def main():
config = Config()
modeler = model.VGG(config)
# read data to train("data/train")
train_reader = read_data.VGGReader(config)
modeler.inference()
loss = modeler.loss
train_op = modeler.train_op(loss)
init = tf.global_variables_initializer()
saver = tf.train.Saver(max_to_keep=100)
sess_config = tf.ConfigProto()
sess_config.gpu_options.allow_growth = True
with tf.Session(config=sess_config) as sess:
sess.run(init)
#saver.restore(sess, config.param_dir + config.load_filename)
#print "restore params" + config.steps
merged = tf.summary.merge_all()
logdir = os.path.join(config.log_dir,
datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
train_writer = tf.summary.FileWriter(logdir, sess.graph)
#start training
print 'start training'
for step in range(config.max_step):
#start_time = time.time()
with tf.device('/cpu:0'):
images_train, labels_train, filesname_train = train_reader.get_random_batch(
True)
feed_dict = {
modeler.image_holder: images_train,
modeler.label_holder: labels_train,
modeler.is_train: True
}
with tf.device('/gpu:0'):
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
with tf.device('/cpu:0'):
if (step + 1) % config.checkpointer_iter == 0:
modeler.save_npy(
sess, config.param_dir + config.save_filename +
str(modeler.global_step.eval()) + '.npy')
if (step + 1) % config.summary_iter == 0:
summary = sess.run(merged, feed_dict=feed_dict)
train_writer.add_summary(summary,
modeler.global_step.eval())
if step % 10 == 0:
print 'step %d, loss = %.3f' % (step, loss_value)
def main():
config = Config()
#modeler = model.VGG(config)
modeler = model.VGG16(include_top=False)
#modeler = model.ResNet50(include_top=False, weights='imagenet', input_shape=[config.img_height,config.img_width, 3], pooling='max')
inputs = Input(shape=[config.img_height,config.img_width,3])
y = modeler(inputs)
# fine tune the model
'''
y = Dense(config.type_size, activation='softmax', name='fc17')(y)
modeler = Model(inputs, y, name='resnet50')
'''
y = Flatten()(y)
y = Dense(4096, activation='relu', name='fc1')(y)
y = Dense(4096, activation='relu', name='fc2')(y)
y = Dense(config.type_size, activation='softmax', name='predictions')(y)
modeler = Model(inputs, y, name='vgg16')
print "restore params" + str(config.restore_steps)
modeler.load_weights(config.params_dir + config.net_name + "-weather-params-" + str(config.restore_steps) + ".h5")
modeler.compile(loss='categorical_crossentropy', optimizer=SGD(lr=config.learning_rate, momentum=0.9,nesterov=True))
# read data to train("data/train")
train_reader = read_data.VGGReader(config)
init = tf.global_variables_initializer()
sess_config = tf.ConfigProto()
sess_config.gpu_options.allow_growth = True
with tf.Session(config=sess_config) as sess:
sess.run(init)
print 'start training'
for step in range(config.max_step):
with tf.device('/cpu:0'):
images_train, labels_train, filesname_train = train_reader.get_random_batch(False)
#images_train = preprocess_input(images_train)
if step == 0:
print "images_train[0]: ", images_train[0]
modeler.train_on_batch(images_train, labels_train)
loss_value = modeler.test_on_batch(images_train, labels_train)
if step%10 == 0:
print 'step %d, loss = %.3f' % (step, loss_value)
#print prediction
if (step+1) % config.save_iter == 0:
# save weights
modeler.save_weights(config.params_dir + config.net_name + "-weather-params-" + str(step+1+config.restore_steps) + ".h5")
pre = modeler.predict(images_train)
for i in range(config.batch_size):
print labels_train[i]
print pre[i]
def main():
config = Config()
modeler = model.VGG(config)
#read data to val("data/val")
val_reader = read_data.VGGReader(config)
modeler.inference()
accuracy = modeler.accuracy()
init = tf.global_variables_initializer()
sess_config = tf.ConfigProto()
sess_config.gpu_options.allow_growth = True
with tf.Session(config=sess_config) as sess:
sess.run(init)
#saver.restore(sess, config.param_dir+config.load_filename)
print 'restore params' + config.steps
#testing
confmat = np.zeros((20, 20))
count = 0
num_iter = config.test_size // config.batch_size
for i in range(num_iter):
with tf.device('/cpu:0'):
images_val, labels_val, filenames_val = val_reader.batch()
with tf.device("/gpu:0"):
predict = sess.run(modeler.pred,
feed_dict={
modeler.image_holder: images_val,
modeler.is_train: False
