Skip to content

GitLab

Commit 052e5e8b authored by Neal Wu's avatar Neal Wu
Browse files

Converted the models repo to TF 1.0 using the upgrade script

parent f21c4278
Hide whitespace changes
Inline Side-by-side
Showing with 111 additions and 111 deletions
inception/inception/slim/ops.py
View file @ 052e5e8b
...@@ -331,9 +331,9 @@ def one_hot_encoding(labels, num_classes, scope=None): ...@@ -331,9 +331,9 @@ def one_hot_encoding(labels, num_classes, scope=None):
batch_size = labels.get_shape()[0] batch_size = labels.get_shape()[0]
indices = tf.expand_dims(tf.range(0, batch_size), 1) indices = tf.expand_dims(tf.range(0, batch_size), 1)
labels = tf.cast(tf.expand_dims(labels, 1), indices.dtype) labels = tf.cast(tf.expand_dims(labels, 1), indices.dtype)
concated = tf.concat([indices, labels], 1) concated = tf.concat(axis=[indices, labels], values=1)
onehot_labels = tf.sparse_to_dense( onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, num_classes]), 1.0, 0.0) concated, tf.stack([batch_size, num_classes]), 1.0, 0.0)
onehot_labels.set_shape([batch_size, num_classes]) onehot_labels.set_shape([batch_size, num_classes])
return onehot_labels return onehot_labels
......
inception/inception/slim/variables.py
View file @ 052e5e8b
...@@ -240,7 +240,7 @@ def global_step(device=''): ...@@ -240,7 +240,7 @@ def global_step(device=''):
# Get the device for the variable. # Get the device for the variable.
with tf.device(variable_device(device, 'global_step')): with tf.device(variable_device(device, 'global_step')):
return tf.get_variable('global_step', shape=[], dtype=tf.int64, return tf.get_variable('global_step', shape=[], dtype=tf.int64,
initializer=tf.zeros_initializer, initializer=tf.zeros_initializer(),
trainable=False, collections=collections) trainable=False, collections=collections)
......
namignizer/model.py
View file @ 052e5e8b
...@@ -64,7 +64,7 @@ class NamignizerModel(object): ...@@ -64,7 +64,7 @@ class NamignizerModel(object):
(cell_output, state) = cell(inputs[:, time_step, :], state) (cell_output, state) = cell(inputs[:, time_step, :], state)
outputs.append(cell_output) outputs.append(cell_output)
output = tf.reshape(tf.concat(outputs, 1), [-1, size]) output = tf.reshape(tf.concat(axis=1, values=outputs), [-1, size])
softmax_w = tf.get_variable("softmax_w", [size, vocab_size]) softmax_w = tf.get_variable("softmax_w", [size, vocab_size])
softmax_b = tf.get_variable("softmax_b", [vocab_size]) softmax_b = tf.get_variable("softmax_b", [vocab_size])
logits = tf.matmul(output, softmax_w) + softmax_b logits = tf.matmul(output, softmax_w) + softmax_b
......
neural_gpu/neural_gpu.py
View file @ 052e5e8b
...@@ -36,7 +36,7 @@ def conv_linear(args, kw, kh, nin, nout, rate, do_bias, bias_start, prefix): ...@@ -36,7 +36,7 @@ def conv_linear(args, kw, kh, nin, nout, rate, do_bias, bias_start, prefix):
if len(args) == 1: if len(args) == 1:
arg = args[0] arg = args[0]
else: else:
arg = tf.concat(args, 3) arg = tf.concat(axis=args, values=3)
res = tf.nn.convolution(arg, k, dilation_rate=(rate, 1), padding="SAME") res = tf.nn.convolution(arg, k, dilation_rate=(rate, 1), padding="SAME")
if not do_bias: return res if not do_bias: return res
with tf.device("/cpu:0"): with tf.device("/cpu:0"):
...@@ -71,14 +71,14 @@ def place_at14(decided, selected, it): ...@@ -71,14 +71,14 @@ def place_at14(decided, selected, it):
"""Place selected at it-th coordinate of decided, dim=1 of 4.""" """Place selected at it-th coordinate of decided, dim=1 of 4."""
slice1 = decided[:, :it, :, :] slice1 = decided[:, :it, :, :]
slice2 = decided[:, it + 1:, :, :] slice2 = decided[:, it + 1:, :, :]
return tf.concat([slice1, selected, slice2], 1) return tf.concat(axis=[slice1, selected, slice2], values=1)
def place_at13(decided, selected, it): def place_at13(decided, selected, it):
"""Place selected at it-th coordinate of decided, dim=1 of 3.""" """Place selected at it-th coordinate of decided, dim=1 of 3."""
slice1 = decided[:, :it, :] slice1 = decided[:, :it, :]
slice2 = decided[:, it + 1:, :] slice2 = decided[:, it + 1:, :]
return tf.concat([slice1, selected, slice2], 1) return tf.concat(axis=[slice1, selected, slice2], values=1)
def tanh_cutoff(x, cutoff): def tanh_cutoff(x, cutoff):
...@@ -211,7 +211,7 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first, ...@@ -211,7 +211,7 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first,
# beam_val is [batch_size x beam_size]; let b = batch_size * beam_size # beam_val is [batch_size x beam_size]; let b = batch_size * beam_size
# decided is len x b x a x b # decided is len x b x a x b
# output is b x out_size; step is b x len x a x b; # output is b x out_size; step is b x len x a x b;
outputs = tf.split(tf.nn.log_softmax(output), beam_size, 0) outputs = tf.split(axis=tf.nn.log_softmax(output), num_or_size_splits=beam_size, value=0)
all_beam_vals, all_beam_idx = [], [] all_beam_vals, all_beam_idx = [], []
beam_range = 1 if is_first else beam_size beam_range = 1 if is_first else beam_size
for i in xrange(beam_range): for i in xrange(beam_range):
...@@ -221,9 +221,9 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first, ...@@ -221,9 +221,9 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first,
cur_beam_val], "GREPO", summarize=8) cur_beam_val], "GREPO", summarize=8)
all_beam_vals.append(top_out + tf.expand_dims(cur_beam_val, 1)) all_beam_vals.append(top_out + tf.expand_dims(cur_beam_val, 1))
all_beam_idx.append(top_out_idx) all_beam_idx.append(top_out_idx)
all_beam_idx = tf.reshape(tf.transpose(tf.concat(all_beam_idx, 1), [1, 0]), all_beam_idx = tf.reshape(tf.transpose(tf.concat(axis=all_beam_idx, values=1), [1, 0]),
[-1]) [-1])
top_beam, top_beam_idx = tf.nn.top_k(tf.concat(all_beam_vals, 1), k=beam_size) top_beam, top_beam_idx = tf.nn.top_k(tf.concat(axis=all_beam_vals, values=1), k=beam_size)
top_beam_idx = tf.Print(top_beam_idx, [top_beam, top_beam_idx], top_beam_idx = tf.Print(top_beam_idx, [top_beam, top_beam_idx],
"GREP", summarize=8) "GREP", summarize=8)
reordered = [[] for _ in xrange(len(tensors_to_reorder) + 1)] reordered = [[] for _ in xrange(len(tensors_to_reorder) + 1)]
...@@ -236,8 +236,8 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first, ...@@ -236,8 +236,8 @@ def reorder_beam(beam_size, batch_size, beam_val, output, is_first,
reordered[0].append(tf.gather(output, which_beam)) reordered[0].append(tf.gather(output, which_beam))
for i, t in enumerate(tensors_to_reorder): for i, t in enumerate(tensors_to_reorder):
reordered[i + 1].append(tf.gather(t, which_beam)) reordered[i + 1].append(tf.gather(t, which_beam))
