def _test_metric_spec(self, metric_spec, hyps, refs, expected_scores):
"""Tests a MetricSpec"""
predictions = {"predicted_tokens": tf.placeholder(dtype=tf.string)}
labels = {"target_tokens": tf.placeholder(dtype=tf.string)}
value, update_op = metric_spec.create_metric_ops(None, labels, predictions)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
scores = []
for hyp, ref in zip(hyps, refs):
hyp = hyp.split(" ")
ref = ref.split(" ")
sess.run(update_op, {
predictions["predicted_tokens"]: [hyp],
labels["target_tokens"]: [ref]
})
scores.append(sess.run(value))
for score, expected in zip(scores, expected_scores):
np.testing.assert_almost_equal(score, expected, decimal=2)
np.testing.assert_almost_equal(score, expected, decimal=2)
python类placeholder()的实例源码
def _load_data_graph(self):
"""
Loads the data graph consisting of the encoder and decoder input placeholders, Label (Target tip summary)
placeholders and the weights of the hidden layer of the Seq2Seq model.
:return: None
"""
# input
with tf.variable_scope("train_test", reuse=True):
# review input - Both original and reversed
self.enc_inp_fwd = [tf.placeholder(tf.int32, shape=(None,), name="input%i" % t)
for t in range(self.seq_length)]
self.enc_inp_bwd = [tf.placeholder(tf.int32, shape=(None,), name="input%i" % t)
for t in range(self.seq_length)]
# desired output
self.labels = [tf.placeholder(tf.int32, shape=(None,), name="labels%i" % t)
for t in range(self.seq_length)]
# weight of the hidden layer
self.weights = [tf.ones_like(labels_t, dtype=tf.float32)
for labels_t in self.labels]
# Decoder input: prepend some "GO" token and drop the final
# token of the encoder input
self.dec_inp = ([tf.zeros_like(self.labels[0], dtype=np.int32, name="GO")] + self.labels[:-1])
def _load_data_graph(self):
"""
Loads the data graph consisting of the encoder and decoder input placeholders, Label (Target tip summary)
placeholders and the weights of the hidden layer of the Seq2Seq model.
:return: None
"""
# input
with tf.variable_scope("train_test", reuse=True):
self.enc_inp = [tf.placeholder(tf.int32, shape=(None,),
name="input%i" % t)
for t in range(self.seq_length)]
# desired output
self.labels = [tf.placeholder(tf.int32, shape=(None,),
name="labels%i" % t)
for t in range(self.seq_length)]
# weight of the hidden layer
self.weights = [tf.ones_like(labels_t, dtype=tf.float32)
for labels_t in self.labels]
# Decoder input: prepend some "GO" token and drop the final
# token of the encoder input
self.dec_inp = ([tf.zeros_like(self.labels[0], dtype=np.int32, name="GO")]
+ self.labels[:-1])
def _load_data_graph(self):
"""
Loads the data graph consisting of the encoder and decoder input placeholders, Label (Target tip summary)
placeholders and the weights of the hidden layer of the Seq2Seq model.
:return: None
"""
# input
with tf.variable_scope("train_test", reuse=True):
self.enc_inp = [tf.placeholder(tf.int32, shape=(None,), name="input%i" % t)
for t in range(self.seq_length)]
# desired output
self.labels = [tf.placeholder(tf.int32, shape=(None,), name="labels%i" % t)
for t in range(self.seq_length)]
# weight of the hidden layer
self.weights = [tf.ones_like(labels_t, dtype=tf.float32)
for labels_t in self.labels]
# Decoder input: prepend some "GO" token and drop the final
# token of the encoder input
self.dec_inp = ([tf.zeros_like(self.labels[0], dtype=np.int32, name="GO")] + self.labels[:-1])
def _load_data_graph(self):
"""
Loads the data graph consisting of the encoder and decoder input placeholders, Label (Target tip summary)
placeholders and the weights of the hidden layer of the Seq2Seq model.
