From f9965fd85bee1c086e15ea2a9f03c121cbfbecf3 Mon Sep 17 00:00:00 2001
From: Tiago Freitas Pereira <tiagofrepereira@gmail.com>
Date: Thu, 6 Oct 2016 10:21:36 +0200
Subject: [PATCH] Several updates. Need to control better these commits
---
bob/learn/tensorflow/data/BaseDataShuffler.py | 4 +-
.../tensorflow/data/MemoryDataShuffler.py | 4 +-
bob/learn/tensorflow/data/TextDataShuffler.py | 27 +++++++++
bob/learn/tensorflow/layers/MaxPooling.py | 5 +-
bob/learn/tensorflow/loss/TripletLoss.py | 4 +-
bob/learn/tensorflow/network/Chopra.py | 51 ++++++++--------
bob/learn/tensorflow/script/train_mnist.py | 5 +-
.../tensorflow/script/train_mnist_siamese.py | 6 +-
.../tensorflow/script/train_mnist_triplet.py | 12 ++--
.../tensorflow/trainers/TripletTrainer.py | 59 +++++++++----------
10 files changed, 103 insertions(+), 74 deletions(-)
diff --git a/bob/learn/tensorflow/data/BaseDataShuffler.py b/bob/learn/tensorflow/data/BaseDataShuffler.py
index 544f37b4..28a6b621 100644
--- a/bob/learn/tensorflow/data/BaseDataShuffler.py
+++ b/bob/learn/tensorflow/data/BaseDataShuffler.py
@@ -101,8 +101,8 @@ class BaseDataShuffler(object):
def get_one_triplet(self, input_data, input_labels):
# Getting a pair of clients
index = numpy.random.choice(len(self.possible_labels), 2, replace=False)
- label_positive = index[0]
- label_negative = index[1]
+ index[0] = self.possible_labels[index[0]]
+ index[1] = self.possible_labels[index[1]]
# Getting the indexes of the data from a particular client
indexes = numpy.where(input_labels == index[0])[0]
diff --git a/bob/learn/tensorflow/data/MemoryDataShuffler.py b/bob/learn/tensorflow/data/MemoryDataShuffler.py
index d9d350a8..ae2e22d5 100644
--- a/bob/learn/tensorflow/data/MemoryDataShuffler.py
+++ b/bob/learn/tensorflow/data/MemoryDataShuffler.py
@@ -82,7 +82,7 @@ class MemoryDataShuffler(BaseDataShuffler):
return data, data_p, labels_siamese
- def get_random_triplet(self, n_triplets=1):
+ def get_random_triplet(self):
"""
Get a random triplet
@@ -96,7 +96,7 @@ class MemoryDataShuffler(BaseDataShuffler):
data_p = numpy.zeros(shape=self.shape, dtype='float32')
data_n = numpy.zeros(shape=self.shape, dtype='float32')
- for i in range(n_triplets):
+ for i in range(self.shape[0]):
data_a[i, ...], data_p[i, ...], data_n[i, ...] = self.get_one_triplet(self.data, self.labels)
return data_a, data_p, data_n
diff --git a/bob/learn/tensorflow/data/TextDataShuffler.py b/bob/learn/tensorflow/data/TextDataShuffler.py
index 22925f37..1829f53e 100644
--- a/bob/learn/tensorflow/data/TextDataShuffler.py
+++ b/bob/learn/tensorflow/data/TextDataShuffler.py
@@ -150,3 +150,30 @@ class TextDataShuffler(BaseDataShuffler):
return data, data_p, labels_siamese
+ def get_random_triplet(self):
+ """
+ Get a random pair of samples
+
+ **Parameters**
+ is_target_set_train: Defining the target set to get the batch