new_tensors = [tf.concat(t, 0) for t in reordered] new_tensors = [tf.concat(axis=t, values=0) for t in reordered]
top_out_idx = tf.concat(top_out_idx, 0) top_out_idx = tf.concat(axis=top_out_idx, values=0)
return (top_beam, new_tensors[0], top_out_idx, new_tensors[1:]) return (top_beam, new_tensors[0], top_out_idx, new_tensors[1:])
...@@ -266,9 +266,9 @@ class NeuralGPU(object): ...@@ -266,9 +266,9 @@ class NeuralGPU(object):
self.input = tf.placeholder(tf.int32, name="inp") self.input = tf.placeholder(tf.int32, name="inp")
self.target = tf.placeholder(tf.int32, name="tgt") self.target = tf.placeholder(tf.int32, name="tgt")
self.prev_step = tf.placeholder(tf.float32, name="prev_step") self.prev_step = tf.placeholder(tf.float32, name="prev_step")
gpu_input = tf.split(self.input, num_gpus, 0) gpu_input = tf.split(axis=self.input, num_or_size_splits=num_gpus, value=0)
gpu_target = tf.split(self.target, num_gpus, 0) gpu_target = tf.split(axis=self.target, num_or_size_splits=num_gpus, value=0)
gpu_prev_step = tf.split(self.prev_step, num_gpus, 0) gpu_prev_step = tf.split(axis=self.prev_step, num_or_size_splits=num_gpus, value=0)
batch_size = tf.shape(gpu_input[0])[0] batch_size = tf.shape(gpu_input[0])[0]
if backward: if backward:
...@@ -410,7 +410,7 @@ class NeuralGPU(object): ...@@ -410,7 +410,7 @@ class NeuralGPU(object):
out_write = output_ta.write(it, output_l[:batch_size, :, :, :]) out_write = output_ta.write(it, output_l[:batch_size, :, :, :])
output = tf.gather(target_emb_weights, out) output = tf.gather(target_emb_weights, out)
output = tf.reshape(output, [-1, 1, nmaps]) output = tf.reshape(output, [-1, 1, nmaps])
output = tf.concat([output] * height, 1) output = tf.concat(axis=[output] * height, values=1)
tgt = tgts[it, :, :, :] tgt = tgts[it, :, :, :]
selected = tf.cond(tf.less(tf.random_uniform([]), self.sampling), selected = tf.cond(tf.less(tf.random_uniform([]), self.sampling),
lambda: output, lambda: tgt) lambda: output, lambda: tgt)
...@@ -419,7 +419,7 @@ class NeuralGPU(object): ...@@ -419,7 +419,7 @@ class NeuralGPU(object):
out_idx = place_at13( out_idx = place_at13(
out_idx, tf.reshape(out, [beam_size * batch_size, 1, 1]), it) out_idx, tf.reshape(out, [beam_size * batch_size, 1, 1]), it)
if mem_size > 0: if mem_size > 0:
mem = tf.concat([mem] * height, 2) mem = tf.concat(axis=[mem] * height, values=2)
dec_write = place_at14(dec_write, mem, it_incr) dec_write = place_at14(dec_write, mem, it_incr)
return (step, dec_write, out_write, mloss + mem_loss, nupd_in + nupd, return (step, dec_write, out_write, mloss + mem_loss, nupd_in + nupd,
out_idx, beam_cost) out_idx, beam_cost)
...@@ -459,7 +459,7 @@ class NeuralGPU(object): ...@@ -459,7 +459,7 @@ class NeuralGPU(object):
gpu_targets_tn) gpu_targets_tn)
embedded_targets_tn = tf.transpose( embedded_targets_tn = tf.transpose(
embedded_targets_tn, [2, 0, 1, 3]) # len x b x 1 x nmaps embedded_targets_tn, [2, 0, 1, 3]) # len x b x 1 x nmaps
embedded_targets_tn = tf.concat([embedded_targets_tn] * height, 2) embedded_targets_tn = tf.concat(axis=[embedded_targets_tn] * height, values=2)
# First image comes from start by applying convolution and adding 0s. # First image comes from start by applying convolution and adding 0s.
start = tf.transpose(start, [0, 2, 1, 3]) # Now b x len x h x vec_s start = tf.transpose(start, [0, 2, 1, 3]) # Now b x len x h x vec_s
...@@ -505,7 +505,7 @@ class NeuralGPU(object): ...@@ -505,7 +505,7 @@ class NeuralGPU(object):
attn_res = attention_query(attn_q, tf.get_variable( attn_res = attention_query(attn_q, tf.get_variable(
"attn_v", [height * nmaps], "attn_v", [height * nmaps],
initializer=tf.random_uniform_initializer(-0.1, 0.1))) initializer=tf.random_uniform_initializer(-0.1, 0.1)))
concatenated = tf.reshape(tf.concat([cell_inp, attn_res], 1), concatenated = tf.reshape(tf.concat(axis=[cell_inp, attn_res], values=1),
[batch_size, 2 * height * nmaps]) [batch_size, 2 * height * nmaps])
cell_inp = tf.layers.dense( cell_inp = tf.layers.dense(
concatenated, height * nmaps, name="attn_merge") concatenated, height * nmaps, name="attn_merge")
...@@ -519,14 +519,14 @@ class NeuralGPU(object): ...@@ -519,14 +519,14 @@ class NeuralGPU(object):
res = tf.gather(target_emb_weights, res) res = tf.gather(target_emb_weights, res)
res *= tf.expand_dims(mask[:, 0], 1) res *= tf.expand_dims(mask[:, 0], 1)
output = tf.layers.dense( output = tf.layers.dense(
tf.concat([output, res], 1), height * nmaps, name="rnnmem") tf.concat(axis=[output, res], values=1), height * nmaps, name="rnnmem")
return new_state, output, mem_loss return new_state, output, mem_loss
# pylint: enable=cell-var-from-loop # pylint: enable=cell-var-from-loop
gpu_targets = tf.squeeze(gpu_target[gpu], [1]) # b x len gpu_targets = tf.squeeze(gpu_target[gpu], [1]) # b x len
gpu_tgt_trans = tf.transpose(gpu_targets, [1, 0]) gpu_tgt_trans = tf.transpose(gpu_targets, [1, 0])
dec_zero = tf.zeros([batch_size, 1], dtype=tf.int32) dec_zero = tf.zeros([batch_size, 1], dtype=tf.int32)
dec_inp = tf.concat([dec_zero, gpu_targets], 1) dec_inp = tf.concat(axis=[dec_zero, gpu_targets], values=1)
dec_inp = dec_inp[:, :length] dec_inp = dec_inp[:, :length]
embedded_dec_inp = tf.gather(target_emb_weights, dec_inp) embedded_dec_inp = tf.gather(target_emb_weights, dec_inp)
embedded_dec_inp_proj = tf.layers.dense( embedded_dec_inp_proj = tf.layers.dense(
...@@ -573,9 +573,9 @@ class NeuralGPU(object): ...@@ -573,9 +573,9 @@ class NeuralGPU(object):
height, vec_size]) height, vec_size])
# Prepare for beam search. # Prepare for beam search.
tgts = tf.concat([embedded_targets_tn] * beam_size, 1) tgts = tf.concat(axis=[embedded_targets_tn] * beam_size, values=1)
beam_cost = tf.zeros([batch_size, beam_size]) beam_cost = tf.zeros([batch_size, beam_size])
step = tf.concat([step] * beam_size, 0) step = tf.concat(axis=[step] * beam_size, values=0)
# First step hard-coded. # First step hard-coded.
step, decided_t, output_ta, mem_loss, nupd, oi, bc = dec_step( step, decided_t, output_ta, mem_loss, nupd, oi, bc = dec_step(
step, 0, 0, decided_t, output_ta, tgts, 0.0, 0, out_idx, step, 0, 0, decided_t, output_ta, tgts, 0.0, 0, out_idx,
...@@ -654,7 +654,7 @@ class NeuralGPU(object): ...@@ -654,7 +654,7 @@ class NeuralGPU(object):
% (gpu, time.time() - start_time)) % (gpu, time.time() - start_time))
self.updates = [] self.updates = []
self.after_enc_step = tf.concat(self.after_enc_step, 0) # Concat GPUs. self.after_enc_step = tf.concat(axis=self.after_enc_step, values=0) # Concat GPUs.