:return: None
"""
# input
with tf.variable_scope("train_test", reuse=True):
# review input - Both original and reversed
self.enc_inp_fwd = [tf.placeholder(tf.int32, shape=(None,), name="input%i" % t)
for t in range(self.seq_length)]
self.enc_inp_bwd = [tf.placeholder(tf.int32, shape=(None,), name="input%i" % t)
for t in range(self.seq_length)]
# desired output
self.labels = [tf.placeholder(tf.int32, shape=(None,), name="labels%i" % t)
for t in range(self.seq_length)]
# weight of the hidden layer
self.weights = [tf.ones_like(labels_t, dtype=tf.float32)
for labels_t in self.labels]
# Decoder input: prepend some "GO" token and drop the final
# token of the encoder input
self.dec_inp = ([tf.zeros_like(self.labels[0], dtype=np.int32, name="GO")] + self.labels[:-1])
def build_model(self):
self.q = tf.placeholder(tf.float32, [self.reader.vocab_size], name="question")
self.a = tf.placeholder(tf.float32, [self.reader.vocab_size], name="answer")
self.build_encoder()
self.build_decoder()
# Kullback Leibler divergence
self.e_loss = -0.5 * tf.reduce_sum(1 + self.log_sigma_sq - tf.square(self.mu) - tf.exp(self.log_sigma_sq))
# Log likelihood
self.g_loss = tf.reduce_sum(tf.log(self.p_x_i))
self.loss = tf.reduce_mean(self.e_loss + self.g_loss)
self.optim = tf.train.AdamOptimizer(learning_rate=self.learning_rate).minimize(-self.loss)
_ = tf.scalar_summary("encoder loss", self.e_loss)
_ = tf.scalar_summary("decoder loss", self.g_loss)
_ = tf.scalar_summary("loss", self.loss)
def __init__(self, files_list, thread_count, batch_size, numcep, numcontext, next_index=lambda x: x + 1):
self._coord = None
self._numcep = numcep
self._x = tf.placeholder(tf.float32, [None, numcep + (2 * numcep * numcontext)])
self._x_length = tf.placeholder(tf.int32, [])
self._y = tf.placeholder(tf.int32, [None,])
self._y_length = tf.placeholder(tf.int32, [])
self.example_queue = tf.PaddingFIFOQueue(shapes=[[None, numcep + (2 * numcep * numcontext)], [], [None,], []],
dtypes=[tf.float32, tf.int32, tf.int32, tf.int32],
capacity=2 * self._get_device_count() * batch_size)
self._enqueue_op = self.example_queue.enqueue([self._x, self._x_length, self._y, self._y_length])
self._close_op = self.example_queue.close(cancel_pending_enqueues=True)
self.batch_size = batch_size
self._numcontext = numcontext
self._thread_count = thread_count
self._files_list = self._create_files_list(files_list)
self._next_index = next_index
def __init__(self, files_list, thread_count, batch_size, numcep, numcontext, next_index=lambda x: x + 1):
self._coord = None
self._numcep = numcep
self._x = tf.placeholder(tf.float32, [None, numcep + (2 * numcep * numcontext)])
self._x_length = tf.placeholder(tf.int32, [])
self._y = tf.placeholder(tf.int32, [None,])
self._y_length = tf.placeholder(tf.int32, [])
self.example_queue = tf.PaddingFIFOQueue(shapes=[[None, numcep + (2 * numcep * numcontext)], [], [None,], []],
dtypes=[tf.float32, tf.int32, tf.int32, tf.int32],
capacity=2 * self._get_device_count() * batch_size)
self._enqueue_op = self.example_queue.enqueue([self._x, self._x_length, self._y, self._y_length])
self._close_op = self.example_queue.close(cancel_pending_enqueues=True)
self.batch_size = batch_size
self._numcontext = numcontext
self._thread_count = thread_count
self._files_list = self._create_files_list(files_list)
self._next_index = next_index
data_set_helpers_RHL_AVSR.py 文件源码
项目：AVSR-Deep-Speech
作者: pandeydivesh15
项目源码
文件源码
阅读 49
收藏 0
点赞 0
评论 0
def __init__(self, files_list, thread_count, batch_size, numcep, numcontext, next_index=lambda x: x + 1):
self._coord = None
self._numcep = numcep
self._x = tf.placeholder(tf.float32, [None, numcep + (2 * numcep * numcontext)])
self._x_length = tf.placeholder(tf.int32, [])
self._y = tf.placeholder(tf.int32, [None,])
self._y_length = tf.placeholder(tf.int32, [])
self.example_queue = tf.PaddingFIFOQueue(shapes=[[None, numcep + (2 * numcep * numcontext)], [], [None,], []],
dtypes=[tf.float32, tf.int32, tf.int32, tf.int32],
capacity=2 * self._get_device_count() * batch_size)
self._enqueue_op = self.example_queue.enqueue([self._x, self._x_length, self._y, self._y_length])
self._close_op = self.example_queue.close(cancel_pending_enqueues=True)
self.batch_size = batch_size
