def eval_lenet(net_name, ckpt_path, trainable=False, err_mean=None, err_stddev=None, train_vars=None, cost_factor=200., n_epoch=1):
netparams = load.load_netparams_tf(ckpt_path, trainable=False)
data_spec = networks.get_data_spec(net_name)
input_node = tf.placeholder(tf.float32, shape=(None, data_spec.crop_size * data_spec.crop_size * data_spec.channels))
input_node_2d = tf.reshape(input_node, shape=(-1, data_spec.crop_size, data_spec.crop_size, data_spec.channels))
label_node = tf.placeholder(tf.float32, [None, 10])
logits_, err_w, err_b, err_lyr = lenet_noisy(input_node_2d, netparams, err_mean, err_stddev, train_vars)
square = [tf.nn.l2_loss(err_w[layer]) for layer in err_w]
square_sum = tf.reduce_sum(square)
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor / (1. + square_sum)
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
if trainable:
train_op = optimizer.minimize(loss_op)
probs = softmax(logits_)
correct_pred = tf.equal(tf.argmax(probs, 1), tf.argmax(label_node, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
mnist = mnist_input.read_data_sets("/tmp/data/", one_hot=True)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
cur_accuracy = 0
for i in range(0, n_epoch):
#if cur_accuracy >= NET_ACC[net_name]:
#break
if trainable:
for step in range(0, mnist.train.num_examples/data_spec.batch_size):
batch_x, batch_y = mnist.train.next_batch(data_spec.batch_size)
sess.run(train_op, feed_dict={input_node: batch_x, label_node: batch_y})
#loss, acc = sess.run([loss_op_1, accuracy], feed_dict={input_node: batch_x, label_node: batch_y})
print('Training finished\n')
cur_accuracy = 100 * (sess.run(accuracy, feed_dict={input_node: mnist.test.images[:], label_node: mnist.test.labels[:]}))
print('test accuracy:\t' + (str)(cur_accuracy))
return sess.run(err_w), cur_accuracy
def eval_lenet(net_name, param_path, qbits, layer_index, layer_name=[], trainable=False, err_mean=None, err_stddev=None, train_vars=None, cost_factor=200., n_epoch=1):
#netparams = load.load_netparams_tf(ckpt_path, trainable=False)
if '.ckpt' in param_path:
netparams = load.load_netparams_tf(param_path, trainable=trainable)
else:
netparams = load.load_netparams_tf_q(param_path, trainable=trainable)
data_spec = helper.get_data_spec(net_name)
input_node = tf.placeholder(tf.float32, shape=(None, data_spec.crop_size * data_spec.crop_size * data_spec.channels))
input_node_2d = tf.reshape(input_node, shape=(-1, data_spec.crop_size, data_spec.crop_size, data_spec.channels))
label_node = tf.placeholder(tf.float32, [None, 10])
#logits_, err_w, err_b, err_lyr = lenet.lenet_noisy(input_node_2d, netparams, err_mean, err_stddev, train_vars)
#logits_ = lenet.lenet_quantized(input_node_2d, netparams, qbits)
if trainable:
#logits_ = lenet.lenet_q_RL(input_node_2d, netparams, qbits, layer_index)
logits_ = lenet.lenet_quantized(input_node_2d, netparams, qbits)
else:
logits_ = lenet.lenet(input_node_2d, netparams)
#square = [tf.nn.l2_loss(err_w[layer]) for layer in err_w]
#square_sum = tf.reduce_sum(square)
#loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor / (1. + square_sum)
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
if trainable:
train_op = optimizer.minimize(loss_op)
probs = helper.softmax(logits_)
correct_pred = tf.equal(tf.argmax(probs, 1), tf.argmax(label_node, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
#mnist = mnist_input.read_data_sets("/tmp/data/", one_hot=True)
mnist = mnist_input.read_data_sets("/home/ahmed/mnist", one_hot=True)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
cur_accuracy = 0
for i in range(0, n_epoch):
#if cur_accuracy >= NET_ACC[net_name]:
#break
if trainable:
for step in range(0, int(mnist.train.num_examples/data_spec.batch_size)):
batch_x, batch_y = mnist.train.next_batch(data_spec.batch_size)
sess.run(train_op, feed_dict={input_node: batch_x, label_node: batch_y})