if backward: if backward:
tf.get_variable_scope()._reuse = False tf.get_variable_scope()._reuse = False
tf.get_variable_scope().set_caching_device(None) tf.get_variable_scope().set_caching_device(None)
...@@ -667,10 +667,10 @@ class NeuralGPU(object): ...@@ -667,10 +667,10 @@ class NeuralGPU(object):
self.losses = [gpu_avg([gpu_losses[g][i] for g in xrange(num_gpus)]) self.losses = [gpu_avg([gpu_losses[g][i] for g in xrange(num_gpus)])
for i in xrange(len(gpu_losses[0]))] for i in xrange(len(gpu_losses[0]))]
self.out_idx = tf.concat(gpu_out_idx, 0) self.out_idx = tf.concat(axis=gpu_out_idx, values=0)
self.grad_norms = [gpu_avg([gpu_grad_norms[g][i] for g in xrange(num_gpus)]) self.grad_norms = [gpu_avg([gpu_grad_norms[g][i] for g in xrange(num_gpus)])
for i in xrange(len(gpu_grad_norms[0]))] for i in xrange(len(gpu_grad_norms[0]))]
self.outputs = [tf.concat([gpu_outputs[g] for g in xrange(num_gpus)], 1)] self.outputs = [tf.concat(axis=[gpu_outputs[g] for g in xrange(num_gpus)], values=1)]
self.quantize_op = quantize_weights_op(512, 8) self.quantize_op = quantize_weights_op(512, 8)
if backward: if backward:
self.saver = tf.train.Saver(tf.global_variables(), max_to_keep=10) self.saver = tf.train.Saver(tf.global_variables(), max_to_keep=10)
......
neural_programmer/data_utils.py 100755 → 100644
View file @ 052e5e8b
File mode changed from 100755 to 100644
neural_programmer/model.py 100755 → 100644
View file @ 052e5e8b
...@@ -121,14 +121,14 @@ class Graph(): ...@@ -121,14 +121,14 @@ class Graph():
if (self.utility.FLAGS.rnn_dropout > 0.0): if (self.utility.FLAGS.rnn_dropout > 0.0):
question_hidden = question_hidden * rnn_dropout_mask question_hidden = question_hidden * rnn_dropout_mask
hidden_vectors.append(tf.expand_dims(question_hidden, 0)) hidden_vectors.append(tf.expand_dims(question_hidden, 0))
hidden_vectors = tf.concat(0, hidden_vectors) hidden_vectors = tf.concat(axis=0, values=hidden_vectors)
return question_hidden, hidden_vectors return question_hidden, hidden_vectors
def history_recurrent_step(self, curr_hprev, hprev): def history_recurrent_step(self, curr_hprev, hprev):
#A single RNN step for controller or history RNN #A single RNN step for controller or history RNN
return tf.tanh( return tf.tanh(
tf.matmul( tf.matmul(
tf.concat(1, [hprev, curr_hprev]), self.params[ tf.concat(axis=1, values=[hprev, curr_hprev]), self.params[
"history_recurrent"])) + self.params["history_recurrent_bias"] "history_recurrent"])) + self.params["history_recurrent_bias"]
def question_number_softmax(self, hidden_vectors): def question_number_softmax(self, hidden_vectors):
...@@ -150,13 +150,13 @@ class Graph(): ...@@ -150,13 +150,13 @@ class Graph():
tf.expand_dims( tf.expand_dims(
tf.transpose(self.batch_ordinal_question_one), 2 tf.transpose(self.batch_ordinal_question_one), 2
), [1, 1, self.utility.FLAGS.embedding_dims]), 0)))) ), [1, 1, self.utility.FLAGS.embedding_dims]), 0))))
question_number_softmax = tf.nn.softmax(tf.concat(1, [first, second])) question_number_softmax = tf.nn.softmax(tf.concat(axis=1, values=[first, second]))
if (self.mode == "test"): if (self.mode == "test"):
cond = tf.equal(question_number_softmax, cond = tf.equal(question_number_softmax,
tf.reshape( tf.reshape(
tf.reduce_max(question_number_softmax, 1), tf.reduce_max(question_number_softmax, 1),
[self.batch_size, 1])) [self.batch_size, 1]))
question_number_softmax = tf.select( question_number_softmax = tf.where(
cond, cond,
tf.fill(tf.shape(question_number_softmax), 1.0), tf.fill(tf.shape(question_number_softmax), 1.0),
tf.fill(tf.shape(question_number_softmax), 0.0)) tf.fill(tf.shape(question_number_softmax), 0.0))
...@@ -164,7 +164,7 @@ class Graph(): ...@@ -164,7 +164,7 @@ class Graph():
self.data_type) self.data_type)
ans = tf.reshape( ans = tf.reshape(
tf.reduce_sum(question_number_softmax * tf.concat( tf.reduce_sum(question_number_softmax * tf.concat(
1, [self.batch_question_number, self.batch_question_number_one]), axis=1, values=[self.batch_question_number, self.batch_question_number_one]),
1), [self.batch_size, 1]) 1), [self.batch_size, 1])
return ans return ans
...@@ -225,7 +225,7 @@ class Graph(): ...@@ -225,7 +225,7 @@ class Graph():
column_controller_vector = nn_utils.apply_dropout( column_controller_vector = nn_utils.apply_dropout(
column_controller_vector, self.utility.FLAGS.dropout, self.mode) column_controller_vector, self.utility.FLAGS.dropout, self.mode)
self.full_column_hidden_vectors = tf.concat( self.full_column_hidden_vectors = tf.concat(
1, [self.column_hidden_vectors, self.word_column_hidden_vectors]) axis=1, values=[self.column_hidden_vectors, self.word_column_hidden_vectors])
self.full_column_hidden_vectors += self.summary_text_entry_embeddings self.full_column_hidden_vectors += self.summary_text_entry_embeddings
self.full_column_hidden_vectors = nn_utils.apply_dropout( self.full_column_hidden_vectors = nn_utils.apply_dropout(
self.full_column_hidden_vectors, self.utility.FLAGS.dropout, self.mode) self.full_column_hidden_vectors, self.utility.FLAGS.dropout, self.mode)
...@@ -258,7 +258,7 @@ class Graph(): ...@@ -258,7 +258,7 @@ class Graph():
temp_ans.append(curr_prob) temp_ans.append(curr_prob)
else: else:
temp_ans.append(tf.zeros_like(curr_prob)) temp_ans.append(tf.zeros_like(curr_prob))
temp_ans = tf.transpose(tf.concat(0, temp_ans)) temp_ans = tf.transpose(tf.concat(axis=0, values=temp_ans))
answer += temp_ans answer += temp_ans
return answer return answer
...@@ -266,7 +266,7 @@ class Graph(): ...@@ -266,7 +266,7 @@ class Graph():
