forked from dennispark0/CS557-Artificial-Intelligence-
/
main.py
502 lines (346 loc) · 16 KB
/
main.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
491
492
493
494
495
496
497
498
499
500
501
502
########################################################################
#
# This file is part of the TensorFlow Tutorials available at:
#
# https://github.com/Hvass-Labs/TensorFlow-Tutorials
#
# Published under the MIT License. See the file LICENSE for details.
#
# Copyright 2016 by Magnus Erik Hvass Pedersen
#
########################################################################
from IPython.display import Image
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
print(tf.__version__)
#from sklearn.metrics import confusion_matrix
import time
from datetime import timedelta
import math
import os
# Use PrettyTensor to simplify Neural Network construction.
import prettytensor as pt
import cifar10
cifar10.maybe_download_and_extract()
class_names = cifar10.load_class_names()
print(class_names)
images_train, cls_train, labels_train = cifar10.load_training_data()
images_test, cls_test, labels_test = cifar10.load_test_data()
#print("Size of:")
#print("- Training-set:\t\t{}".format(len(images_train)))
#print("- Test-set:\t\t{}".format(len(images_test)))
from cifar10 import img_size, num_channels, num_classes
#we are going to crop and randomly offset the image in training (but recenter them for the TESTING)
img_size_cropped = 24
def plot_images(images, cls_true, cls_pred=None, smooth=True):
assert len(images) == len(cls_true) == 9
# Create figure with sub-plots.
fig, axes = plt.subplots(3, 3)
# Adjust vertical spacing if we need to print ensemble and best-net.
if cls_pred is None:
hspace = 0.3
else:
hspace = 0.6
fig.subplots_adjust(hspace=hspace, wspace=0.3)
for i, ax in enumerate(axes.flat):
# Interpolation type.
if smooth:
interpolation = 'spline16'
else:
interpolation = 'nearest'
# Plot image.
ax.imshow(images[i, :, :, :],
interpolation=interpolation)
# Name of the true class.
cls_true_name = class_names[cls_true[i]]
# Show true and predicted classes.
if cls_pred is None:
xlabel = "True: {0}".format(cls_true_name)
else:
# Name of the predicted class.
cls_pred_name = class_names[cls_pred[i]]
xlabel = "Answer: {0}\nError: {1}".format(cls_true_name, cls_pred_name)
# Show the classes as the label on the x-axis.
ax.set_xlabel(xlabel)
# Remove ticks from the plot.
ax.set_xticks([])
ax.set_yticks([])
# Ensure the plot is shown correctly with multiple plots
# in a single Notebook cell.
plt.show()
images = images_test[0:9]
# Get the true classes for those images.
cls_true = cls_test[0:9]
# Plot the images and labels using our helper-function above.
#plot_images(images=images, cls_true=cls_true, smooth=False)
#(images=images, cls_true=cls_true, smooth=True)
x = tf.placeholder(tf.float32, shape=[None, img_size, img_size, num_channels], name='x')
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
def pre_process_image(image, training):
# This function takes a single image as input,
# and a boolean whether to build the training or testing graph.
if training:
#various distortions for the training layers
# Randomly crop the input image (this is where img_size_cropped is used)
image = tf.random_crop(image, size=[img_size_cropped, img_size_cropped, num_channels])
# Randomly flip the image horizontally.
image = tf.image.random_flip_left_right(image)
# Randomly adjust hue, contrast and saturation.
image = tf.image.random_hue(image, max_delta=0.05)
image = tf.image.random_contrast(image, lower=0.3, upper=1.0)
image = tf.image.random_brightness(image, max_delta=0.2)
image = tf.image.random_saturation(image, lower=0.0, upper=2.0)
# Some of these functions may overflow and result in pixel
# values beyond the [0, 1] range. It is unclear from the
# documentation of TensorFlow 0.10.0rc0 whether this is
# intended. A simple solution is to limit the range.
# Limit the image pixels between [0, 1] in case of overflow.
image = tf.minimum(image, 1.0)
image = tf.maximum(image, 0.0)
else:
# For training, add the following to the TensorFlow graph.
# Crop the input image around the centre so it is the same
# size as images that are randomly cropped during training.
image = tf.image.resize_image_with_crop_or_pad(image,
target_height=img_size_cropped,
target_width=img_size_cropped)
return image
def pre_process(images, training):
# Use TensorFlow to loop over all the input images and call
# the function above which takes a single image as input.
images = tf.map_fn(lambda image: pre_process_image(image, training), images)
return images
distorted_images = pre_process(images=x, training=True)
def main_network(images, training):
# Wrap the input images as a Pretty Tensor object.
x_pretty = pt.wrap(images)
# Pretty Tensor uses special numbers to distinguish between
# the training and testing phases.
if training:
phase = pt.Phase.train
else:
phase = pt.Phase.infer
# CNN using Pretty Tensor.
#we can now quickly chain any number of layers to define neural networks
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=phase):
y_pred, loss = x_pretty.\
conv2d(kernel=5, depth=64, name='layer_conv1', batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name='layer_conv2').\
max_pool(kernel=2, stride=2).\
flatten().\
fully_connected(size=256, name='layer_fc1').\
fully_connected(size=128, name='layer_fc2').\
softmax_classifier(num_classes=num_classes, labels=y_true)
return y_pred, loss
#get fully connected layers from the flattened convluted layers
def create_network(training):
# Wrap the neural network in the scope named 'network'.
# Create new variables during training, and re-use during testing.
with tf.variable_scope('network', reuse=not training):
# Just rename the input placeholder variable for convenience.
images = x
# Create TensorFlow graph for pre-processing.
images = pre_process(images=images, training=training)
# Create TensorFlow graph for the main processing.
y_pred, loss = main_network(images=images, training=training)
return y_pred, loss
global_step = tf.Variable(initial_value=0,
name='global_step', trainable=False)
_, loss = create_network(training=True)
#set the learning rate-- 0.0001 served me well very well for a while but I needed to lower it later
lr = 1e-4
print(global_step)
#use Adam's algorithm to minimize loss
optimizer = tf.train.AdamOptimizer(learning_rate=0.00003).minimize(loss, global_step=global_step)
y_pred, _ = create_network(training=False)
y_pred_cls = tf.argmax(y_pred, dimension=1)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver()
def get_weights_variable(layer_name):
with tf.variable_scope("network/" + layer_name, reuse=True):
variable = tf.get_variable('weights')
return variable
weights_conv1 = get_weights_variable(layer_name='layer_conv1')
weights_conv2 = get_weights_variable(layer_name='layer_conv2')
def get_layer_output(layer_name):
# The name of the last operation of the convolutional layer.
# This assumes you are using Relu as the activation-function.
tensor_name = "network/" + layer_name + "/Relu:0"
# Get the tensor with this name.
tensor = tf.get_default_graph().get_tensor_by_name(tensor_name)
return tensor
output_conv1 = get_layer_output(layer_name='layer_conv1')
output_conv2 = get_layer_output(layer_name='layer_conv2')
session = tf.Session()
save_dir = 'checkpoints/'
#WARNING: deleting the latest testing files will leave us searching for it anyways.
#To revert to an earlier training sess, rename that session to the latest one and replace the active one
if not os.path.exists(save_dir):
os.makedirs(save_dir)
save_path = os.path.join(save_dir, 'cifar10_cnn')
try:
print("Looking for checkpoint ...")
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=save_dir)
# Try and load the data in the checkpoint.
saver.restore(session, save_path=last_chk_path)
print("Restored checkpoint from:", last_chk_path)
except:
print("No checkpoint found. Initializing Tensorflow graph variables.")
session.run(tf.global_variables_initializer())
#this is a batch size I found comfy on my PC. smaller sizes will require more iterations to train
train_batch_size = 64
def random_batch():
# Number of images in the training-set.
num_images = len(images_train)
# Create a random index.
idx = np.random.choice(num_images,
size=train_batch_size,
replace=False)
# Use the random index to select random images and labels.
x_batch = images_train[idx, :, :, :]
y_batch = labels_train[idx, :]
return x_batch, y_batch
def optimize(num_iterations):
# Start-time used for printing time-usage below.
start_time = time.time()
for i in range(num_iterations):
# Get a batch of training examples.
# x_batch now holds a batch of images and
# y_true_batch are the true labels for those images.
x_batch, y_true_batch = random_batch()
# Put the batch into a dict with the proper names
# for placeholder variables in the TensorFlow graph.
feed_dict_train = {x: x_batch,
y_true: y_true_batch}
# Run the optimizer using this batch of training data.
# TensorFlow assigns the variables in feed_dict_train
# to the placeholder variables and then runs the optimizer.
# We also want to retrieve the global_step counter.
i_global, _ = session.run([global_step, optimizer],
feed_dict=feed_dict_train)
# Print status to screen every 100 iterations (and last).
if (i_global % 100 == 0) or (i == num_iterations - 1):
# Calculate the accuracy on the training-batch.
batch_acc = session.run(accuracy,
feed_dict=feed_dict_train)
# Print status.
msg = "Global Step: {0:>6}, Training Batch Accuracy: {1:>6.1%}"
print(msg.format(i_global, batch_acc))
#if this gets annoying, increase the % value or remove the clause altogether
if (i_global % 1000 == 0) or (i == num_iterations - 1):
# Save all variables of the TensorFlow graph to an iteratively named file
saver.save(session,
save_path=save_path,
global_step=global_step)
print("Saved checkpoint.")