+
+ **Return**
+ """
+
+ data_a = numpy.zeros(shape=self.shape, dtype='float32')
+ data_p = numpy.zeros(shape=self.shape, dtype='float32')
+ data_n = numpy.zeros(shape=self.shape, dtype='float32')
+
+ for i in range(self.shape[0]):
+ file_name_a, file_name_p, file_name_n = self.get_one_triplet(self.data, self.labels)
+ data_a[i, ...] = self.load_from_file(str(file_name_a), self.shape)
+ data_p[i, ...] = self.load_from_file(str(file_name_p), self.shape)
+ data_n[i, ...] = self.load_from_file(str(file_name_n), self.shape)
+
+ if self.scale:
+ data_a *= self.scale_value
+ data_p *= self.scale_value
+ data_n *= self.scale_value
+
+ return data_a, data_p, data_n
+
diff --git a/bob/learn/tensorflow/layers/MaxPooling.py b/bob/learn/tensorflow/layers/MaxPooling.py
index e8566003..4897b940 100644
--- a/bob/learn/tensorflow/layers/MaxPooling.py
+++ b/bob/learn/tensorflow/layers/MaxPooling.py
@@ -10,11 +10,12 @@ from .Layer import Layer
class MaxPooling(Layer):
- def __init__(self, name):
+ def __init__(self, name, shape=[1, 2, 2, 1]):
"""
Constructor
"""
super(MaxPooling, self).__init__(name, use_gpu=False)
+ self.shape = shape
def create_variables(self, input_layer):
self.input_layer = input_layer
@@ -22,6 +23,6 @@ class MaxPooling(Layer):
def get_graph(self):
with tf.name_scope(str(self.name)):
- output = tf.nn.max_pool(self.input_layer, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
+ output = tf.nn.max_pool(self.input_layer, ksize=self.shape, strides=[1, 1, 1, 1], padding='SAME')
return output
diff --git a/bob/learn/tensorflow/loss/TripletLoss.py b/bob/learn/tensorflow/loss/TripletLoss.py
index abfa5f38..2806b1ec 100644
--- a/bob/learn/tensorflow/loss/TripletLoss.py
+++ b/bob/learn/tensorflow/loss/TripletLoss.py
@@ -30,7 +30,7 @@ class TripletLoss(BaseLoss):
"""
- def __init__(self, margin=2.0):
+ def __init__(self, margin=5.0):
self.margin = margin
def __call__(self, anchor_feature, positive_feature, negative_feature):
@@ -41,5 +41,5 @@ class TripletLoss(BaseLoss):
d_negative = tf.square(compute_euclidean_distance(anchor_feature, negative_feature))
loss = tf.maximum(0., d_positive - d_negative + self.margin)
-
return tf.reduce_mean(loss), tf.reduce_mean(d_positive), tf.reduce_mean(d_negative)
+ #return loss, d_positive, d_negative
diff --git a/bob/learn/tensorflow/network/Chopra.py b/bob/learn/tensorflow/network/Chopra.py
index bcc516f3..96f9e346 100644
--- a/bob/learn/tensorflow/network/Chopra.py
+++ b/bob/learn/tensorflow/network/Chopra.py
@@ -9,6 +9,18 @@ Class that creates the architecture presented in the paper:
Chopra, Sumit, Raia Hadsell, and Yann LeCun. "Learning a similarity metric discriminatively, with application to
face verification." 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Vol. 1. IEEE, 2005.
+This is modifield version of the original architecture.