self._numcontext = numcontext
self._thread_count = thread_count
self._files_list = self._create_files_list(files_list)
self._next_index = next_index
def get_video_weights(video_id_batch):
video_id_to_index = tf.contrib.lookup.string_to_index_table_from_file(
vocabulary_file=FLAGS.sample_vocab_file, default_value=0)
indexes = video_id_to_index.lookup(video_id_batch)
weights, length = get_video_weights_array()
weights_input = tf.placeholder(tf.float32, shape=[length], name="sample_weights_input")
weights_tensor = tf.get_variable("sample_weights",
shape=[length],
trainable=False,
dtype=tf.float32,
initializer=tf.constant_initializer(weights))
weights_assignment = tf.assign(weights_tensor, weights_input)
tf.add_to_collection("weights_input", weights_input)
tf.add_to_collection("weights_assignment", weights_assignment)
video_weight_batch = tf.nn.embedding_lookup(weights_tensor, indexes)
return video_weight_batch
def get_video_weights(video_id_batch):
video_id_to_index = tf.contrib.lookup.string_to_index_table_from_file(
vocabulary_file=FLAGS.sample_vocab_file, default_value=0)
indexes = video_id_to_index.lookup(video_id_batch)
weights, length = get_video_weights_array()
weights_input = tf.placeholder(tf.float32, shape=[length], name="sample_weights_input")
weights_tensor = tf.get_variable("sample_weights",
shape=[length],
trainable=False,
dtype=tf.float32,
initializer=tf.constant_initializer(weights))
weights_assignment = tf.assign(weights_tensor, weights_input)
tf.add_to_collection("weights_input", weights_input)
tf.add_to_collection("weights_assignment", weights_assignment)
video_weight_batch = tf.nn.embedding_lookup(weights_tensor, indexes)
return video_weight_batch
def get_video_weights(video_id_batch):
video_id_to_index = tf.contrib.lookup.string_to_index_table_from_file(
vocabulary_file=FLAGS.sample_vocab_file, default_value=0)
indexes = video_id_to_index.lookup(video_id_batch)
weights, length = get_video_weights_array()
weights_input = tf.placeholder(tf.float32, shape=[length], name="sample_weights_input")
weights_tensor = tf.get_variable("sample_weights",
shape=[length],
trainable=False,
dtype=tf.float32,
initializer=tf.constant_initializer(weights))
weights_assignment = tf.assign(weights_tensor, weights_input)
tf.add_to_collection("weights_input", weights_input)
tf.add_to_collection("weights_assignment", weights_assignment)
video_weight_batch = tf.nn.embedding_lookup(weights_tensor, indexes)
return video_weight_batch
def get_video_weights(video_id_batch):
video_id_to_index = tf.contrib.lookup.string_to_index_table_from_file(
vocabulary_file=FLAGS.sample_vocab_file, default_value=0)
indexes = video_id_to_index.lookup(video_id_batch)
weights, length = get_video_weights_array()
weights_input = tf.placeholder(tf.float32, shape=[length], name="sample_weights_input")
weights_tensor = tf.get_variable("sample_weights",
shape=[length],
trainable=False,
dtype=tf.float32,
initializer=tf.constant_initializer(weights))
weights_assignment = tf.assign(weights_tensor, weights_input)
tf.add_to_collection("weights_input", weights_input)
tf.add_to_collection("weights_assignment", weights_assignment)
video_weight_batch = tf.nn.embedding_lookup(weights_tensor, indexes)
return video_weight_batch
def __init__(self, ob_space, ac_space, layers=[256], **kwargs):
self.x = x = tf.placeholder(tf.float32, [None] + list(ob_space))
rank = len(ob_space)
if rank == 3: # pixel input
for i in range(4):
x = tf.nn.elu(conv2d(x, 32, "c{}".format(i + 1), [3, 3], [2, 2]))
elif rank == 1: # plain features
#x = tf.nn.elu(linear(x, 256, "l1", normalized_columns_initializer(0.01)))
pass
else:
raise TypeError("observation space must have rank 1 or 3, got %d" % rank)
x = flatten(x)
for i, layer in enumerate(layers):
x = tf.nn.elu(linear(x, layer, "l{}".format(i + 1), tf.contrib.layers.xavier_initializer()))
self.logits = linear(x, ac_space, "action", tf.contrib.layers.xavier_initializer())
self.vf = tf.reshape(linear(x, 1, "value", tf.contrib.layers.xavier_initializer()), [-1])
self.sample = categorical_sample(self.logits, ac_space)[0, :]
self.var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, tf.get_variable_scope().name)
self.state_in = []
def __init__(self, ob_space, ac_space, layers=[256], **kwargs):