})
#print predict, labels_val
if labels_val[0][predict[0]] > 0:
count += 1
confmat[predict[0]][predict[0]] += 1
else:
for i in range(20):
if labels_val[0][i] > 0:
confmat[i][predict[0]] += 1
confmat = confmat * 20 / 5823
print 'AP: ', count * 1.0 / config.test_size
print 'confusion matrix: '
print confmat
def main():
config = Config()
#modeler = model.VGG(config)
modeler = model.VGG16(include_top=False)
#modeler = model.ResNet50(include_top=False, input_shape=[config.img_height,config.img_width, 3], pooling='max')
inputs = Input(shape=[config.img_height, config.img_width, 3])
y = modeler(inputs)
y = Flatten()(y)
y = Dense(4096, activation='relu', name='fc1')(y)
y = Dense(4096, activation='relu', name='fc2')(y)
y = Dense(config.type_size, activation='softmax', name='predictions')(y)
modeler = Model(inputs, y, name='vgg16')
'''
y = Dense(config.type_size, activation='softmax', name='fc17')(y)
modeler = Model(inputs, y, name='resnet50')
'''
modeler.load_weights(config.params_dir + config.net_name + "-params-" +
str(config.test_num) + ".h5")
# read data to test("data/train")
val_reader = read_data.VGGReader(config)
print "finding thresholds..."
for step in range(config.max_step):
if step % (config.test_size // 10) == 0:
print 100 * step // config.test_size, "%"
images_val, labels_val, filesname_val = val_reader.get_batch()
probs = modeler.predict(images_val)
thresholds, scores = find_threshold1(probs, labels_val)
i = np.argmax(scores)
best_threshold, best_score = thresholds[i], scores[i]
best_thresholds, best_scores = find_threshold2(probs,
labels_val,
num_iters=500,
seed=best_threshold)
with open(
"./thresholds/" + config.net_name + "-weather-thresholds-" +
config.test_num + ".txt", 'w') as fr:
for i in range(len(best_thresholds)):
fr.write(str(best_thresholds[i]) + " ")
def main():
config = Config()
modeler = model.VGG(config)
modeler.inference()
# read data to test("data/train")
val_reader = read_data.VGGReader(config)
init = tf.global_variables_initializer()
sess_config = tf.ConfigProto()
sess_config.gpu_options.allow_growth = True
with tf.Session(config=sess_config) as sess:
sess.run(init)
print 'restore params' + config.test_num
print "finding thresholds..."
for step in range(config.max_step):
if step % (config.test_size // 10) == 0:
print 100 * step // config.test_size, "%"
with tf.device("/cpu:0"):
images_val, labels_val, filesname_val = val_reader.batch()
with tf.device("/gpu:0"):
_, probs = sess.run([modeler.pred, modeler.prob],
feed_dict={
modeler.image_holder: images_val,
modeler.is_train: False
})
thresholds, scores = find_threshold1(probs, labels_val)
i = np.argmax(scores)
best_threshold, best_score = thresholds[i], scores[i]
best_thresholds, best_scores = find_threshold2(probs,
labels_val,
num_iters=500,
seed=best_threshold)
with open(
"./thresholds/" + config.net_name + "-thresholds-" +
config.test_num + ".txt", 'w') as fr:
for i in range(len(best_thresholds)):
fr.write(str(best_thresholds[i]) + " ")
def main():
config = Config()
#modeler = model.VGG(config)
#modeler = model.VGG16(include_top=False)
modeler = model.ResNet50(include_top=False, input_shape=[config.img_height,config.img_width, 3], pooling='max')
inputs = Input(shape=[config.img_height,config.img_width,3])
y = modeler(inputs)
'''
y = Flatten()(y)
y = Dense(4096, activation='relu', name='fc1')(y)
y = Dense(4096, activation='relu', name='fc2')(y)
y = Dense(config.type_size, activation='softmax', name='predictions')(y)
modeler = Model(inputs, y, name='vgg16')
'''
y = Dense(config.type_size, activation='softmax', name='fc17')(y)
modeler = Model(inputs, y, name='resnet50')
modeler.load_weights(config.params_dir + config.net_name + "-params-" + str(config.test_num) + ".h5")
#modeler.compile(loss='categorical_crossentropy', optimizer=SGD(lr=config.learning_rate, momentum=0.9,nesterov=True))
# read data to test("data/train")
test_reader = read_data.VGGReader(config)
pre_prob = list()
with open("./thresholds/" + config.net_name + "-thresholds-" + config.test_num + ".txt", 'rb') as fr:
for line in fr:
tmp = re.split(' ', line.strip())
for i in range(config.type_size):
pre_prob.append(float(tmp[i]))
print "thresholds: ", pre_prob
test_labels = list()
pre_labels = list()
val_labels = list()
print "start testing..."