# Ending time.
end_time = time.time()
# Difference between start and end-times.
time_dif = end_time - start_time
# Print the time-usage.
print("Time usage: " + str(timedelta(seconds=int(round(time_dif)))))
def plot_example_errors(cls_pred, correct):
# This function is called from print_test_accuracy() below.
# cls_pred is an array of the predicted class-number for
# all images in the test-set.
# correct is a boolean array whether the predicted class
# is equal to the true class for each image in the test-set.
# Negate the boolean array.
incorrect = (correct==False)
# Get the images from the test-set that have been
# incorrectly classified.
images = images_test[incorrect]
# Get the predicted classes for those images.
cls_pred = cls_pred[incorrect]
# Get the true classes for those images.
cls_true = cls_test[incorrect]
# Plot the first 9 images.
plot_images(images=images[0:9],
cls_true=cls_true[0:9],
cls_pred=cls_pred[0:9])
# Split the data-set in batches of this size to limit RAM usage.
#LOWER THIS IF ENCOUNTERING ISSUES
batch_size = 256
def predict_cls(images, labels, cls_true):
# Number of images.
num_images = len(images)
# Allocate an array for the predicted classes which
# will be calculated in batches and filled into this array.
cls_pred = np.zeros(shape=num_images, dtype=np.int)
# Now calculate the predicted classes for the batches.
# We will just iterate through all the batches.
# The starting index for the next batch is denoted i.
i = 0
while i < num_images:
# The ending index for the next batch is denoted j.
j = min(i + batch_size, num_images)
# Create a feed-dict with the images and labels
# between index i and j.
feed_dict = {x: images[i:j, :],
y_true: labels[i:j, :]}
# Calculate the predicted class using TensorFlow.
cls_pred[i:j] = session.run(y_pred_cls, feed_dict=feed_dict)
# Set the start-index for the next batch to the
# end-index of the current batch.
i = j
# Create a boolean array whether each image is correctly classified.
correct = (cls_true == cls_pred)
return correct, cls_pred
def predict_cls_test():
return predict_cls(images = images_test,
labels = labels_test,
cls_true = cls_test)
def classification_accuracy(correct):
# When averaging a boolean array, False means 0 and True means 1.
# So we are calculating: number of True / len(correct) which is
# the same as the classification accuracy.
# Return the classification accuracy
# and the number of correct classifications.
return correct.mean(), correct.sum()
def print_test_accuracy(show_example_errors=False,
show_confusion_matrix=False):
# For all the images in the test-set,
# calculate the predicted classes and whether they are correct.
correct, cls_pred = predict_cls_test()
# Classification accuracy and the number of correct classifications.
acc, num_correct = classification_accuracy(correct)
# Number of images being classified.
num_images = len(correct)
# Print the accuracy.
msg = "Accuracy on Test-Set: {0:.1%} ({1} / {2})"
print(msg.format(acc, num_correct, num_images))
# Plot some examples of mis-classifications, if desired.
if show_example_errors:
print("Example errors:")
plot_example_errors(cls_pred=cls_pred, correct=correct)
#could not get this to work
# if show_confusion_matrix:
# print("Confusion Matrix:")
# plot_confusion_matrix(cls_pred=cls_pred)
def get_test_image(i):
return images_test[i, :, :, :], cls_test[i]
img, cls = get_test_image(16)
#run 1000 iterations at a time, takes us roughly 8 mins
optimize(num_iterations=2000)
print_test_accuracy(show_example_errors=True,
show_confusion_matrix=False)
#a method for plotting images
def plot_image(image):
# Create figure with sub-plots.
fig, axes = plt.subplots(1, 2)
# References to the sub-plots.
ax0 = axes.flat[0]
ax1 = axes.flat[1]
# Show raw and smoothened images in sub-plots.
ax0.imshow(image, interpolation='nearest')
ax1.imshow(image, interpolation='spline16')
# Set labels.
ax0.set_xlabel('Raw')
ax1.set_xlabel('Smooth')
# Ensure the plot is shown correctly with multiple plots
# in a single Notebook cell.
plt.show()