self.x = x = tf.placeholder(tf.float32, [None] + list(ob_space))
rank = len(ob_space)
if rank == 3: # pixel input
for i in range(4):
x = tf.nn.elu(conv2d(x, 32, "c{}".format(i + 1), [3, 3], [2, 2]))
elif rank == 1: # plain features
#x = tf.nn.elu(linear(x, 256, "l1", normalized_columns_initializer(0.01)))
pass
else:
raise TypeError("observation space must have rank 1 or 3, got %d" % rank)
x = flatten(x)
for i, layer in enumerate(layers):
x = tf.nn.elu(linear(x, layer, "l{}".format(i + 1), tf.contrib.layers.xavier_initializer()))
self.logits = linear(x, ac_space, "action", tf.contrib.layers.xavier_initializer())
self.vf = tf.reshape(linear(x, 1, "value", tf.contrib.layers.xavier_initializer()), [-1])
self.sample = categorical_sample(self.logits, ac_space)[0, :]
self.var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, tf.get_variable_scope().name)
self.state_in = []
def __init__(self, ob_space, ac_space, size=256, **kwargs):
self.x = x = tf.placeholder(tf.float32, [None] + list(ob_space))
for i in range(4):
x = tf.nn.elu(conv2d(x, 32, "l{}".format(i + 1), [3, 3], [2, 2]))
# introduce a "fake" batch dimension of 1 after flatten so that we can do GRU over time dim
x = tf.expand_dims(flatten(x), 1)
gru = rnn.GRUCell(size)
h_init = np.zeros((1, size), np.float32)
self.state_init = [h_init]
h_in = tf.placeholder(tf.float32, [1, size])
self.state_in = [h_in]
gru_outputs, gru_state = tf.nn.dynamic_rnn(
gru, x, initial_state=h_in, sequence_length=[size], time_major=True)
x = tf.reshape(gru_outputs, [-1, size])
self.logits = linear(x, ac_space, "action", normalized_columns_initializer(0.01))
self.vf = tf.reshape(linear(x, 1, "value", normalized_columns_initializer(1.0)), [-1])
self.state_out = [gru_state[:1]]
self.sample = categorical_sample(self.logits, ac_space)[0, :]
self.var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, tf.get_variable_scope().name)
def __init__(self, shape, name=None):
"""Takes input in uint8 format which is cast to float32 and divided by 255
before passing it to the model.
On GPU this ensures lower data transfer times.
Parameters
----------
shape: [int]
shape of the tensor.
name: str
name of the underlying placeholder
"""
super().__init__(tf.placeholder(tf.uint8, [None] + list(shape), name=name))
self._shape = shape
self._output = tf.cast(super().get(), tf.float32) / 255.0
def test_qrnn_linear_forward(self):
batch_size = 100
sentence_length = 5
word_size = 10
size = 5
data = self.create_test_data(batch_size, sentence_length, word_size)
with tf.Graph().as_default() as q_linear:
qrnn = QRNN(in_size=word_size, size=size, conv_size=1)
X = tf.placeholder(tf.float32, [batch_size, sentence_length, word_size])
forward_graph = qrnn.forward(X)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
hidden = sess.run(forward_graph, feed_dict={X: data})
self.assertEqual((batch_size, size), hidden.shape)
def test_qrnn_with_previous(self):
batch_size = 100
sentence_length = 5
word_size = 10
size = 5
data = self.create_test_data(batch_size, sentence_length, word_size)
with tf.Graph().as_default() as q_with_previous:
qrnn = QRNN(in_size=word_size, size=size, conv_size=2)
X = tf.placeholder(tf.float32, [batch_size, sentence_length, word_size])
forward_graph = qrnn.forward(X)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
hidden = sess.run(forward_graph, feed_dict={X: data})
self.assertEqual((batch_size, size), hidden.shape)
def test_qrnn_convolution(self):
batch_size = 100
sentence_length = 5
word_size = 10
size = 5
data = self.create_test_data(batch_size, sentence_length, word_size)
with tf.Graph().as_default() as q_conv:
qrnn = QRNN(in_size=word_size, size=size, conv_size=3)
X = tf.placeholder(tf.float32, [batch_size, sentence_length, word_size])
forward_graph = qrnn.forward(X)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
hidden = sess.run(forward_graph, feed_dict={X: data})
self.assertEqual((batch_size, size), hidden.shape)
def __init__(self, check_):
self.img_feed = tf.placeholder(tf.float32)
self.output_logits = tf.nn.softmax(
models.foodv_test(
self.img_feed,
reg_val=0.0,
is_train=False,
dropout_p=1.0))
self.sess = tf.Session()
self.checkpoint_name = check_
saver = tf.train.Saver()
print("loading model...")
