def eval(params):
batch_size = params['batch_size']
num_examples = len(params['test_files'][0])
with tf.Graph().as_default():
batch = dut.distorted_inputs(params,is_training=is_training)
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_19(batch[0], num_classes=params['n_output'], is_training=is_training)
init_fn=ut.get_init_fn(slim,params)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params['per_process_gpu_memory_fraction']
with tf.Session(config=config) as sess:
# sess.run(tf.initialize_all_variables())
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(qr.create_threads(sess, coord=coord, daemon=True, start=True))
init_fn(sess)
num_iter = int(math.ceil(num_examples / batch_size))
print('%s: Testing started.' % (datetime.now()))
step = 0
loss_lst=[]
run_lst=[]
run_lst.append(logits)
[run_lst.append(lst) for lst in batch[1:len(batch)]]
while step < num_iter and not coord.should_stop():
try:
batch_res= sess.run(run_lst)
except tf.errors.OutOfRangeError:
print ('Testing finished....%d'%step)
break
if(params['write_est']==True):
ut.write_est(params,batch_res)
est=batch_res[0]
gt=batch_res[1]
loss= ut.get_loss(params,gt,est)
loss_lst.append(loss)
s ='VAL --> batch %i/%i | error %f'%(step,num_iter,loss)
ut.log_write(s,params)
# joint_list=['/'.join(p1.split('/')[0:-1]).replace('joints','img').replace('.cdf','')+'/frame_'+(p1.split('/')[-1].replace('.txt','')).zfill(5)+'.png' for p1 in image_names]
# print ('List equality check:')
# print len(label_names) == len(set(label_names))
# print sum(joint_list==label_names)==(len(est))
# print(len(label_names))
step += 1
coord.request_stop()
coord.join(threads)
return np.mean(loss_lst)
def run_steps(params, epoch_counter):
with tf.Graph().as_default():
num_examples = len(params['training_files'][0])
number_of_steps = int(math.ceil(
num_examples / params['batch_size'])) - 1
number_of_steps = number_of_steps * (epoch_counter + 1)
tf.logging.set_verbosity(tf.logging.INFO)
batch = dut.distorted_inputs(params, is_training=is_training)
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, endpoint = vgg.vgg_19(batch[0],
num_classes=params['n_output'],
is_training=is_training)
# # Create the model:
# with slim.arg_scope(inception.inception_v2_arg_scope()):
# logits, _ = inception.inception_v2(batch[0], num_classes=params['n_output'], is_training=is_training)
err = tf.sub(logits, batch[1])
losses = tf.reduce_mean(tf.reduce_sum(tf.square(err), 1))
reg_loss = slim.losses.get_total_loss()
total_loss = losses + reg_loss
tf.scalar_summary('losses/total_loss', total_loss)
tf.scalar_summary('losses/losses', losses)
tf.scalar_summary('losses/reg_loss', reg_loss)
summary_writer = tf.train.SummaryWriter(params["sm"])
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=params['lr'])
train_op = slim.learning.create_train_op(total_loss,
optimizer,
summarize_gradients=True)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params[
'per_process_gpu_memory_fraction']
# Run the training:
final_loss = learn.train(
loss=losses,
logits=logits,
batch=batch,
endpoint=endpoint,
train_op=train_op,
logdir=params["cp_file"],
init_fn=ut.get_init_fn(slim, params),
number_of_steps=number_of_steps,
summary_writer=summary_writer,
session_config=config,
)
return final_loss
def eval(params):
# batch_size = params['batch_size']
# num_examples = len(params['test_files'][0])
with tf.Graph().as_default() as g:
url = '/home/coskun/PycharmProjects/data/pose/mv_val/img/S9/Discussion 1.54138969/frame_00010.png'
filename_queue = tf.train.string_input_producer(
[url]) # list of files to read
reader = tf.WholeFileReader()
key, value = reader.read(filename_queue)