+It is inspired on https://gitlab.idiap.ch/bob/xfacereclib.cnn/blob/master/lua/network.lua
+
+-- C1 : Convolutional, kernel = 7x7 pixels, 15 feature maps
+-- M2 : MaxPooling, 2x2
+-- HT : Hard Hyperbolic Tangent
+-- C3 : Convolutional, kernel = 6x6 pixels, 45 feature maps
+-- M4 : MaxPooling, 4x3
+-- HT : Hard Hyperbolic Tangent
+-- R : Reshaping layer HT 5x5 => 25 (45 times; once for each feature map)
+-- L5 : Linear 25 => 250
+
"""
@@ -26,15 +38,16 @@ class Chopra(SequenceNetwork):
conv1_kernel_size=7,
conv1_output=15,
+ pooling1_size=[1, 2, 2, 1],
+
+
conv2_kernel_size=6,
conv2_output=45,
- conv3_kernel_size=5,
- conv3_output=250,
+ pooling2_size=[1, 4, 3, 1],
- fc6_output=50,
- n_classes=40,
- default_feature_layer="fc7",
+ fc1_output=250,
+ default_feature_layer="fc1",
seed=10,
use_gpu=False):
@@ -45,19 +58,19 @@ class Chopra(SequenceNetwork):
conv1_kernel_size=5,
conv1_output=32,
+ pooling1_size=[1, 2, 2, 1],
+
conv2_kernel_size=5,
conv2_output=64,
- conv3_kernel_size=5,
- conv3_output=250,
+ pooling2_size=[1, 4, 3, 1],
- fc6_output=50,
- n_classes=10
+ fc1_output=50,
seed = 10
"""
super(Chopra, self).__init__(default_feature_layer=default_feature_layer,
- use_gpu=use_gpu)
+ use_gpu=use_gpu)
self.add(Conv2D(name="conv1", kernel_size=conv1_kernel_size,
filters=conv1_output,
@@ -65,7 +78,7 @@ class Chopra(SequenceNetwork):
weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
bias_initialization=Constant(use_gpu=self.use_gpu)
))
- self.add(MaxPooling(name="pooling1"))
+ self.add(MaxPooling(name="pooling1", shape=pooling1_size))
self.add(Conv2D(name="conv2", kernel_size=conv2_kernel_size,
filters=conv2_output,
@@ -73,21 +86,9 @@ class Chopra(SequenceNetwork):
weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
bias_initialization=Constant(use_gpu=self.use_gpu)
))
- self.add(MaxPooling(name="pooling2"))
+ self.add(MaxPooling(name="pooling2", shape=pooling2_size))
- self.add(Conv2D(name="conv3", kernel_size=conv3_kernel_size,
- filters=conv3_output,
- activation=tf.nn.tanh,
- weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
- bias_initialization=Constant(use_gpu=self.use_gpu)
- ))
-
- self.add(FullyConnected(name="fc6", output_dim=fc6_output,
- activation=tf.nn.tanh,
- weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
- bias_initialization=Constant(use_gpu=self.use_gpu)
- ))
- self.add(FullyConnected(name="fc7", output_dim=n_classes,
+ self.add(FullyConnected(name="fc1", output_dim=fc1_output,
activation=None,
weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
bias_initialization=Constant(use_gpu=self.use_gpu)))
diff --git a/bob/learn/tensorflow/script/train_mnist.py b/bob/learn/tensorflow/script/train_mnist.py
index a8db168f..ee8221c9 100644
--- a/bob/learn/tensorflow/script/train_mnist.py
+++ b/bob/learn/tensorflow/script/train_mnist.py
@@ -23,7 +23,7 @@ import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.data import MemoryDataShuffler, TextDataShuffler
-from bob.learn.tensorflow.network import Lenet, MLP, Dummy
+from bob.learn.tensorflow.network import Lenet, MLP, Dummy, Chopra
from bob.learn.tensorflow.trainers import Trainer
from bob.learn.tensorflow.loss import BaseLoss
@@ -89,7 +89,8 @@ def main():
# Preparing the architecture
cnn = True
if cnn:
- architecture = Lenet(seed=SEED)
+ architecture = Chopra(seed=SEED)
+ #architecture = Lenet(seed=SEED)
#architecture = Dummy(seed=SEED)
loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
trainer = Trainer(architecture=architecture, loss=loss, iterations=ITERATIONS)