#loss, acc = sess.run([loss_op_1, accuracy], feed_dict={input_node: batch_x, label_node: batch_y})
print('epoch# {:>6} finished\n', i)
cur_accuracy = 100 * (sess.run(accuracy, feed_dict={input_node: mnist.test.images[:], label_node: mnist.test.labels[:]}))
print('{:>6}/{:<6} {:>6.2f}%'.format(i, n_epoch, cur_accuracy))
print('Final Test Accuracy = \t' + (str)(cur_accuracy))
return cur_accuracy, sess.run(netparams)
def eval_imagenet(net_name, param_path, param_q_path, qbits, layer_index, layer_name, file_idx, shift_back, trainable=False, err_mean=None, err_stddev=None, train_vars=None, cost_factor=200., n_epoch=1):
"""all layers are trainable in the conventional retraining procedure"""
if '.ckpt' in param_path:
netparams = load.load_netparams_tf(param_path, trainable=True)
else:
netparams = load.load_netparams_tf_q(param_path, trainable=True)
data_spec = helper.get_data_spec(net_name)
input_node = tf.placeholder(tf.float32, shape=(None, data_spec.crop_size, data_spec.crop_size, data_spec.channels))
label_node = tf.placeholder(tf.int32)
if net_name == 'alexnet_noisy':
logits_, err_w, err_b, err_lyr = networks.alexnet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'alexnet':
if trainable:
logits_ = alexnet.alexnet_q(input_node, netparams, qbits)
else:
logits_ = alexnet.alexnet(input_node, netparams)
elif net_name == 'alexnet_shift':
logits_ = networks.alexnet_shift(input_node, netparams)
elif net_name == 'googlenet':
logits_, err_w, err_b, err_lyr = networks.googlenet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'nin':
logits_, err_w, err_b, err_lyr = networks.nin_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18':
logits_ = resnet18.resnet18(input_node, netparams)
#logits_, err_w, err_b, err_lyr = networks.resnet18_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18_shift':
logits_ = networks.resnet18_shift(input_node, netparams, shift_back)
elif net_name == 'resnet50':
logits_, err_w, err_b, err_lyr = networks.resnet50_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'squeezenet':
logits_, err_w, err_b, err_lyr = networks.squeezenet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'vgg16net':
logits_, err_w, err_b, err_lyr = networks.vgg16net_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
#square = [tf.nn.l2_loss(err_w[layer]) for layer in err_w]
#square_sum = tf.reduce_sum(square)
#loss_op = tf.reduce_mean(tf.nn.oftmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor / (1. + square_sum)
# ======== calculating the quantization error of a certain layer ==========
if trainable:
""" read the quantized weights (quantized version of the most recent retrained) """
w_q_pickle = param_q_path
with open(w_q_pickle, 'rb') as f:
params_quantized = pickle.load(f)
layer = layer_name
params_quantized_layer = tf.get_variable(name='params_quantized_layer', initializer=tf.constant(params_quantized[0][layer]), trainable=False)
q_diff = tf.subtract(params_quantized_layer, netparams['weights'][layer])
q_diff_cost = tf.nn.l2_loss(q_diff)
#loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor*q_diff_cost
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node))
probs = helper.softmax(logits_)
top_k_op = tf.nn.in_top_k(probs, label_node, 5)
#optimizer = tf.train.AdamOptimizer(learning_rate=0.0001, epsilon=0.1)
optimizer = tf.train.AdamOptimizer(learning_rate=0.01, beta1=0.9, beta2=0.999, epsilon=10-8)
if trainable:
train_op = optimizer.minimize(loss_op)
correct_pred = tf.equal(tf.argmax(probs, 1), tf.argmax(label_node, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
if trainable:
count = 0
correct = 0
cur_accuracy = 0
for i in range(0, n_epoch):
#if cur_accuracy >= NET_ACC[net_name]:
#break
#image_producer = dataset.ImageNetProducer(val_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_10K/val_10.txt', data_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_10K', data_spec=data_spec)