#converts soft selection to hard selection. used at test time #converts soft selection to hard selection. used at test time
cond = tf.equal( cond = tf.equal(
softmax, tf.reshape(tf.reduce_max(softmax, 1), [self.batch_size, 1])) softmax, tf.reshape(tf.reduce_max(softmax, 1), [self.batch_size, 1]))
softmax = tf.select( softmax = tf.where(
cond, tf.fill(tf.shape(softmax), 1.0), tf.fill(tf.shape(softmax), 0.0)) cond, tf.fill(tf.shape(softmax), 1.0), tf.fill(tf.shape(softmax), 0.0))
softmax = tf.cast(softmax, self.data_type) softmax = tf.cast(softmax, self.data_type)
return softmax return softmax
...@@ -297,7 +297,7 @@ class Graph(): ...@@ -297,7 +297,7 @@ class Graph():
curr_prob = curr_prob * tf.expand_dims((1 - sum_prob), 2) curr_prob = curr_prob * tf.expand_dims((1 - sum_prob), 2)
curr_prob = curr_prob * tf.expand_dims( curr_prob = curr_prob * tf.expand_dims(
tf.cast((1 - sum_prob) > 0.0, self.data_type), 2) tf.cast((1 - sum_prob) > 0.0, self.data_type), 2)
answer = tf.select(select_mask, curr_prob, answer) answer = tf.where(select_mask, curr_prob, answer)
sum_prob += tf.reduce_sum(curr_prob, 2) sum_prob += tf.reduce_sum(curr_prob, 2)
return answer return answer
...@@ -335,11 +335,11 @@ class Graph(): ...@@ -335,11 +335,11 @@ class Graph():
1) #BS * max_elements 1) #BS * max_elements
select_min = tf.reduce_sum(init_min * select_full_column_softmax, select_min = tf.reduce_sum(init_min * select_full_column_softmax,
1) #BS * max_elements 1) #BS * max_elements
select_prev = tf.concat(1, [ select_prev = tf.concat(axis=1, values=[
tf.slice(select, [0, 1], [self.batch_size, self.max_elements - 1]), tf.slice(select, [0, 1], [self.batch_size, self.max_elements - 1]),
tf.cast(tf.zeros([self.batch_size, 1]), self.data_type) tf.cast(tf.zeros([self.batch_size, 1]), self.data_type)
]) ])
select_next = tf.concat(1, [ select_next = tf.concat(axis=1, values=[
tf.cast(tf.zeros([self.batch_size, 1]), self.data_type), tf.slice( tf.cast(tf.zeros([self.batch_size, 1]), self.data_type), tf.slice(
select, [0, 0], [self.batch_size, self.max_elements - 1]) select, [0, 0], [self.batch_size, self.max_elements - 1])
]) ])
...@@ -352,11 +352,11 @@ class Graph(): ...@@ -352,11 +352,11 @@ class Graph():
length_content = 1 length_content = 1
length_select = 13 length_select = 13
length_print = 1 length_print = 1
values = tf.concat(1, [count]) values = tf.concat(axis=1, values=[count])
softmax_content = tf.slice(softmax, [0, 0], softmax_content = tf.slice(softmax, [0, 0],
[self.batch_size, length_content]) [self.batch_size, length_content])
#compute scalar output #compute scalar output
output = tf.reduce_sum(tf.mul(softmax_content, values), 1) output = tf.reduce_sum(tf.multiply(softmax_content, values), 1)
#compute lookup answer #compute lookup answer
softmax_print = tf.slice(softmax, [0, length_content + length_select], softmax_print = tf.slice(softmax, [0, length_content + length_select],
[self.batch_size, length_print]) [self.batch_size, length_print])
...@@ -384,7 +384,7 @@ class Graph(): ...@@ -384,7 +384,7 @@ class Graph():
] ]
select = tf.reduce_sum( select = tf.reduce_sum(
tf.tile(tf.expand_dims(softmax_select, 2), [1, 1, self.max_elements]) * tf.tile(tf.expand_dims(softmax_select, 2), [1, 1, self.max_elements]) *
tf.concat(1, select_lists), 1) tf.concat(axis=1, values=select_lists), 1)
select = select * self.select_whole_mask select = select * self.select_whole_mask
return output, select return output, select
...@@ -396,11 +396,11 @@ class Graph(): ...@@ -396,11 +396,11 @@ class Graph():
self.batch_question_attention_mask) #batch_size * embedding_dims self.batch_question_attention_mask) #batch_size * embedding_dims
controller_vector = tf.nn.relu( controller_vector = tf.nn.relu(
tf.matmul(hprev, self.params["controller_prev"]) + tf.matmul( tf.matmul(hprev, self.params["controller_prev"]) + tf.matmul(
tf.concat(1, [question_embedding, attention_vector]), self.params[ tf.concat(axis=1, values=[question_embedding, attention_vector]), self.params[
"controller"])) "controller"]))
column_controller_vector = tf.nn.relu( column_controller_vector = tf.nn.relu(
tf.matmul(hprev, self.params["column_controller_prev"]) + tf.matmul( tf.matmul(hprev, self.params["column_controller_prev"]) + tf.matmul(
tf.concat(1, [question_embedding, attention_vector]), self.params[ tf.concat(axis=1, values=[question_embedding, attention_vector]), self.params[
"column_controller"])) "column_controller"]))
controller_vector = nn_utils.apply_dropout( controller_vector = nn_utils.apply_dropout(
controller_vector, self.utility.FLAGS.dropout, self.mode) controller_vector, self.utility.FLAGS.dropout, self.mode)
...@@ -413,7 +413,7 @@ class Graph(): ...@@ -413,7 +413,7 @@ class Graph():
tf.matmul(tf.transpose(self.params_unit), tf.transpose(softmax))) tf.matmul(tf.transpose(self.params_unit), tf.transpose(softmax)))
column_controller_vector = tf.nn.relu( column_controller_vector = tf.nn.relu(
tf.matmul( tf.matmul(
tf.concat(1, [ tf.concat(axis=1, values=[
column_controller_vector, weighted_op_representation column_controller_vector, weighted_op_representation
]), self.params["break_conditional"])) ]), self.params["break_conditional"]))
full_column_softmax = self.compute_column_softmax(column_controller_vector, full_column_softmax = self.compute_column_softmax(column_controller_vector,
...@@ -429,7 +429,7 @@ class Graph(): ...@@ -429,7 +429,7 @@ class Graph():
def compute_lookup_error(self, val): def compute_lookup_error(self, val):
#computes lookup error. #computes lookup error.