for step in range(config.test_size):
if step % (config.test_size // 10) == 0:
print 100 * step // config.test_size, "%"
images_test, labels_test, filesname_test = test_reader.batch()
prob = modeler.predict(images_test)
test_index = list()
for i in range(config.type_size):
val_labels.append(labels_test[0][i])
if prob[0][i] > pre_prob[i]:
test_index.append(i)
s = filesname_test[0]
for n in range(config.type_size):
is_in = False
for m in range(len(test_index)):
if n == test_index[m]:
is_in = True
if is_in:
s += " 1.0"
pre_labels.append(1.0)
else:
s += " 0.0"
pre_labels.append(0.0)
test_labels.append(s)
print "scores: ", fbeta_score(val_labels, pre_labels, beta=2)
if config.val_mode == False:
with open("./labels/test_results.csv", 'w') as fr:
fcsv = csv.writer(fr)
for i in range(len(test_labels)):
fcsv.writerow([test_labels[i]])
def main():
config = Config()
modeler = model.VGG(config)
#read data to val("data/val")
val_reader = read_data.VGGReader(config)
modeler.inference()
accuracy = modeler.accuracy()
init = tf.global_variables_initializer()
#saver = tf.train.Saver(max_to_keep=200)
sess_config = tf.ConfigProto()
sess_config.gpu_options.allow_growth = True
label_indexs = list()
test_labels = list()
with tf.Session(config=sess_config) as sess:
sess.run(init)
#saver.restore(sess, Config.vgg_path)
print 'restore params' + config.steps
#testing
count = 0
num_iter = config.test_size // config.batch_size
max_false_probs = [0.0] * config.type_size
max_true_probs = [0.0] * config.type_size
pre_prob = [
0.13, 0.13, 0.13, 0.13, 0.13, 0.13, 0.13, 0.6, 0.13, 0.13, 0.13,
0.13, 0.13, 0.13, 0.13, 0.13, 0.13
]
for i in range(num_iter):
label_index = list()
with tf.device('/cpu:0'):
images_val, labels_val, filenames_val = val_reader.batch()
with tf.device("/gpu:0"):
predict, prob = sess.run([modeler.pred, modeler.prob],
feed_dict={
modeler.image_holder: images_val,
modeler.is_train: False
})
if i < 20:
print predict, labels_val
print prob
if i % (num_iter // 10) == 0:
print 100 * i / num_iter, "%"
for j in range(config.type_size):
if (labels_val[0][j] == 1.0
and prob[0][j] > max_true_probs[j]):
max_true_probs[j] = prob[0][j]
if (labels_val[0][j] == 0.0
and prob[0][j] > max_false_probs[j]):
max_false_probs[j] = prob[0][j]
if prob[0][j] > pre_prob[j]:
label_index.append(j)
label_indexs.append(label_index)
is_correct = True
for k in range(len(label_index)):
if labels_val[0][label_index[k]] == 0.0:
is_correct = False
break
count_in = 0
count_in1 = 0
for k in range(len(labels_val[0])):
if labels_val[0][k] > 0.0:
count_in1 += 1
for n in range(len(label_index)):
if label_index[n] == k:
count_in += 1
break
if count_in != count_in1:
is_correct = False
s = filenames_val[0]
for n in range(17):
is_in = False
for m in range(len(label_index)):
if n == label_index[m]:
is_in = True
if is_in:
s += " 1.0"
else:
s += " 0.0"
test_labels.append(s)
if is_correct:
count += 1
with open("./labels/test_labels_pro.csv", 'w') as fr:
fcsv = csv.writer(fr)
for i in range(len(test_labels)):
fcsv.writerow([test_labels[i]])
'''