#path_train = '/home/ahmed/projects/NN_quant/imageNet_training'
path_train = '/home/ahmed/ILSVRC2012_img_train'
#image_producer = dataset.ImageNetProducer(val_path=path_train + '/train_shuf_'+str(file_idx)+'.txt', data_path=path_train, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path=path_train + '/reward_20k.txt', data_path=path_train, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path=path_train + '/train_50classes.txt', data_path=path_train, data_spec=data_spec)
image_producer = dataset.ImageNetProducer(val_path=path_train + '/train_shuf.txt', data_path=path_train, data_spec=data_spec)
total = len(image_producer) * n_epoch
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess, coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
sess.run(train_op, feed_dict={input_node: images, label_node: one_hot_labels})
# AHMED: debug
#netparams_tmp = sess.run(netparams)
#print('train = ', np.amax(netparams_tmp['weights']['conv2']))
#print('len set = ', len(set(np.array(netparams['weights']['conv2']))))
# ------------
#correct += np.sum(sess.run(top_k_op, feed_dict={input_node: images, label_node: labels}))
# AHMED: modify
#top, logits_tmp, loss_op_tmp = sess.run([top_k_op, logits_q, loss_op], feed_dict={input_node: images, label_node: labels})
#top, act_q_tmp, weights_fp_tmp, weights_q_tmp = sess.run([top_k_op, act_, weights_fp, weights_q], feed_dict={input_node: images, label_node: labels})
top = sess.run([top_k_op], feed_dict={input_node: images, label_node: labels})
correct += np.sum(top)
#print(np.amax(weights_q_tmp))
#print(len(set(weights_q_tmp.ravel())))
# --------
count += len(labels)
cur_accuracy = float(correct) * 100 / count
file_label = 'retrain_reward'
for i in range(len(qbits)):
file_label=file_label+'_'+str(qbits[i])
write_to_csv([count, total, cur_accuracy],file_label)
print('{:>6}/{:<6} {:>6.2f}%'.format(count, total, cur_accuracy))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
#return sess.run(err_w), cur_accuracy
# "sess.run" returns the netparams as normal value (converts it from tf to normal python variable)
return cur_accuracy, sess.run(netparams)
else:
count = 0
correct = 0
cur_accuracy = 0
#path_val = './nn_quant_and_run_code_train/ILSVRC2012_img_val'
path_val = '/home/ahmed/ILSVRC2012_img_val'
image_producer = dataset.ImageNetProducer(val_path=path_val + '/val.txt', data_path=path_val, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path=path_val + '/val_50classes.txt', data_path=path_val, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path=path_val + '/val_reward_3k.txt', data_path=path_val, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_40K/val_40.txt', data_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_40K', data_spec=data_spec)
total = len(image_producer)
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess, coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
#correct += np.sum(sess.run(top_k_op, feed_dict={input_node: images, label_node: labels}))
top = sess.run([top_k_op], feed_dict={input_node: images, label_node: labels})
correct += np.sum(top)
count += len(labels)
cur_accuracy = float(correct) * 100 / count
print('{:>6}/{:<6} {:>6.2f}%'.format(count, total, cur_accuracy))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
return cur_accuracy, 0
def eval_imagenet(net_name,
param_path,
shift_back,
trainable=False,
err_mean=None,
err_stddev=None,
train_vars=None,
cost_factor=200.,
n_epoch=1):
if '.ckpt' in param_path:
netparams = load.load_netparams_tf(param_path, trainable=False)
else:
netparams = load.load_netparams_tf_q(param_path, trainable=False)
#print((len(netparams['biases'])))
data_spec = networks.get_data_spec(net_name)
input_node = tf.placeholder(tf.float32,
shape=(None, data_spec.crop_size,
data_spec.crop_size,
data_spec.channels))
label_node = tf.placeholder(tf.int32)
if net_name == 'alexnet_noisy':