cond = tf.equal(self.batch_print_answer, val) cond = tf.equal(self.batch_print_answer, val)
inter = tf.select( inter = tf.where(
cond, self.init_print_error, cond, self.init_print_error,
tf.tile( tf.tile(
tf.reshape(tf.constant(1e10, self.data_type), [1, 1, 1]), [ tf.reshape(tf.constant(1e10, self.data_type), [1, 1, 1]), [
...@@ -450,12 +450,12 @@ class Graph(): ...@@ -450,12 +450,12 @@ class Graph():
def error_computation(self): def error_computation(self):
#computes the error of each example in a batch #computes the error of each example in a batch
math_error = 0.5 * tf.square(tf.sub(self.scalar_output, self.batch_answer)) math_error = 0.5 * tf.square(tf.subtract(self.scalar_output, self.batch_answer))
#scale math error #scale math error
math_error = math_error / self.rows math_error = math_error / self.rows
math_error = tf.minimum(math_error, self.utility.FLAGS.max_math_error * math_error = tf.minimum(math_error, self.utility.FLAGS.max_math_error *
tf.ones(tf.shape(math_error), self.data_type)) tf.ones(tf.shape(math_error), self.data_type))
self.init_print_error = tf.select( self.init_print_error = tf.where(
self.batch_gold_select, -1 * tf.log(self.batch_lookup_answer + 1e-300 + self.batch_gold_select, -1 * tf.log(self.batch_lookup_answer + 1e-300 +
self.invert_select_full_mask), -1 * self.invert_select_full_mask), -1 *
tf.log(1 - self.batch_lookup_answer)) * self.select_full_mask tf.log(1 - self.batch_lookup_answer)) * self.select_full_mask
...@@ -466,24 +466,24 @@ class Graph(): ...@@ -466,24 +466,24 @@ class Graph():
print_error += self.compute_lookup_error(val + 0.0) print_error += self.compute_lookup_error(val + 0.0)
print_error = print_error * self.utility.FLAGS.print_cost / self.num_entries print_error = print_error * self.utility.FLAGS.print_cost / self.num_entries
if (self.mode == "train"): if (self.mode == "train"):
error = tf.select( error = tf.where(
tf.logical_and( tf.logical_and(
tf.not_equal(self.batch_answer, 0.0), tf.not_equal(self.batch_answer, 0.0),
tf.not_equal( tf.not_equal(
tf.reduce_sum(tf.reduce_sum(self.batch_print_answer, 1), 1), tf.reduce_sum(tf.reduce_sum(self.batch_print_answer, 1), 1),
0.0)), 0.0)),
self.soft_min(math_error, print_error), self.soft_min(math_error, print_error),
tf.select( tf.where(
tf.not_equal(self.batch_answer, 0.0), math_error, print_error)) tf.not_equal(self.batch_answer, 0.0), math_error, print_error))
else: else:
error = tf.select( error = tf.where(
tf.logical_and( tf.logical_and(
tf.equal(self.scalar_output, 0.0), tf.equal(self.scalar_output, 0.0),
tf.equal( tf.equal(
tf.reduce_sum(tf.reduce_sum(self.batch_lookup_answer, 1), 1), tf.reduce_sum(tf.reduce_sum(self.batch_lookup_answer, 1), 1),
0.0)), 0.0)),
tf.ones_like(math_error), tf.ones_like(math_error),
tf.select( tf.where(
tf.equal(self.scalar_output, 0.0), print_error, math_error)) tf.equal(self.scalar_output, 0.0), print_error, math_error))
return error return error
...@@ -558,7 +558,7 @@ class Graph(): ...@@ -558,7 +558,7 @@ class Graph():
input_col = tf.reduce_sum( input_col = tf.reduce_sum(
tf.expand_dims(soft_column_softmax, 2) * tf.expand_dims(soft_column_softmax, 2) *
self.full_column_hidden_vectors, 1) self.full_column_hidden_vectors, 1)
history_input = tf.concat(1, [input_op, input_col]) history_input = tf.concat(axis=1, values=[input_op, input_col])
history_input = nn_utils.apply_dropout( history_input = nn_utils.apply_dropout(
history_input, self.utility.FLAGS.dropout, self.mode) history_input, self.utility.FLAGS.dropout, self.mode)
hprev = self.history_recurrent_step(history_input, hprev) hprev = self.history_recurrent_step(history_input, hprev)
...@@ -567,7 +567,7 @@ class Graph(): ...@@ -567,7 +567,7 @@ class Graph():
self.scalar_output = output self.scalar_output = output
error = self.error_computation() error = self.error_computation()
cond = tf.less(error, 0.0001, name="cond") cond = tf.less(error, 0.0001, name="cond")
correct_add = tf.select( correct_add = tf.where(
cond, tf.fill(tf.shape(cond), 1.0), tf.fill(tf.shape(cond), 0.0)) cond, tf.fill(tf.shape(cond), 1.0), tf.fill(tf.shape(cond), 0.0))
correct = tf.reduce_sum(correct_add) correct = tf.reduce_sum(correct_add)
error = error / batch_size error = error / batch_size
...@@ -579,11 +579,11 @@ class Graph(): ...@@ -579,11 +579,11 @@ class Graph():
#Sets mask variables and performs batch processing #Sets mask variables and performs batch processing
self.batch_gold_select = self.batch_print_answer > 0.0 self.batch_gold_select = self.batch_print_answer > 0.0
self.full_column_mask = tf.concat( self.full_column_mask = tf.concat(
1, [self.batch_number_column_mask, self.batch_word_column_mask]) axis=1, values=[self.batch_number_column_mask, self.batch_word_column_mask])
self.full_processed_column = tf.concat( self.full_processed_column = tf.concat(
1, axis=1,
[self.batch_processed_number_column, self.batch_processed_word_column]) values=[self.batch_processed_number_column, self.batch_processed_word_column])
self.full_processed_sorted_index_column = tf.concat(1, [ self.full_processed_sorted_index_column = tf.concat(axis=1, values=[
self.batch_processed_sorted_index_number_column, self.batch_processed_sorted_index_number_column,
self.batch_processed_sorted_index_word_column self.batch_processed_sorted_index_word_column
]) ])
...@@ -603,7 +603,7 @@ class Graph(): ...@@ -603,7 +603,7 @@ class Graph():
tf.equal(self.batch_word_column_entry_mask, tf.equal(self.batch_word_column_entry_mask,
self.utility.dummy_token_id)), self.data_type) self.utility.dummy_token_id)), self.data_type)
self.select_full_mask = tf.concat( self.select_full_mask = tf.concat(
1, [self.select_mask, self.select_word_mask]) axis=1, values=[self.select_mask, self.select_word_mask])
self.select_whole_mask = tf.maximum( self.select_whole_mask = tf.maximum(
tf.reshape( tf.reshape(
tf.slice(self.select_mask, [0, 0, 0], tf.slice(self.select_mask, [0, 0, 0],
...@@ -614,7 +614,7 @@ class Graph(): ...@@ -614,7 +614,7 @@ class Graph():
[self.batch_size, 1, self.max_elements]), [self.batch_size, 1, self.max_elements]),
[self.batch_size, self.max_elements])) [self.batch_size, self.max_elements]))
self.invert_select_full_mask = tf.cast( self.invert_select_full_mask = tf.cast(
tf.concat(1, [ tf.concat(axis=1, values=[
tf.equal(self.batch_number_column, self.utility.FLAGS.pad_int), tf.equal(self.batch_number_column, self.utility.FLAGS.pad_int),
tf.equal(self.batch_word_column_entry_mask, tf.equal(self.batch_word_column_entry_mask,
self.utility.dummy_token_id) self.utility.dummy_token_id)
......
neural_programmer/neural_programmer.py 100755 → 100644
View file @ 052e5e8b
File mode changed from 100755 to 100644
neural_programmer/nn_utils.py 100755 → 100644
View file @ 052e5e8b
File mode changed from 100755 to 100644
neural_programmer/parameters.py 100755 → 100644
View file @ 052e5e8b
File mode changed from 100755 to 100644
neural_programmer/wiki_data.py 100755 → 100644
View file @ 052e5e8b
File mode changed from 100755 to 100644
next_frame_prediction/cross_conv/model.py
View file @ 052e5e8b
...@@ -65,7 +65,7 @@ class CrossConvModel(object): ...@@ -65,7 +65,7 @@ class CrossConvModel(object):
diff = diff * 2.0 - self.params['scale'] diff = diff * 2.0 - self.params['scale']
diff_output = self.diff_output * 2.0 - self.params['scale'] diff_output = self.diff_output * 2.0 - self.params['scale']
concat_image = tf.concat( concat_image = tf.concat(
1, [image, image + diff_output, image + diff, diff_output]) axis=1, values=[image, image + diff_output, image + diff, diff_output])
tf.summary.image('origin_predict_expect_predictdiff', concat_image) tf.summary.image('origin_predict_expect_predictdiff', concat_image)
self.summary_op = tf.summary.merge_all() self.summary_op = tf.summary.merge_all()
return self.loss return self.loss
...@@ -113,7 +113,7 @@ class CrossConvModel(object): ...@@ -113,7 +113,7 @@ class CrossConvModel(object):
assert shape[1] == shape[2] and shape[1] == 128 assert shape[1] == shape[2] and shape[1] == 128
batch_size = shape[0] batch_size = shape[0]
net = tf.concat(3, [image, diff]) net = tf.concat(axis=3, values=[image, diff])
with tf.variable_scope('motion_encoder'): with tf.variable_scope('motion_encoder'):
with slim.arg_scope([slim.conv2d], padding='VALID'): with slim.arg_scope([slim.conv2d], padding='VALID'):
net = slim.conv2d(net, 96, [5, 5], stride=1) net = slim.conv2d(net, 96, [5, 5], stride=1)
...@@ -128,7 +128,7 @@ class CrossConvModel(object): ...@@ -128,7 +128,7 @@ class CrossConvModel(object):
z = tf.reshape(net, shape=[batch_size, -1]) z = tf.reshape(net, shape=[batch_size, -1])
self.z_mean, self.z_stddev_log = tf.split( self.z_mean, self.z_stddev_log = tf.split(
split_dim=1, num_split=2, value=z) axis=1, num_or_size_splits=2, value=z)
self.z_stddev = tf.exp(self.z_stddev_log) self.z_stddev = tf.exp(self.z_stddev_log)
epsilon = tf.random_normal( epsilon = tf.random_normal(
...@@ -174,7 +174,7 @@ class CrossConvModel(object): ...@@ -174,7 +174,7 @@ class CrossConvModel(object):
def _CrossConv(self, encoded_images): def _CrossConv(self, encoded_images):
"""Apply the motion kernel on the encoded_images.""" """Apply the motion kernel on the encoded_images."""