saver.restore(self.sess, self.checkpoint_name)
print("Model loaded !")
def __init__(self, embedding):
self.sess = tf.Session()
self.inputs = tf.placeholder(tf.float32,
[None, embedding.shape[1]],
name='inputs')
self.test_vec = tf.placeholder(tf.float32, [1, embedding.shape[1]],
name='test_vec')
self.cos_distance = tf.matmul(self.inputs, tf.transpose(self.test_vec))
#-----------------------------------------------------------------------
# Compute normalized embedding matrix
#-----------------------------------------------------------------------
row_sum = tf.reduce_sum(tf.square(self.inputs), axis=1,
keep_dims=True)
norm = tf.sqrt(row_sum)
self.normalized = self.inputs / norm
self.embedding = self.sess.run(self.normalized,
feed_dict={self.inputs: embedding})
#---------------------------------------------------------------------------
def __init__(self, rnd_vec_dim, hidden_units, output_dim, alpha):
#-----------------------------------------------------------------------
# Inputs
#-----------------------------------------------------------------------
self.inputs_rnd = tf.placeholder(tf.float32, (None, rnd_vec_dim),
name='inputs_rnd')
#-----------------------------------------------------------------------
# The generator
#-----------------------------------------------------------------------
self.alpha = alpha
with tf.variable_scope('generator'):
h1 = tf.layers.dense(self.inputs_rnd, hidden_units, activation=None)
h1 = LeakyReLU(h1, self.alpha)
self.gen_logits = tf.layers.dense(h1, output_dim, activation=None)
self.gen_out = tf.tanh(self.gen_logits)
#---------------------------------------------------------------------------
def __init__(self, name='model', sess=None):
assert sess != None
self.name = name
self.sess = sess
self.x = tf.placeholder(tf.float32, [None, img_dim[0], img_dim[1], img_dim[2]], name='Observaion')
self.y = tf.placeholder(tf.float32, [None, n_action], name='Steer')
self._build_net(True, False)
self._build_net(False, True)
self._define_train_ops()
tl.layers.initialize_global_variables(self.sess)
print()
self.n_test.print_layers()
print()
self.n_test.print_params(False)
print()
# exit()
def build_model(self):
Z = tf.placeholder(tf.float32, [self.batch_size, self.dim_z])
Y = tf.placeholder(tf.float32, [self.batch_size, self.dim_y])
image_real = tf.placeholder(tf.float32, [self.batch_size]+self.image_shape)
h4 = self.generate(Z,Y)
#image_gen comes from sigmoid output of generator
image_gen = tf.nn.sigmoid(h4)
raw_real2 = self.discriminate(image_real, Y)
#p_real = tf.nn.sigmoid(raw_real)
p_real=tf.reduce_mean(raw_real2)
raw_gen2 = self.discriminate(image_gen, Y)
#p_gen = tf.nn.sigmoid(raw_gen)
p_gen = tf.reduce_mean(raw_gen2)
discrim_cost = tf.reduce_sum(raw_real2) - tf.reduce_sum(raw_gen2)
gen_cost = -tf.reduce_mean(raw_gen2)
return Z, Y, image_real, discrim_cost, gen_cost, p_real, p_gen
def samples_generator(self, batch_size):
Z = tf.placeholder(tf.float32, [batch_size, self.dim_z])
Y = tf.placeholder(tf.float32, [batch_size, self.dim_y])
yb = tf.reshape(Y, [batch_size, 1, 1, self.dim_y])
Z_ = tf.concat([Z,Y], 1)
h1 = tf.nn.relu(batchnormalize(tf.matmul(Z_, self.gen_W1)))
h1 = tf.concat([h1, Y], 1)
h2 = tf.nn.relu(batchnormalize(tf.matmul(h1, self.gen_W2)))
h2 = tf.reshape(h2, [batch_size,6,6,self.dim_W2])
h2 = tf.concat([h2, yb*tf.ones([batch_size, 6,6, self.dim_y])], 3)
output_shape_l3 = [batch_size,12,12,self.dim_W3]
h3 = tf.nn.conv2d_transpose(h2, self.gen_W3, output_shape=output_shape_l3, strides=[1,2,2,1])