logits_, err_w, err_b, err_lyr = networks.alexnet_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'alexnet':
logits_ = networks.alexnet(input_node, netparams)
elif net_name == 'alexnet_shift':
logits_ = networks.alexnet_shift(input_node, netparams)
elif net_name == 'googlenet':
logits_, err_w, err_b, err_lyr = networks.googlenet_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'nin':
logits_, err_w, err_b, err_lyr = networks.nin_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18':
logits_ = networks.resnet18(input_node, netparams)
#logits_, err_w, err_b, err_lyr = networks.resnet18_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18_shift':
logits_ = networks.resnet18_shift(input_node, netparams, shift_back)
elif net_name == 'resnet50':
logits_, err_w, err_b, err_lyr = networks.resnet50_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'squeezenet':
logits_, err_w, err_b, err_lyr = networks.squeezenet_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'vgg16net':
logits_, err_w, err_b, err_lyr = networks.vgg16net_noisy(
input_node, netparams, err_mean, err_stddev, train_vars)
#square = [tf.nn.l2_loss(err_w[layer]) for layer in err_w]
#square_sum = tf.reduce_sum(square)
#loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor / (1. + square_sum)
# ======== calculating the quantization error of a certain layer
# here needs PARAM
w_q_pickle = '/home/behnam/results/quantized/resnet18/May12_resnet18_10_res2a_branch1_5_bits.pickle'
with open(w_q_pickle, 'r') as f:
params_quantized = pickle.load(f)
# here needs PARAM
layer = 'res2a_branch1'
params_quantized_layer = tf.get_variable(name='params_quantized_layer',
initializer=tf.constant(
params_quantized[0][layer]),
trainable=False)
q_diff = tf.subtract(params_quantized_layer, netparams['weights'][layer])
q_diff_cost = tf.nn.l2_loss(q_diff)
loss_op = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(
logits=logits_, labels=label_node)) + cost_factor * q_diff_cost
#loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node))
probs = softmax(logits_)
top_k_op = tf.nn.in_top_k(probs, label_node, 5)
optimizer = tf.train.AdamOptimizer(learning_rate=0.001, epsilon=0.1)
if trainable:
train_op = optimizer.minimize(loss_op)
correct_pred = tf.equal(tf.argmax(probs, 1), tf.argmax(label_node, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
if trainable:
count = 0
correct = 0
cur_accuracy = 0
for i in range(0, n_epoch):
#if cur_accuracy >= NET_ACC[net_name]:
#break
#image_producer = dataset.ImageNetProducer(val_path='/home/behnam/ILSVRC2012_img_val_40K/val_40.txt', data_path='/home/behnam/ILSVRC2012_img_val_40K', data_spec=data_spec)
path_train = '/home/behnam/ILSVRC2012_img_train'
image_producer = dataset.ImageNetProducer(
val_path=path_train + '/train_shuf_200k.txt',
data_path=path_train,
data_spec=data_spec)
total = len(image_producer) * n_epoch
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess,
coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
sess.run(train_op,
feed_dict={
input_node: images,
label_node: one_hot_labels
})
correct += np.sum(
sess.run(top_k_op,
feed_dict={
input_node: images,
label_node: labels
}))
count += len(labels)
cur_accuracy = float(correct) * 100 / count
print('{:>6}/{:<6} {:>6.2f}%'.format(
count, total, cur_accuracy))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
#return sess.run(err_w), cur_accuracy
# "sess.run" returns the netparams as normal value (converts it from tf to normal python variable)
return cur_accuracy, sess.run(netparams)
else:
count = 0
correct = 0
cur_accuracy = 0
path_val = '/home/behnam/ILSVRC2012_img_val_40K'
image_producer = dataset.ImageNetProducer(val_path=path_val +
'/val_40.txt',
data_path=path_val,
data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path='/home/behnam/ILSVRC2012_img_val_40K/val_40.txt', data_path='/home/behnam/ILSVRC2012_img_val_40K', data_spec=data_spec)