cross_conved_images = [] cross_conved_images = []
kernels = tf.split(split_dim=3, num_split=4, value=self.kernel) kernels = tf.split(axis=3, num_or_size_splits=4, value=self.kernel)
for (i, encoded_image) in enumerate(encoded_images): for (i, encoded_image) in enumerate(encoded_images):
with tf.variable_scope('cross_conv_%d' % i): with tf.variable_scope('cross_conv_%d' % i):
kernel = kernels[i] kernel = kernels[i]
...@@ -187,7 +187,7 @@ class CrossConvModel(object): ...@@ -187,7 +187,7 @@ class CrossConvModel(object):
for j in xrange(len(encoded_image)): for j in xrange(len(encoded_image)):
conved_image.append(self._CrossConvHelper( conved_image.append(self._CrossConvHelper(
encoded_image[j], kernel[j])) encoded_image[j], kernel[j]))
cross_conved_images.append(tf.concat(0, conved_image)) cross_conved_images.append(tf.concat(axis=0, values=conved_image))
sys.stderr.write('cross_conved shape: %s\n' % sys.stderr.write('cross_conved shape: %s\n' %
cross_conved_images[-1].get_shape()) cross_conved_images[-1].get_shape())
return cross_conved_images return cross_conved_images
...@@ -224,7 +224,7 @@ class CrossConvModel(object): ...@@ -224,7 +224,7 @@ class CrossConvModel(object):
nets.append(self._Deconv( nets.append(self._Deconv(
cross_conved_image, 64, kernel_size=3, stride=stride)) cross_conved_image, 64, kernel_size=3, stride=stride))
net = tf.concat(3, nets) net = tf.concat(axis=3, values=nets)
net = slim.conv2d(net, 128, [9, 9], padding='SAME', stride=1) net = slim.conv2d(net, 128, [9, 9], padding='SAME', stride=1)
net = slim.conv2d(net, 128, [1, 1], padding='SAME', stride=1) net = slim.conv2d(net, 128, [1, 1], padding='SAME', stride=1)
net = slim.conv2d(net, 3, [1, 1], padding='SAME', stride=1) net = slim.conv2d(net, 3, [1, 1], padding='SAME', stride=1)
......
next_frame_prediction/cross_conv/reader.py
View file @ 052e5e8b
...@@ -42,7 +42,7 @@ def SequenceToImageAndDiff(images): ...@@ -42,7 +42,7 @@ def SequenceToImageAndDiff(images):
for i in xrange(0, len(resized_images)-1): for i in xrange(0, len(resized_images)-1):
diffs.append(resized_images[i+1] - resized_images[i]) diffs.append(resized_images[i+1] - resized_images[i])
image_diff_list.append( image_diff_list.append(
(tf.concat(0, resized_images[:-1]), tf.concat(0, diffs))) (tf.concat(axis=0, values=resized_images[:-1]), tf.concat(axis=0, values=diffs)))
return image_diff_list return image_diff_list
......
real_nvp/real_nvp_multiscale_dataset.py
View file @ 052e5e8b
...@@ -332,7 +332,7 @@ def masked_conv_aff_coupling(input_, mask_in, dim, name, ...@@ -332,7 +332,7 @@ def masked_conv_aff_coupling(input_, mask_in, dim, name,
residual_blocks=residual_blocks, residual_blocks=residual_blocks,
bottleneck=bottleneck, skip=skip) bottleneck=bottleneck, skip=skip)
mask = tf.mod(mask_channel + mask, 2) mask = tf.mod(mask_channel + mask, 2)
res = tf.split(res, 2, 3) res = tf.split(axis=res, num_or_size_splits=2, value=3)
shift, log_rescaling = res[-2], res[-1] shift, log_rescaling = res[-2], res[-1]
scale = variable_on_cpu( scale = variable_on_cpu(
"rescaling_scale", [], "rescaling_scale", [],
...@@ -486,9 +486,9 @@ def conv_ch_aff_coupling(input_, dim, name, ...@@ -486,9 +486,9 @@ def conv_ch_aff_coupling(input_, dim, name,
scope.reuse_variables() scope.reuse_variables()
if change_bottom: if change_bottom:
input_, canvas = tf.split(input_, 2, 3) input_, canvas = tf.split(axis=input_, num_or_size_splits=2, value=3)
else: else:
canvas, input_ = tf.split(input_, 2, 3) canvas, input_ = tf.split(axis=input_, num_or_size_splits=2, value=3)
shape = input_.get_shape().as_list() shape = input_.get_shape().as_list()
batch_size = shape[0] batch_size = shape[0]
height = shape[1] height = shape[1]
...@@ -509,7 +509,7 @@ def conv_ch_aff_coupling(input_, dim, name, ...@@ -509,7 +509,7 @@ def conv_ch_aff_coupling(input_, dim, name,
train=train, weight_norm=weight_norm, train=train, weight_norm=weight_norm,
residual_blocks=residual_blocks, residual_blocks=residual_blocks,
bottleneck=bottleneck, skip=skip) bottleneck=bottleneck, skip=skip)
shift, log_rescaling = tf.split(res, 2, 3) shift, log_rescaling = tf.split(axis=res, num_or_size_splits=2, value=3)
scale = variable_on_cpu( scale = variable_on_cpu(
"scale", [], "scale", [],
tf.constant_initializer(1.)) tf.constant_initializer(1.))