diff --git a/bob/learn/tensorflow/script/train_mnist_siamese.py b/bob/learn/tensorflow/script/train_mnist_siamese.py
index 465d3227..5cfd16fd 100644
--- a/bob/learn/tensorflow/script/train_mnist_siamese.py
+++ b/bob/learn/tensorflow/script/train_mnist_siamese.py
@@ -39,7 +39,7 @@ def main():
perc_train = 0.9
# Loading data
- mnist = False
+ mnist = True
if mnist:
train_data, train_labels, validation_data, validation_labels = \
@@ -118,8 +118,8 @@ def main():
if cnn:
# LENET PAPER CHOPRA
- #architecture = Chopra(default_feature_layer="fc7")
- architecture = Lenet(default_feature_layer="fc2", n_classes=n_classes, conv1_output=8, conv2_output=16,use_gpu=USE_GPU)
+ architecture = Chopra(seed=SEED)
+ #architecture = Lenet(default_feature_layer="fc2", n_classes=n_classes, conv1_output=8, conv2_output=16,use_gpu=USE_GPU)
#architecture = VGG(n_classes=n_classes, use_gpu=USE_GPU)
#architecture = Dummy(seed=SEED)
diff --git a/bob/learn/tensorflow/script/train_mnist_triplet.py b/bob/learn/tensorflow/script/train_mnist_triplet.py
index cbe1878e..c46eb1c5 100644
--- a/bob/learn/tensorflow/script/train_mnist_triplet.py
+++ b/bob/learn/tensorflow/script/train_mnist_triplet.py
@@ -39,7 +39,7 @@ def main():
perc_train = 0.9
# Loading data
- mnist = True
+ mnist = False
if mnist:
train_data, train_labels, validation_data, validation_labels = \
@@ -125,15 +125,15 @@ def main():
#architecture = LenetDropout(default_feature_layer="fc2", n_classes=n_classes, conv1_output=4, conv2_output=8, use_gpu=USE_GPU)
loss = TripletLoss()
- optimizer = tf.train.GradientDescentOptimizer(0.0001)
-
+ optimizer = tf.train.GradientDescentOptimizer(0.000001)
trainer = TripletTrainer(architecture=architecture,
loss=loss,
iterations=ITERATIONS,
snapshot=VALIDATION_TEST,
- optimizer=optimizer)
- #trainer.train(train_data_shuffler, validation_data_shuffler)
- trainer.train(train_data_shuffler)
+ optimizer=optimizer
+ )
+ trainer.train(train_data_shuffler, validation_data_shuffler)
+ #trainer.train(train_data_shuffler)
else:
mlp = MLP(n_classes, hidden_layers=[15, 20])
diff --git a/bob/learn/tensorflow/trainers/TripletTrainer.py b/bob/learn/tensorflow/trainers/TripletTrainer.py
index 054edc33..fcb2c2c1 100644
--- a/bob/learn/tensorflow/trainers/TripletTrainer.py
+++ b/bob/learn/tensorflow/trainers/TripletTrainer.py
@@ -87,36 +87,29 @@ class TripletTrainer(Trainer):
bob.io.base.create_directories_safe(self.temp_dir)
# Creating two graphs
- #train_placeholder_anchor_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_anchor")
- #train_placeholder_positive_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_positive")
- #train_placeholder_negative_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_negative")
+ train_placeholder_anchor_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_anchor")
+ train_placeholder_positive_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_positive")
+ train_placeholder_negative_data, _ = train_data_shuffler.get_placeholders_forprefetch(name="train_negative")
# Defining a placeholder queue for prefetching
- #queue = tf.FIFOQueue(capacity=100,
- # dtypes=[tf.float32, tf.float32, tf.float32],
- # shapes=[train_placeholder_anchor_data.get_shape().as_list()[1:],
- # train_placeholder_positive_data.get_shape().as_list()[1:],
- # train_placeholder_negative_data.get_shape().as_list()[1:]])
+ queue = tf.FIFOQueue(capacity=100,
+ dtypes=[tf.float32, tf.float32, tf.float32],
+ shapes=[train_placeholder_anchor_data.get_shape().as_list()[1:],