h3 = tf.nn.relu( batchnormalize(h3) )
h3 = tf.concat([h3, yb*tf.ones([batch_size, 12,12,self.dim_y])], 3)
output_shape_l4 = [batch_size,24,24,self.dim_channel]
h4 = tf.nn.conv2d_transpose(h3, self.gen_W4, output_shape=output_shape_l4, strides=[1,2,2,1])
x = tf.nn.sigmoid(h4)
return Z, Y, x
def __init__(self, channels=3, n_class=2, cost="cross_entropy", cost_kwargs={}, **kwargs):
tf.reset_default_graph()
self.n_class = n_class
self.summaries = kwargs.get("summaries", True)
self.x = tf.placeholder("float", shape=[None, None, None, channels])
self.y = tf.placeholder("float", shape=[None, None, None, n_class])
self.keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
logits, self.variables, self.offset = create_conv_net(self.x, self.keep_prob, channels, n_class, **kwargs)
self.cost = self._get_cost(logits, cost, cost_kwargs)
self.gradients_node = tf.gradients(self.cost, self.variables)
self.cross_entropy = tf.reduce_mean(cross_entropy(tf.reshape(self.y, [-1, n_class]),
tf.reshape(pixel_wise_softmax_2(logits), [-1, n_class])))
self.predicter = pixel_wise_softmax_2(logits)
self.correct_pred = tf.equal(tf.argmax(self.predicter, 3), tf.argmax(self.y, 3))
self.accuracy = tf.reduce_mean(tf.cast(self.correct_pred, tf.float32))
def __init__(self,
name,
size_input__layer,
size_hidden_layer,
size_output_layer,
l2_coeff,
keep_prob,
optimizer='SGD'):
"""Make new tensors and connect them."""
self.size_input__layer = size_input__layer
self.size_hidden_layer = size_hidden_layer
self.size_output_layer = size_output_layer
self.keep_prob = keep_prob
self.input__placeholder = tf.placeholder(tf.float32, shape=(None, size_input__layer))
self.answer_placeholder = tf.placeholder(tf.float32, shape=(None, size_output_layer))
self.learning_rate = tf.placeholder(tf.float32)
self.inference_proc, l2_proc = self.inference(self.input__placeholder, name)
self.loss_proc = NN.loss(self.inference_proc, l2_proc, l2_coeff, self.answer_placeholder)
self.training_proc = NN.training(self.loss_proc, self.learning_rate, optimizer)
def _build_graph(self, image_size):
self.image_size = image_size
self.images = tf.placeholder(tf.float32,
shape = (None, image_size, image_size, 3))
images_mini = tf.image.resize_images(self.images,
size = (int(image_size/4),
int(image_size/4)))
self.images_blur = tf.image.resize_images(images_mini,
size = (image_size, image_size))
self.net = U_Net(output_ch = 3, block_fn = 'origin')
self.images_reconst = self.net(self.images_blur, reuse = False)
# self.image_reconst can be [-inf +inf], so need to clip its value if visualize them as images.
self.loss = tf.reduce_mean((self.images_reconst - self.images)**2)
self.opt = tf.train.AdamOptimizer()\
.minimize(self.loss, var_list = self.net.vars)
self.saver = tf.train.Saver()
self.sess.run(tf.global_variables_initializer())
def predictPL(self):
B = self.flags.batch_size
W,H,C = self.flags.width, self.flags.height, self.flags.color
inputs = tf.placeholder(dtype=tf.float32,shape=[None,H,W,C])
#with open(self.flags.pred_path,'w') as f:
# pass
self._build(inputs,resize=False)
counter = 0
with tf.Session() as sess:
self.sess = sess
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
for imgs,imgnames in self.DATA.test_generator():
pred = sess.run(self.logit,feed_dict={inputs:imgs})
np.save("%s/%d.npy"%(self.flags.pred_path,counter),{"pred":pred,"name":imgnames})
counter+=len(imgs)
if counter/B%10 ==0:
print_mem_time("%d images predicted"%counter)
# train with placeholders