# image_raw = tf.image.decode_png(value) # use png or jpg decoder based on your files.
image_raw = tf.image.decode_png(value, channels=3)
processed_image = human36m_preprocessing.preprocess_image(
image_raw, 224, 224, is_training=is_training)
processed_images = tf.expand_dims(processed_image, 0)
# image, label = dut.distorted_inputs(params,is_training=is_training)
with slim.arg_scope(inception.inception_v2_arg_scope()):
logits, end_points = inception.inception_v2(
processed_images,
num_classes=params['n_output'],
is_training=is_training)
init_fn = ut.get_init_fn(slim, params, load_previus_cp=True)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params[
'per_process_gpu_memory_fraction']
# operations = g.get_operations()
# for operation in operations:
# print "Operation:",operation.name
features = g.get_tensor_by_name(
'InceptionV2/InceptionV2/Mixed_3b/concat:0')
# features = g.get_tensor_by_name('InceptionV2/InceptionV2/MaxPool_3a_3x3/MaxPool:0')
with tf.Session(config=config) as sess:
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(
qr.create_threads(sess,
coord=coord,
daemon=True,
start=True))
init_fn(sess)
num_iter = 1
print('%s: Model reading started.' % (datetime.now()))
step = 0
loss_lst = []
# while step < num_iter and not coord.should_stop():
while step < num_iter:
try:
features_values = sess.run(features)
except tf.errors.OutOfRangeError:
print('Testing finished....%d' % step)
break
print features_values.shape
img_arr = np.squeeze(features_values[:, :, :, 1])
print img_arr.shape
img = Image.fromarray(img_arr).convert('RGB')
img.save(
'/home/coskun/PycharmProjects/poseft/files/temp/my.png')
img.show()
# joint_list=['/'.join(p1.split('/')[0:-1]).replace('joints','img').replace('.cdf','')+'/frame_'+(p1.split('/')[-1].replace('.txt','')).zfill(5)+'.png' for p1 in image_names]
# print ('List equality check:')
# print len(label_names) == len(set(label_names))
# print sum(joint_list==label_names)==(len(est))
# print(len(label_names))init_fn=ut.get_init_fn(slim,params,load_previus_cp=True)
step += 1
coord.request_stop()
coord.join(threads)
def run_steps(params,epoch_counter):
with tf.Graph().as_default():
num_examples=len(params['training_files'][0])
number_of_steps = int(math.ceil(num_examples / params['batch_size']))-1
print "Number of steps: %i" % number_of_steps
number_of_steps=number_of_steps*(epoch_counter+1)
tf.logging.set_verbosity(tf.logging.INFO)
batch = dut.distorted_inputs(params,is_training=is_training)
# with tf.Session() as sess:
# tf.initialize_all_variables().run()
# print('Variables init.......')
# retur=sess.run(batch)
# print(retur)
#
# Create the model:
with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()):
logits,aux, endpoint = inception_resnet_v2.inception_resnet_v2(batch[0], num_classes=params['n_output'], is_training=is_training)
err=tf.subtract(logits, batch[1])
losses = tf.reduce_sum(tf.reduce_sum(tf.square(err)))
err_tr = tf.reshape(err, shape=[-1, 3])
err_tr = tf.square(err_tr)
err_tr = tf.reduce_sum(err_tr,axis=1)
err_tr = tf.sqrt(err_tr)
err_tr = tf.reduce_mean(err_tr)
# err_aux=tf.subtract(aux, batch[1])
# losses_aux = tf.reduce_sum(tf.reduce_sum(tf.square(err_aux)))
reg_loss=slim.losses.get_total_loss()