+ train_placeholder_positive_data.get_shape().as_list()[1:],
+ train_placeholder_negative_data.get_shape().as_list()[1:]])
# Fetching the place holders from the queue
- #enqueue_op = queue.enqueue_many([train_placeholder_anchor_data,
- # train_placeholder_positive_data,
- # train_placeholder_negative_data])
- #train_anchor_feature_batch, train_positive_label_batch, train_negative_label_batch = \
- # queue.dequeue_many(train_data_shuffler.batch_size)
+ enqueue_op = queue.enqueue_many([train_placeholder_anchor_data,
+ train_placeholder_positive_data,
+ train_placeholder_negative_data])
+ train_anchor_feature_batch, train_positive_feature_batch, train_negative_feature_batch = \
+ queue.dequeue_many(train_data_shuffler.batch_size)
# Creating the architecture for train and validation
if not isinstance(self.architecture, SequenceNetwork):
raise ValueError("The variable `architecture` must be an instance of "
"`bob.learn.tensorflow.network.SequenceNetwork`")
-
- #############
- train_anchor_feature_batch, _ = train_data_shuffler.get_placeholders(name="train_anchor")
- train_positive_feature_batch, _ = train_data_shuffler.get_placeholders(name="train_positive")
- train_negative_feature_batch, _ = train_data_shuffler.get_placeholders(name="train_negative")
- #############
-
# Creating the siamese graph
#import ipdb; ipdb.set_trace();
train_anchor_graph = self.architecture.compute_graph(train_anchor_feature_batch)
@@ -145,9 +138,9 @@ class TripletTrainer(Trainer):
tf.initialize_all_variables().run()
# Start a thread to enqueue data asynchronously, and hide I/O latency.
- #thread_pool = tf.train.Coordinator()
- #tf.train.start_queue_runners(coord=thread_pool)
- #threads = start_thread()
+ thread_pool = tf.train.Coordinator()
+ tf.train.start_queue_runners(coord=thread_pool)
+ threads = start_thread()
# TENSOR BOARD SUMMARY
train_writer = tf.train.SummaryWriter(os.path.join(self.temp_dir, 'LOGS'), session.graph)
@@ -165,18 +158,24 @@ class TripletTrainer(Trainer):
for step in range(self.iterations):
- batch_anchor, batch_positive, batch_negative = train_data_shuffler.get_random_triplet()
+ #batch_anchor, batch_positive, batch_negative = train_data_shuffler.get_random_triplet()
+
+ #feed_dict = {train_anchor_feature_batch: batch_anchor,
+ # train_positive_feature_batch: batch_positive,
+ # train_negative_feature_batch: batch_negative}
+
- feed_dict = {train_anchor_feature_batch: batch_anchor,
- train_positive_feature_batch: batch_positive,
- train_negative_feature_batch: batch_negative}
+ #_, l, lr, summary, pos, neg = session.run([optimizer, loss_train, learning_rate, merged, within_class, between_class], feed_dict=feed_dict)
+ #_, l, lr, pos, neg, f_anchor, f_positive, f_negative = session.run(
+ # [optimizer, loss_train, learning_rate, within_class, between_class, train_anchor_feature_batch, train_positive_feature_batch, train_negative_feature_batch], feed_dict=feed_dict)
+ #import ipdb; ipdb.set_trace();
- _, l, lr, summary = session.run([optimizer, loss_train, learning_rate, merged], feed_dict=feed_dict)
- #_, l, lr= session.run([optimizer, loss_train, learning_rate])
+ _, l, lr, summary = session.run([optimizer, loss_train, learning_rate, merged])
train_writer.add_summary(summary, step)
- print str(step) + " -- loss: " + str(l)
+ #print str(step) + " -- loss: " + str(l)
+ #print str(step) + " -- loss: {0}; pos: {1}; neg: {2}".format(l, pos, neg)
sys.stdout.flush()
if validation_data_shuffler is not None and step % self.snapshot == 0:
--
GitLab