accuracy(inp,outp,targ)
#print('region fitting error', rfe)
#print('accuracy', acc)
line_str = '%s %s %s\n' % (results["global_step"], rfe, acc)
with open(a.output_dir + '/train.precession', 'a') as f:
f.write(line_str)
print("wrote index at", index_path)
if sv.should_stop():
break
with open(a.output_dir + '/train.time', 'w') as f:
f.write(str(time.time() - start)+'\n')
main()