total = len(image_producer)
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess,
coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
correct += np.sum(
sess.run(top_k_op,
feed_dict={
input_node: images,
label_node: labels
}))
count += len(labels)
cur_accuracy = float(correct) * 100 / count
print('{:>6}/{:<6} {:>6.2f}%'.format(count, total,
cur_accuracy))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
return cur_accuracy, 0
def eval_imagenet(net_name, param_path, shift_back, trainable=False, err_mean=None, err_stddev=None, train_vars=None, cost_factor=200., n_epoch=1):
if '.ckpt' in param_path:
netparams = load.load_netparams_tf(param_path, trainable=False)
else:
netparams = load.load_netparams_tf_q(param_path, trainable=False)
# AHMED: debug
print('input = ', np.amax(netparams['weights']['conv2']))
# ------------
network = 'alexnet'
param_path_fp = './rlbitwidth.tfmodels/caffe2tf/tfmodels/' + network +'/' + network +'.ckpt'
netparams_fp = load.load_netparams_tf(param_path_fp, trainable=False)
#print((len(netparams['biases'])))
data_spec = helper.get_data_spec(net_name)
input_node = tf.placeholder(tf.float32, shape=(None, data_spec.crop_size, data_spec.crop_size, data_spec.channels))
label_node = tf.placeholder(tf.int32)
if net_name == 'alexnet_noisy':
logits_, err_w, err_b, err_lyr = networks.alexnet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'alexnet':
if trainable:
logits_, act_, weights_fp = alexnet.alexnet(input_node, netparams_fp)
act_q, weights_q = alexnet.alexnet_conv1_conv3(input_node, netparams)
else:
logits_ , _ , _ = alexnet.alexnet(input_node, netparams)
elif net_name == 'alexnet_shift':
logits_ = networks.alexnet_shift(input_node, netparams)
elif net_name == 'googlenet':
logits_, err_w, err_b, err_lyr = networks.googlenet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'nin':
logits_, err_w, err_b, err_lyr = networks.nin_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18':
logits_ = resnet18.resnet18(input_node, netparams)
#logits_, err_w, err_b, err_lyr = networks.resnet18_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'resnet18_shift':
logits_ = networks.resnet18_shift(input_node, netparams, shift_back)
elif net_name == 'resnet50':
logits_, err_w, err_b, err_lyr = networks.resnet50_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'squeezenet':
logits_, err_w, err_b, err_lyr = networks.squeezenet_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
elif net_name == 'vgg16net':
logits_, err_w, err_b, err_lyr = networks.vgg16net_noisy(input_node, netparams, err_mean, err_stddev, train_vars)
#square = [tf.nn.l2_loss(err_w[layer]) for layer in err_w]
#square_sum = tf.reduce_sum(square)
#loss_op = tf.reduce_mean(tf.nn.oftmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor / (1. + square_sum)
# ======== calculating the quantization error of a certain layer
# here needs PARAM
"""
if trainable:
w_q_pickle = '/home/ahmed/projects/NN_quant/results/quantized/resnet18/May12_resnet18_10_res2a_branch1_5_bits.pickle'
with open(w_q_pickle, 'r') as f:
params_quantized = pickle.load(f)
# here needs PARAM
layer = 'res2a_branch1'
params_quantized_layer = tf.get_variable(name='params_quantized_layer', initializer=tf.constant(params_quantized[0][layer]), trainable=False)
q_diff = tf.subtract(params_quantized_layer, netparams['weights'][layer])
q_diff_cost = tf.nn.l2_loss(q_diff)
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node)) + cost_factor*q_diff_cost
"""
#loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_, labels=label_node))
# AHMED test: partial backprop
#logits_diff = tf.subtract(logits_.ravel(), logits_q.ravel())
probs = helper.softmax(logits_)
top_k_op = tf.nn.in_top_k(probs, label_node, 5)
if trainable:
"""trial#1"""
#act_diff = tf.subtract(tf.reshape(act_, [-1]), tf.reshape(act_q, [-1]))
#act_diff_cost_section1 = tf.nn.l2_loss(act_diff)