# total_loss = losses+0.4*losses_aux+reg_loss
total_loss = losses+reg_loss
#Compute cross entropy
# with tf.Session() as sess:
# tf.initialize_all_variables().run()
# print('Variables init.......')
# r1,r2=sess.run([losses,reg_loss])
# print(r1)
#
tf.summary.scalar('losses/total_loss', total_loss)
tf.summary.scalar('losses/losses', losses)
tf.summary.scalar('losses/training_loss', err_tr)
tf.summary.scalar('losses/reg_loss', reg_loss)
summary_writer = tf.summary.FileWriter(params["sm"])
#
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=params['lr'])
#
# optimizer.compute_gradients()
train_op = slim.learning.create_train_op(total_loss, optimizer,summarize_gradients=False)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.95
# Run the training:
# final_loss = learn.train(
# loss=losses,
# logits=logits,
# batch=batch,
# endpoint=endpoint,
# train_op=train_op,
# logdir=params["cp_file"],
# init_fn=ut.get_init_fn(slim,params),
# number_of_steps=number_of_steps,
# summary_writer=summary_writer,
# session_config=config,
# )
final_loss = tf.contrib.slim.learning.train(
train_op=train_op,
logdir=params["cp_file"],
init_fn=ut.get_init_fn(slim,params),
number_of_steps=number_of_steps,
summary_writer=summary_writer,
session_config=config,
)
# final_loss=0
return final_loss
image_raw = tf.image.decode_png(value, channels=3)
# image = tf.image.resize_bilinear(image_raw, [256, 256,3], align_corners=False)
processed_image = human36m_preprocessing.preprocess_image(
image_raw, 299, 299, is_training=is_training)
processed_images = tf.expand_dims(processed_image, 0)
# image, label = dut.distorted_inputs(params,is_training=is_training)
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, aux, end_points = inception.inception_v3(
processed_images,
num_classes=params['n_output'],
is_training=is_training)
init_fn = ut.get_init_fn(slim, params)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params[
'per_process_gpu_memory_fraction']
loss_lst = []
run_lst = []
run_lst.append(logits)
with tf.Session(config=config) as sess:
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(
qr.create_threads(sess, coord=coord, daemon=True, start=True))
def eval(params):
batch_size = params['batch_size']
params['write_est']=False
num_examples = len(params['test_files'][0])
with tf.Graph().as_default():
batch = dut.distorted_inputs(params,is_training=is_training)
with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()):
logits,aux, end_points = inception_resnet_v2.inception_resnet_v2(batch[0],
num_classes=params['n_output'],
is_training=is_training)
# Obtain the trainable variables and a saver
# variables_to_restore = slim.get_variables_to_restore()
init_fn=ut.get_init_fn(slim,params)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params['per_process_gpu_memory_fraction']
with tf.Session() as sess:
init_op = tf.group(tf.initialize_all_variables(), tf.initialize_local_variables())
# init_op = tf.global_variables_initializer()
sess.run(init_op)
init_fn(sess)
coord = tf.train.Coordinator()
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(qr.create_threads(sess, coord=coord, daemon=True, start=True))
num_iter = int(math.ceil(num_examples / batch_size))
print('%s: Testing started.' % (datetime.now()))
step = 0
loss_lst=[]
run_lst=[]
run_lst.append(logits)
# run_lst.append(end_points['PreLogitsFlatten'])
# run_lst.append(end_points['PrePool'])
[run_lst.append(lst) for lst in batch[1:len(batch)]]
while step < num_iter and not coord.should_stop():
try:
batch_res= sess.run(run_lst)
except tf.errors.OutOfRangeError:
print ('Testing finished....%d'%step)
break
if(params['write_est']==True):
ut.write_mid_est(params,batch_res)
est=batch_res[0]
gt=batch_res[1]
# print(est.shape)
# print(gt.shape)
prepool=batch_res[-1]
loss,_= ut.get_loss(params,gt,est)
loss_lst.append(loss)
s ='VAL --> batch %i/%i | error %f'%(step,num_iter,loss)
if step%10==0:
ut.log_write(s,params,screen_print=True)
print "Current number of examples / mean err: %i / %f"%(step*gt.shape[0],np.mean(loss_lst))
else:
ut.log_write(s, params, screen_print=False)
# joint_list=['/'.join(p1.split('/')[0:-1]).replace('joints','img').replace('.cdf','')+'/frame_'+(p1.split('/')[-1].replace('.txt','')).zfill(5)+'.png' for p1 in image_names]
# print ('List equality check:')
# print len(label_names) == len(set(label_names))
# print sum(joint_list==label_names)==(len(est))
# print(len(label_names))
step += 1
coord.request_stop()
coord.join(threads)
return np.mean(loss_lst)