...@@ -570,9 +570,9 @@ def conv_ch_add_coupling(input_, dim, name, ...@@ -570,9 +570,9 @@ def conv_ch_add_coupling(input_, dim, name,
scope.reuse_variables() scope.reuse_variables()
if change_bottom: if change_bottom:
input_, canvas = tf.split(input_, 2, 3) input_, canvas = tf.split(axis=input_, num_or_size_splits=2, value=3)
else: else:
canvas, input_ = tf.split(input_, 2, 3) canvas, input_ = tf.split(axis=input_, num_or_size_splits=2, value=3)
shape = input_.get_shape().as_list() shape = input_.get_shape().as_list()
channels = shape[3] channels = shape[3]
res = input_ res = input_
...@@ -736,8 +736,8 @@ def rec_masked_conv_coupling(input_, hps, scale_idx, n_scale, ...@@ -736,8 +736,8 @@ def rec_masked_conv_coupling(input_, hps, scale_idx, n_scale,
log_diff_1 = log_diff[:, :, :, :channels] log_diff_1 = log_diff[:, :, :, :channels]
log_diff_2 = log_diff[:, :, :, channels:] log_diff_2 = log_diff[:, :, :, channels:]
else: else:
res_1, res_2 = tf.split(res, 2, 3) res_1, res_2 = tf.split(axis=res, num_or_size_splits=2, value=3)
log_diff_1, log_diff_2 = tf.split(log_diff, 2, 3) log_diff_1, log_diff_2 = tf.split(axis=log_diff, num_or_size_splits=2, value=3)
res_1, inc_log_diff = rec_masked_conv_coupling( res_1, inc_log_diff = rec_masked_conv_coupling(
input_=res_1, hps=hps, scale_idx=scale_idx + 1, n_scale=n_scale, input_=res_1, hps=hps, scale_idx=scale_idx + 1, n_scale=n_scale,
use_batch_norm=use_batch_norm, weight_norm=weight_norm, use_batch_norm=use_batch_norm, weight_norm=weight_norm,
...@@ -798,8 +798,8 @@ def rec_masked_deconv_coupling(input_, hps, scale_idx, n_scale, ...@@ -798,8 +798,8 @@ def rec_masked_deconv_coupling(input_, hps, scale_idx, n_scale,
log_diff_1 = log_diff[:, :, :, :channels] log_diff_1 = log_diff[:, :, :, :channels]
log_diff_2 = log_diff[:, :, :, channels:] log_diff_2 = log_diff[:, :, :, channels:]
else: else:
res_1, res_2 = tf.split(res, 2, 3) res_1, res_2 = tf.split(axis=res, num_or_size_splits=2, value=3)
log_diff_1, log_diff_2 = tf.split(log_diff, 2, 3) log_diff_1, log_diff_2 = tf.split(axis=log_diff, num_or_size_splits=2, value=3)
res_1, log_diff_1 = rec_masked_deconv_coupling( res_1, log_diff_1 = rec_masked_deconv_coupling(
input_=res_1, hps=hps, input_=res_1, hps=hps,
scale_idx=scale_idx + 1, n_scale=n_scale, scale_idx=scale_idx + 1, n_scale=n_scale,
...@@ -1305,7 +1305,7 @@ class RealNVP(object): ...@@ -1305,7 +1305,7 @@ class RealNVP(object):
z_lost = z_complete z_lost = z_complete
for scale_idx in xrange(hps.n_scale - 1): for scale_idx in xrange(hps.n_scale - 1):
z_lost = squeeze_2x2_ordered(z_lost) z_lost = squeeze_2x2_ordered(z_lost)
z_lost, _ = tf.split(z_lost, 2, 3) z_lost, _ = tf.split(axis=z_lost, num_or_size_splits=2, value=3)
z_compressed = z_lost z_compressed = z_lost
z_noisy = z_lost z_noisy = z_lost
for _ in xrange(scale_idx + 1): for _ in xrange(scale_idx + 1):
......
real_nvp/real_nvp_utils.py
View file @ 052e5e8b
...@@ -99,8 +99,8 @@ def conv_layer(input_, ...@@ -99,8 +99,8 @@ def conv_layer(input_,
filter_size[1] - input_.get_shape().as_list()[2], filter_size[1] - input_.get_shape().as_list()[2],
input_.get_shape().as_list()[3] input_.get_shape().as_list()[3]
]) ])
res = tf.concat(1, [pad_1, res]) res = tf.concat(axis=1, values=[pad_1, res])
res = tf.concat(2, [pad_2, res]) res = tf.concat(axis=2, values=[pad_2, res])
res = tf.nn.conv2d( res = tf.nn.conv2d(
input=res, input=res,
filter=weights, filter=weights,
...@@ -139,8 +139,8 @@ def depool_2x2(input_, stride=2): ...@@ -139,8 +139,8 @@ def depool_2x2(input_, stride=2):
channels = shape[3] channels = shape[3]
res = tf.reshape(input_, [batch_size, height, 1, width, 1, channels]) res = tf.reshape(input_, [batch_size, height, 1, width, 1, channels])
res = tf.concat( res = tf.concat(
2, [res, tf.zeros([batch_size, height, stride - 1, width, 1, channels])]) axis=2, values=[res, tf.zeros([batch_size, height, stride - 1, width, 1, channels])])
res = tf.concat(4, [ res = tf.concat(axis=4, values=[
res, tf.zeros([batch_size, height, stride, width, stride - 1, channels]) res, tf.zeros([batch_size, height, stride, width, stride - 1, channels])
]) ])
res = tf.reshape(res, [batch_size, stride * height, stride * width, channels]) res = tf.reshape(res, [batch_size, stride * height, stride * width, channels])
...@@ -158,11 +158,11 @@ def batch_random_flip(input_): ...@@ -158,11 +158,11 @@ def batch_random_flip(input_):
height = shape[1] height = shape[1]
width = shape[2] width = shape[2]
channels = shape[3] channels = shape[3]
res = tf.split(0, batch_size, input_) res = tf.split(axis=0, num_or_size_splits=batch_size, value=input_)
res = [elem[0, :, :, :] for elem in res] res = [elem[0, :, :, :] for elem in res]
res = [tf.image.random_flip_left_right(elem) for elem in res] res = [tf.image.random_flip_left_right(elem) for elem in res]
res = [tf.reshape(elem, [1, height, width, channels]) for elem in res] res = [tf.reshape(elem, [1, height, width, channels]) for elem in res]
res = tf.concat(0, res) res = tf.concat(axis=0, values=res)
return res return res
...@@ -175,7 +175,7 @@ def as_one_hot(input_, n_indices): ...@@ -175,7 +175,7 @@ def as_one_hot(input_, n_indices):
n_elem = numpy.prod(shape) n_elem = numpy.prod(shape)
indices = tf.range(n_elem) indices = tf.range(n_elem)
indices = tf.cast(indices, tf.int64) indices = tf.cast(indices, tf.int64)
indices_input = tf.concat(0, [indices, tf.reshape(input_, [-1])]) indices_input = tf.concat(axis=0, values=[indices, tf.reshape(input_, [-1])])
indices_input = tf.reshape(indices_input, [2, -1]) indices_input = tf.reshape(indices_input, [2, -1])
indices_input = tf.transpose(indices_input) indices_input = tf.transpose(indices_input)
res = tf.sparse_to_dense( res = tf.sparse_to_dense(
......
slim/deployment/model_deploy.py
View file @ 052e5e8b
...@@ -232,10 +232,10 @@ def _gather_clone_loss(clone, num_clones, regularization_losses): ...@@ -232,10 +232,10 @@ def _gather_clone_loss(clone, num_clones, regularization_losses):
sum_loss = tf.add_n(all_losses) sum_loss = tf.add_n(all_losses)
# Add the summaries out of the clone device block. # Add the summaries out of the clone device block.
if clone_loss is not None: if clone_loss is not None:
tf.scalar_summary(clone.scope + '/clone_loss', clone_loss, tf.summary.scalar(clone.scope + '/clone_loss', clone_loss,
name='clone_loss') name='clone_loss')
if regularization_loss is not None: if regularization_loss is not None:
tf.scalar_summary('regularization_loss', regularization_loss, tf.summary.scalar('regularization_loss', regularization_loss,
name='regularization_loss') name='regularization_loss')
return sum_loss return sum_loss
...@@ -404,12 +404,12 @@ def deploy(config, ...@@ -404,12 +404,12 @@ def deploy(config,
if total_loss is not None: if total_loss is not None:
# Add total_loss to summary. # Add total_loss to summary.
summaries.add(tf.scalar_summary('total_loss', total_loss, summaries.add(tf.summary.scalar('total_loss', total_loss,
name='total_loss')) name='total_loss'))
if summaries: if summaries:
# Merge all summaries together. # Merge all summaries together.
summary_op = tf.merge_summary(list(summaries), name='summary_op') summary_op = tf.summary.merge(list(summaries), name='summary_op')
else: else:
summary_op = None summary_op = None
...@@ -467,9 +467,9 @@ def _add_gradients_summaries(grads_and_vars): ...@@ -467,9 +467,9 @@ def _add_gradients_summaries(grads_and_vars):
grad_values = grad.values grad_values = grad.values
else: else:
grad_values = grad grad_values = grad
summaries.append(tf.histogram_summary(var.op.name + ':gradient', summaries.append(tf.summary.histogram(var.op.name + ':gradient',
grad_values)) grad_values))
summaries.append(tf.histogram_summary(var.op.name + ':gradient_norm', summaries.append(tf.summary.histogram(var.op.name + ':gradient_norm',
tf.global_norm([grad_values]))) tf.global_norm([grad_values])))
else: else:
tf.logging.info('Var %s has no gradient', var.op.name) tf.logging.info('Var %s has no gradient', var.op.name)
......