"""trial#2"""
#act_ = tf.nn.sigmoid(Z3)
#act_diff_cost_section1 = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=act_q, labels=tf.nn.sigmoid(act_)))
"""trial#3"""
act_diff_cost_section1 = tf.reduce_mean(tf.losses.mean_squared_error(predictions=act_q, labels=act_))
optimizer = tf.train.AdamOptimizer(learning_rate=0.00005, beta1=0.9, beta2=0.999, epsilon=10-8)
#train_op = optimizer.minimize(loss_op)
train_op = optimizer.minimize(act_diff_cost_section1)
correct_pred = tf.equal(tf.argmax(probs, 1), tf.argmax(label_node, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
if trainable:
count = 0
correct = 0
cur_accuracy = 0
for i in range(0, n_epoch):
#if cur_accuracy >= NET_ACC[net_name]:
#break
#image_producer = dataset.ImageNetProducer(val_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_10K/val_10.txt', data_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_10K', data_spec=data_spec)
path_train = '/home/ahmed/projects/NN_quant/imageNet_training'
image_producer = dataset.ImageNetProducer(val_path=path_train + '/train_shuf_100k.txt', data_path=path_train, data_spec=data_spec)
total = len(image_producer) * n_epoch
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess, coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
#sess.run(train_op, feed_dict={input_node: images, label_node: one_hot_labels})
_ , loss_op_tmp = sess.run([train_op, act_diff_cost_section1], feed_dict={input_node: images, label_node: one_hot_labels})
# AHMED: debug
netparams_tmp = sess.run(netparams)
#print('train = ', np.amax(netparams_tmp['weights']['conv2']))
#print('len set = ', len(set(np.array(netparams['weights']['conv2']))))
# ------------
#correct += np.sum(sess.run(top_k_op, feed_dict={input_node: images, label_node: labels}))
# AHMED: modify
#top, logits_tmp, loss_op_tmp = sess.run([top_k_op, logits_q, loss_op], feed_dict={input_node: images, label_node: labels})
#top, act_q_tmp, weights_fp_tmp, weights_q_tmp = sess.run([top_k_op, act_, weights_fp, weights_q], feed_dict={input_node: images, label_node: labels})
top, act_q_tmp, weights_q_tmp = sess.run([top_k_op, act_, weights_q], feed_dict={input_node: images, label_node: labels})
correct += np.sum(top)
#print(np.amax(weights_q_tmp))
#print(len(set(weights_q_tmp.ravel())))
# --------
count += len(labels)
cur_accuracy = float(correct) * 100 / count
#print('{:>6}/{:<6} {:>6.2f}%'.format(count, total, cur_accuracy))
print('{:>6}/{:<6} {:>6.2f} error'.format(count, total, loss_op_tmp))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
#return sess.run(err_w), cur_accuracy
# "sess.run" returns the netparams as normal value (converts it from tf to normal python variable)
return cur_accuracy, sess.run(netparams)
else:
count = 0
correct = 0
cur_accuracy = 0
path_val = '../nn_quant_and_run_code/ILSVRC2012_img_val'
image_producer = dataset.ImageNetProducer(val_path=path_val + '/val.txt', data_path=path_val, data_spec=data_spec)
#image_producer = dataset.ImageNetProducer(val_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_40K/val_40.txt', data_path='/home/ahmed/projects/NN_quant/ILSVRC2012_img_val_40K', data_spec=data_spec)
total = len(image_producer)
coordinator = tf.train.Coordinator()
threads = image_producer.start(session=sess, coordinator=coordinator)
for (labels, images) in image_producer.batches(sess):
one_hot_labels = np.zeros((len(labels), 1000))
for k in range(len(labels)):
one_hot_labels[k][labels[k]] = 1
#correct += np.sum(sess.run(top_k_op, feed_dict={input_node: images, label_node: labels}))
top = sess.run([top_k_op], feed_dict={input_node: images, label_node: labels})
correct += np.sum(top)
count += len(labels)
cur_accuracy = float(correct) * 100 / count
print('{:>6}/{:<6} {:>6.2f}%'.format(count, total, cur_accuracy))
coordinator.request_stop()
coordinator.join(threads, stop_grace_period_secs=2)
return cur_accuracy, 0