slim/eval_image_classifier.py
View file @ 052e5e8b
...@@ -160,7 +160,7 @@ def main(_): ...@@ -160,7 +160,7 @@ def main(_):
# Print the summaries to screen. # Print the summaries to screen.
for name, value in names_to_values.iteritems(): for name, value in names_to_values.iteritems():
summary_name = 'eval/%s' % name summary_name = 'eval/%s' % name
op = tf.scalar_summary(summary_name, value, collections=[]) op = tf.summary.scalar(summary_name, value, collections=[])
op = tf.Print(op, [value], summary_name) op = tf.Print(op, [value], summary_name)
tf.add_to_collection(tf.GraphKeys.SUMMARIES, op) tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
......
slim/nets/alexnet.py
View file @ 052e5e8b
...@@ -113,7 +113,7 @@ def alexnet_v2(inputs, ...@@ -113,7 +113,7 @@ def alexnet_v2(inputs,
net = slim.conv2d(net, num_classes, [1, 1], net = slim.conv2d(net, num_classes, [1, 1],
activation_fn=None, activation_fn=None,
normalizer_fn=None, normalizer_fn=None,
biases_initializer=tf.zeros_initializer, biases_initializer=tf.zeros_initializer(),
scope='fc8') scope='fc8')
# Convert end_points_collection into a end_point dict. # Convert end_points_collection into a end_point dict.
......
slim/nets/cifarnet.py
View file @ 052e5e8b
...@@ -77,7 +77,7 @@ def cifarnet(images, num_classes=10, is_training=False, ...@@ -77,7 +77,7 @@ def cifarnet(images, num_classes=10, is_training=False,
net = slim.fully_connected(net, 192, scope='fc4') net = slim.fully_connected(net, 192, scope='fc4')
end_points['fc4'] = net end_points['fc4'] = net
logits = slim.fully_connected(net, num_classes, logits = slim.fully_connected(net, num_classes,
biases_initializer=tf.zeros_initializer, biases_initializer=tf.zeros_initializer(),
weights_initializer=trunc_normal(1/192.0), weights_initializer=trunc_normal(1/192.0),
weights_regularizer=None, weights_regularizer=None,
activation_fn=None, activation_fn=None,
......
slim/nets/inception_v1.py
View file @ 052e5e8b
...@@ -93,7 +93,7 @@ def inception_v1_base(inputs, ...@@ -93,7 +93,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -110,7 +110,7 @@ def inception_v1_base(inputs, ...@@ -110,7 +110,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -132,7 +132,7 @@ def inception_v1_base(inputs, ...@@ -132,7 +132,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -149,7 +149,7 @@ def inception_v1_base(inputs, ...@@ -149,7 +149,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -166,7 +166,7 @@ def inception_v1_base(inputs, ...@@ -166,7 +166,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -183,7 +183,7 @@ def inception_v1_base(inputs, ...@@ -183,7 +183,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -200,7 +200,7 @@ def inception_v1_base(inputs, ...@@ -200,7 +200,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -222,7 +222,7 @@ def inception_v1_base(inputs, ...@@ -222,7 +222,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
...@@ -239,7 +239,7 @@ def inception_v1_base(inputs, ...@@ -239,7 +239,7 @@ def inception_v1_base(inputs,
with tf.variable_scope('Branch_3'): with tf.variable_scope('Branch_3'):
branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if final_endpoint == end_point: return net, end_points if final_endpoint == end_point: return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint) raise ValueError('Unknown final endpoint %s' % final_endpoint)
......
slim/nets/inception_v2.py
View file @ 052e5e8b
...@@ -145,7 +145,7 @@ def inception_v2_base(inputs, ...@@ -145,7 +145,7 @@ def inception_v2_base(inputs,
branch_3, depth(32), [1, 1], branch_3, depth(32), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 28 x 28 x 256 # 28 x 28 x 256
...@@ -175,7 +175,7 @@ def inception_v2_base(inputs, ...@@ -175,7 +175,7 @@ def inception_v2_base(inputs,
branch_3, depth(64), [1, 1], branch_3, depth(64), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 28 x 28 x 320 # 28 x 28 x 320
...@@ -200,7 +200,7 @@ def inception_v2_base(inputs, ...@@ -200,7 +200,7 @@ def inception_v2_base(inputs,
with tf.variable_scope('Branch_2'): with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d( branch_2 = slim.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3') net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = tf.concat(3, [branch_0, branch_1, branch_2]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 14 x 14 x 576 # 14 x 14 x 576
...@@ -230,7 +230,7 @@ def inception_v2_base(inputs, ...@@ -230,7 +230,7 @@ def inception_v2_base(inputs,
branch_3, depth(128), [1, 1], branch_3, depth(128), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 14 x 14 x 576 # 14 x 14 x 576
...@@ -260,7 +260,7 @@ def inception_v2_base(inputs, ...@@ -260,7 +260,7 @@ def inception_v2_base(inputs,
branch_3, depth(128), [1, 1], branch_3, depth(128), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 14 x 14 x 576 # 14 x 14 x 576
...@@ -290,7 +290,7 @@ def inception_v2_base(inputs, ...@@ -290,7 +290,7 @@ def inception_v2_base(inputs,
branch_3, depth(96), [1, 1], branch_3, depth(96), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
...@@ -321,7 +321,7 @@ def inception_v2_base(inputs, ...@@ -321,7 +321,7 @@ def inception_v2_base(inputs,
branch_3, depth(96), [1, 1], branch_3, depth(96), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 14 x 14 x 576 # 14 x 14 x 576
...@@ -346,7 +346,7 @@ def inception_v2_base(inputs, ...@@ -346,7 +346,7 @@ def inception_v2_base(inputs,
with tf.variable_scope('Branch_2'): with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d(net, [3, 3], stride=2, branch_2 = slim.max_pool2d(net, [3, 3], stride=2,
scope='MaxPool_1a_3x3') scope='MaxPool_1a_3x3')
net = tf.concat(3, [branch_0, branch_1, branch_2]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
# 7 x 7 x 1024 # 7 x 7 x 1024
...@@ -376,7 +376,7 @@ def inception_v2_base(inputs, ...@@ -376,7 +376,7 @@ def inception_v2_base(inputs,
branch_3, depth(128), [1, 1], branch_3, depth(128), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
...@@ -407,7 +407,7 @@ def inception_v2_base(inputs, ...@@ -407,7 +407,7 @@ def inception_v2_base(inputs,
branch_3, depth(128), [1, 1], branch_3, depth(128), [1, 1],
weights_initializer=trunc_normal(0.1), weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1') scope='Conv2d_0b_1x1')
net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3]) net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net end_points[end_point] = net
if end_point == final_endpoint: return net, end_points if end_point == final_endpoint: return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint) raise ValueError('Unknown final endpoint %s' % final_endpoint)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment