From 1a517ecd4564f1436c79e1945bb991b2e8423973 Mon Sep 17 00:00:00 2001
From: Tiago Freitas Pereira <tiagofrepereira@gmail.com>
Date: Fri, 11 Nov 2016 17:08:33 +0100
Subject: [PATCH] DOcumenting
---
bob/learn/tensorflow/datashuffler/Memory.py | 2 +-
.../tensorflow/datashuffler/SiameseDisk.py | 7 +-
.../tensorflow/datashuffler/TripletDisk.py | 10 +-
.../tensorflow/network/SequenceNetwork.py | 4 +-
bob/learn/tensorflow/network/VGG16_mod.py | 8 +-
bob/learn/tensorflow/test/test_cnn.py | 69 ++++--------
bob/learn/tensorflow/test/test_cnn_load.py | 44 ++++++++
.../test/test_cnn_pretrained_model.py | 47 ++++++--
bob/learn/tensorflow/test/test_cnn_scratch.py | 7 +-
.../tensorflow/test/test_datashuffler.py | 2 +-
.../test/test_datashuffler_augmentation.py | 2 +-
bob/learn/tensorflow/test/test_dnn.py | 50 ++++-----
.../tensorflow/trainers/SiameseTrainer.py | 28 ++---
bob/learn/tensorflow/trainers/Trainer.py | 13 +--
.../tensorflow/trainers/TripletTrainer.py | 40 +++----
bob/learn/tensorflow/utils/session.py | 3 -
doc/py_api.rst | 2 +
doc/user_guide.rst | 105 +++++++++++++++---
18 files changed, 274 insertions(+), 169 deletions(-)
create mode 100644 bob/learn/tensorflow/test/test_cnn_load.py
diff --git a/bob/learn/tensorflow/datashuffler/Memory.py b/bob/learn/tensorflow/datashuffler/Memory.py
index 45e64404..1b9509e0 100644
--- a/bob/learn/tensorflow/datashuffler/Memory.py
+++ b/bob/learn/tensorflow/datashuffler/Memory.py
@@ -60,7 +60,7 @@ class Memory(Base):
indexes = numpy.array(range(self.data.shape[0]))
numpy.random.shuffle(indexes)
- selected_data = self.data[indexes[0:self.batch_size], :, :, :]
+ selected_data = self.data[indexes[0:self.batch_size], ...]
selected_labels = self.labels[indexes[0:self.batch_size]]
# Applying the data augmentation
diff --git a/bob/learn/tensorflow/datashuffler/SiameseDisk.py b/bob/learn/tensorflow/datashuffler/SiameseDisk.py
index 03b4423d..52f64ee4 100644
--- a/bob/learn/tensorflow/datashuffler/SiameseDisk.py
+++ b/bob/learn/tensorflow/datashuffler/SiameseDisk.py
@@ -75,13 +75,10 @@ class SiameseDisk(Siamese, Disk):
genuine = True
for i in range(self.shape[0]):
file_name, file_name_p = self.get_genuine_or_not(self.data, self.labels, genuine=genuine)
- sample_l[i, ...] = self.load_from_file(str(file_name))
- sample_r[i, ...] = self.load_from_file(str(file_name_p))
+ sample_l[i, ...] = self.normalize_sample(self.load_from_file(str(file_name)))
+ sample_r[i, ...] = self.normalize_sample(self.load_from_file(str(file_name_p)))
labels_siamese[i] = not genuine
genuine = not genuine
- sample_l = self.normalize_sample(sample_l)
- sample_r = self.normalize_sample(sample_r)
-
return sample_l, sample_r, labels_siamese
diff --git a/bob/learn/tensorflow/datashuffler/TripletDisk.py b/bob/learn/tensorflow/datashuffler/TripletDisk.py
index 2df05c08..fd117190 100644
--- a/bob/learn/tensorflow/datashuffler/TripletDisk.py
+++ b/bob/learn/tensorflow/datashuffler/TripletDisk.py
@@ -78,12 +78,8 @@ class TripletDisk(Triplet, Disk):
for i in range(self.shape[0]):
file_name_a, file_name_p, file_name_n = self.get_one_triplet(self.data, self.labels)
- sample_a[i, ...] = self.load_from_file(str(file_name_a))
- sample_p[i, ...] = self.load_from_file(str(file_name_p))
- sample_n[i, ...] = self.load_from_file(str(file_name_n))
-
- sample_a = self.normalize_sample(sample_a)
- sample_p = self.normalize_sample(sample_p)
- sample_n = self.normalize_sample(sample_n)
+ sample_a[i, ...] = self.normalize_sample(self.load_from_file(str(file_name_a)))
+ sample_p[i, ...] = self.normalize_sample(self.load_from_file(str(file_name_p)))
+ sample_n[i, ...] = self.normalize_sample(self.load_from_file(str(file_name_n)))
return [sample_a, sample_p, sample_n]
diff --git a/bob/learn/tensorflow/network/SequenceNetwork.py b/bob/learn/tensorflow/network/SequenceNetwork.py
index fd727c1d..49af83b5 100644
--- a/bob/learn/tensorflow/network/SequenceNetwork.py
+++ b/bob/learn/tensorflow/network/SequenceNetwork.py
@@ -322,8 +322,8 @@ class SequenceNetwork(six.with_metaclass(abc.ABCMeta, object)):
session = Session.instance().session
self.sequence_net = pickle.loads(open(path+"_sequence_net.pickle").read())
- #saver = tf.train.import_meta_graph(path + ".meta", clear_devices=clear_devices)
- saver = tf.train.import_meta_graph(path + ".meta")
+ saver = tf.train.import_meta_graph(path + ".meta", clear_devices=clear_devices)
+ #saver = tf.train.import_meta_graph(path + ".meta")
saver.restore(session, path)
self.inference_graph = tf.get_collection("inference_graph")[0]
self.inference_placeholder = tf.get_collection("inference_placeholder")[0]
diff --git a/bob/learn/tensorflow/network/VGG16_mod.py b/bob/learn/tensorflow/network/VGG16_mod.py
index a3b7f187..bdfa4f89 100644
--- a/bob/learn/tensorflow/network/VGG16_mod.py
+++ b/bob/learn/tensorflow/network/VGG16_mod.py
@@ -71,10 +71,13 @@ class VGG16_mod(SequenceNetwork):
default_feature_layer="fc8",
seed=10,
+
+ do_dropout=True,
+
use_gpu=False):
super(VGG16_mod, self).__init__(default_feature_layer=default_feature_layer,
- use_gpu=use_gpu)
+ use_gpu=use_gpu)
# First convolutional block
self.conv1_1_kernel_size = conv1_1_kernel_size
@@ -223,6 +226,9 @@ class VGG16_mod(SequenceNetwork):
))
self.add(AveragePooling(name="pooling5", strides=[1, 2, 2, 1]))
+ if do_dropout:
+ self.add(Dropout(name="dropout", keep_prob=0.4))
+
self.add(FullyConnected(name="fc8", output_dim=n_classes,
activation=None,
weights_initialization=Xavier(seed=seed, use_gpu=self.use_gpu),
diff --git a/bob/learn/tensorflow/test/test_cnn.py b/bob/learn/tensorflow/test/test_cnn.py
index 43f0ff5e..257258e1 100644
--- a/bob/learn/tensorflow/test/test_cnn.py
+++ b/bob/learn/tensorflow/test/test_cnn.py
@@ -8,12 +8,11 @@ from bob.learn.tensorflow.datashuffler import Memory, SiameseMemory, TripletMemo
from bob.learn.tensorflow.network import Chopra
from bob.learn.tensorflow.loss import BaseLoss, ContrastiveLoss, TripletLoss
from bob.learn.tensorflow.trainers import Trainer, SiameseTrainer, TripletTrainer, constant
+from .test_cnn_scratch import validate_network
-# from ..analyzers import ExperimentAnalizer, SoftmaxAnalizer
-from bob.learn.tensorflow.util import load_mnist
+from bob.learn.tensorflow.utils import load_mnist
import tensorflow as tf
import bob.io.base
-import os
import shutil
from scipy.spatial.distance import cosine
import bob.measure
@@ -28,7 +27,7 @@ iterations = 50
seed = 10
-def dummy_experiment(data_s, architecture, session):
+def dummy_experiment(data_s, architecture):
"""
Create a dummy experiment and return the EER
"""
@@ -38,12 +37,12 @@ def dummy_experiment(data_s, architecture, session):
# Extracting features for enrollment
enroll_data, enroll_labels = data_shuffler.get_batch()
- enroll_features = architecture(enroll_data, session=session)
+ enroll_features = architecture(enroll_data)
del enroll_data
# Extracting features for probing
probe_data, probe_labels = data_shuffler.get_batch()
- probe_features = architecture(probe_data, session=session)
+ probe_features = architecture(probe_data)
del probe_data
# Creating models
@@ -102,26 +101,14 @@ def test_cnn_trainer():
prefetch=False,
temp_dir=directory)
trainer.train(train_data_shuffler)
- del trainer #Just to clean tf.variables
- with tf.Session() as session:
+ accuracy = validate_network(validation_data, validation_labels, architecture)
- # Testing
- chopra = Chopra(seed=seed, fc1_output=10)
- chopra.load(session, os.path.join(directory, "model.ckp"))
-
- validation_data_shuffler = Memory(validation_data, validation_labels,
- input_shape=[28, 28, 1],
- batch_size=validation_batch_size)
-
- [data, labels] = validation_data_shuffler.get_batch()
- predictions = chopra(data, session=session)
- accuracy = 100. * numpy.sum(numpy.argmax(predictions, 1) == labels) / predictions.shape[0]
-
- # At least 80% of accuracy
- assert accuracy > 80.
- shutil.rmtree(directory)
- del chopra
+ # At least 80% of accuracy
+ assert accuracy > 80.
+ shutil.rmtree(directory)
+ del trainer
+ del architecture
def test_siamesecnn_trainer():
@@ -155,19 +142,15 @@ def test_siamesecnn_trainer():
temp_dir=directory)
trainer.train(train_data_shuffler)
- del trainer # Just to clean tf.variables
- with tf.Session() as session:
- # Testing
- chopra = Chopra(seed=seed, fc1_output=10)
- chopra.load(session, os.path.join(directory, "model.ckp"))
+ eer = dummy_experiment(validation_data_shuffler, architecture)
- eer = dummy_experiment(validation_data_shuffler, chopra, session)
+ # At least 80% of accuracy
+ assert eer < 0.25
+ shutil.rmtree(directory)
- # At least 80% of accuracy
- assert eer < 0.25
- shutil.rmtree(directory)
- del chopra
+ del architecture
+ del trainer # Just to clean tf.variables
def test_tripletcnn_trainer():
@@ -201,17 +184,13 @@ def test_tripletcnn_trainer():
temp_dir=directory)
trainer.train(train_data_shuffler)
- del trainer # Just to clean tf.variables
- with tf.Session() as session:
+ # Testing
+ eer = dummy_experiment(validation_data_shuffler, architecture)
- # Testing
- chopra = Chopra(seed=seed, fc1_output=10)
- chopra.load(session, os.path.join(directory, "model.ckp"))
+ # At least 80% of accuracy
+ assert eer < 0.25
+ shutil.rmtree(directory)
- eer = dummy_experiment(validation_data_shuffler, chopra, session)
-
- # At least 80% of accuracy
- assert eer < 0.25
- shutil.rmtree(directory)
- del chopra
+ del architecture
+ del trainer # Just to clean tf.variables
diff --git a/bob/learn/tensorflow/test/test_cnn_load.py b/bob/learn/tensorflow/test/test_cnn_load.py
new file mode 100644
index 00000000..02553e40
--- /dev/null
+++ b/bob/learn/tensorflow/test/test_cnn_load.py
@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+# vim: set fileencoding=utf-8 :
+# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
+# @date: Thu 13 Oct 2016 13:35 CEST
+
+
+"""
+Some unit tests that create networks on the fly
+"""
+
+
+import numpy
+import pkg_resources
+from bob.learn.tensorflow.utils import load_mnist
+from bob.learn.tensorflow.network import SequenceNetwork
+from bob.learn.tensorflow.datashuffler import Memory
+
+
+def validate_network(validation_data, validation_labels, network):
+ # Testing
+ validation_data_shuffler = Memory(validation_data, validation_labels,
+ input_shape=[28, 28, 1],
+ batch_size=400)
+
+ [data, labels] = validation_data_shuffler.get_batch()
+ predictions = network.predict(data)
+ accuracy = 100. * numpy.sum(predictions == labels) / predictions.shape[0]
+
+ return accuracy
+
+"""
+def test_load_test_cnn():
+
+ _, _, validation_data, validation_labels = load_mnist()
+
+ # Creating datashufflers
+ validation_data = numpy.reshape(validation_data, (validation_data.shape[0], 28, 28, 1))
+ network = SequenceNetwork()
+ network.load(pkg_resources.resource_filename(__name__, 'data/cnn_mnist/model.ckp'))
+
+ accuracy = validate_network(validation_data, validation_labels, network)
+ assert accuracy > 80
+ del network
+"""
diff --git a/bob/learn/tensorflow/test/test_cnn_pretrained_model.py b/bob/learn/tensorflow/test/test_cnn_pretrained_model.py
index b27a1e23..e8d4e90c 100644
--- a/bob/learn/tensorflow/test/test_cnn_pretrained_model.py
+++ b/bob/learn/tensorflow/test/test_cnn_pretrained_model.py
@@ -9,7 +9,10 @@ import os
from bob.learn.tensorflow.datashuffler import Memory, ImageAugmentation
from bob.learn.tensorflow.loss import BaseLoss
from bob.learn.tensorflow.trainers import Trainer, constant
-from bob.learn.tensorflow.util import load_mnist
+from bob.learn.tensorflow.utils import load_mnist
+from bob.learn.tensorflow.network import SequenceNetwork
+from bob.learn.tensorflow.layers import Conv2D, FullyConnected
+
import tensorflow as tf
import shutil
@@ -22,10 +25,36 @@ validation_batch_size = 400
iterations = 50
seed = 10
-from test_cnn_scratch import scratch_network, validate_network
+
+def scratch_network():
+ # Creating a random network
+ scratch = SequenceNetwork(default_feature_layer="fc1")
+ scratch.add(Conv2D(name="conv1", kernel_size=3,
+ filters=10,
+ activation=tf.nn.tanh,
+ batch_norm=False))
+ scratch.add(FullyConnected(name="fc1", output_dim=10,
+ activation=None,
+ batch_norm=False
+ ))
+
+ return scratch
+
+
+def validate_network(validation_data, validation_labels, network):
+ # Testing
+ validation_data_shuffler = Memory(validation_data, validation_labels,
+ input_shape=[28, 28, 1],
+ batch_size=validation_batch_size)
+
+ [data, labels] = validation_data_shuffler.get_batch()
+ predictions = network.predict(data)
+ accuracy = 100. * numpy.sum(predictions == labels) / predictions.shape[0]
+
+ return accuracy
-def test_cnn_trainer_scratch():
+def test_cnn_pretrained():
train_data, train_labels, validation_data, validation_labels = load_mnist()
train_data = numpy.reshape(train_data, (train_data.shape[0], 28, 28, 1))
@@ -55,8 +84,7 @@ def test_cnn_trainer_scratch():
learning_rate=constant(0.05, name="lr"),
temp_dir=directory)
trainer.train(train_data_shuffler)
-
- accuracy = validate_network(validation_data, validation_labels, directory)
+ accuracy = validate_network(validation_data, validation_labels, scratch)
assert accuracy > 85
del scratch
@@ -77,7 +105,12 @@ def test_cnn_trainer_scratch():
trainer.train(train_data_shuffler)
- accuracy = validate_network(validation_data, validation_labels, directory2)
- assert accuracy > 85
+ accuracy = validate_network(validation_data, validation_labels, scratch)
+ assert accuracy > 90
shutil.rmtree(directory)
shutil.rmtree(directory2)
+
+ del scratch
+ del loss
+ del trainer
+
diff --git a/bob/learn/tensorflow/test/test_cnn_scratch.py b/bob/learn/tensorflow/test/test_cnn_scratch.py
index 242eac52..580985e7 100644
--- a/bob/learn/tensorflow/test/test_cnn_scratch.py
+++ b/bob/learn/tensorflow/test/test_cnn_scratch.py
@@ -7,12 +7,11 @@ import numpy
import bob.io.base
import os
from bob.learn.tensorflow.datashuffler import Memory, ImageAugmentation
-from bob.learn.tensorflow.initialization import Xavier, Constant
from bob.learn.tensorflow.network import SequenceNetwork
from bob.learn.tensorflow.loss import BaseLoss
from bob.learn.tensorflow.trainers import Trainer
from bob.learn.tensorflow.utils import load_mnist
-from bob.learn.tensorflow.layers import Conv2D, FullyConnected, MaxPooling
+from bob.learn.tensorflow.layers import Conv2D, FullyConnected
import tensorflow as tf
import shutil
@@ -33,13 +32,9 @@ def scratch_network():
scratch.add(Conv2D(name="conv1", kernel_size=3,
filters=10,
activation=tf.nn.tanh,
- weights_initialization=Xavier(seed=seed, use_gpu=False),
- bias_initialization=Constant(use_gpu=False),
batch_norm=False))
scratch.add(FullyConnected(name="fc1", output_dim=10,
activation=None,
- weights_initialization=Xavier(seed=seed, use_gpu=False),
- bias_initialization=Constant(use_gpu=False),
batch_norm=False
))
diff --git a/bob/learn/tensorflow/test/test_datashuffler.py b/bob/learn/tensorflow/test/test_datashuffler.py
index fb13e422..648fdbed 100644
--- a/bob/learn/tensorflow/test/test_datashuffler.py
+++ b/bob/learn/tensorflow/test/test_datashuffler.py
@@ -6,7 +6,7 @@
import numpy
from bob.learn.tensorflow.datashuffler import Memory, SiameseMemory, TripletMemory, Disk, SiameseDisk, TripletDisk
import pkg_resources
-from ..util import load_mnist
+from bob.learn.tensorflow.utils import load_mnist
import os
"""
diff --git a/bob/learn/tensorflow/test/test_datashuffler_augmentation.py b/bob/learn/tensorflow/test/test_datashuffler_augmentation.py
index 67de430d..ed1281dd 100644
--- a/bob/learn/tensorflow/test/test_datashuffler_augmentation.py
+++ b/bob/learn/tensorflow/test/test_datashuffler_augmentation.py
@@ -6,7 +6,7 @@
import numpy
from bob.learn.tensorflow.datashuffler import Memory, SiameseMemory, TripletMemory, Disk, SiameseDisk, TripletDisk, ImageAugmentation
import pkg_resources
-from ..util import load_mnist
+from bob.learn.tensorflow.utils import load_mnist
import os
"""
diff --git a/bob/learn/tensorflow/test/test_dnn.py b/bob/learn/tensorflow/test/test_dnn.py
index 613b744c..ddb5b0ff 100644
--- a/bob/learn/tensorflow/test/test_dnn.py
+++ b/bob/learn/tensorflow/test/test_dnn.py
@@ -8,13 +8,9 @@ from bob.learn.tensorflow.datashuffler import Memory
from bob.learn.tensorflow.network import MLP
from bob.learn.tensorflow.loss import BaseLoss
from bob.learn.tensorflow.trainers import Trainer, constant
-# from ..analyzers import ExperimentAnalizer, SoftmaxAnalizer
-from bob.learn.tensorflow.util import load_mnist
+from bob.learn.tensorflow.utils import load_mnist
import tensorflow as tf
-import bob.io.base
-import os
import shutil
-import bob.measure
"""
Some unit tests for the datashuffler
@@ -26,14 +22,25 @@ iterations = 200
seed = 10
+def validate_network(validation_data, validation_labels, network):
+ # Testing
+ validation_data_shuffler = Memory(validation_data, validation_labels,
+ input_shape=[784],
+ batch_size=validation_batch_size)
+
+ [data, labels] = validation_data_shuffler.get_batch()
+ predictions = network.predict(data)
+ accuracy = 100. * numpy.sum(predictions == labels) / predictions.shape[0]
+
+ return accuracy
+
+
def test_dnn_trainer():
train_data, train_labels, validation_data, validation_labels = load_mnist()
- train_data = numpy.reshape(train_data, (train_data.shape[0], 28, 28, 1))
- validation_data = numpy.reshape(validation_data, (validation_data.shape[0], 28, 28, 1))
# Creating datashufflers
train_data_shuffler = Memory(train_data, train_labels,
- input_shape=[28, 28, 1],
+ input_shape=[784],
batch_size=batch_size)
directory = "./temp/dnn"
@@ -53,21 +60,12 @@ def test_dnn_trainer():
learning_rate=constant(0.05, name="dnn_lr"),
temp_dir=directory)
trainer.train(train_data_shuffler)
- del trainer# Just to clean the variables
-
- with tf.Session() as session:
- # Testing
- mlp = MLP(10, hidden_layers=[15, 20])
- mlp.load(session, os.path.join(directory, "model.ckp"))
- validation_data_shuffler = Memory(validation_data, validation_labels,
- input_shape=[28, 28, 1],
- batch_size=validation_batch_size)
-
- [data, labels] = validation_data_shuffler.get_batch()
- predictions = mlp(data, session=session)
- accuracy = 100. * numpy.sum(numpy.argmax(predictions, 1) == labels) / predictions.shape[0]
-
- # At least 50% of accuracy for the DNN
- assert accuracy > 50.
- shutil.rmtree(directory)
- session.close()
+
+ accuracy = validate_network(validation_data, validation_labels, architecture)
+
+ # At least 50% of accuracy for the DNN
+ assert accuracy > 50.
+ shutil.rmtree(directory)
+
+ del architecture
+ del trainer # Just to clean the variables
diff --git a/bob/learn/tensorflow/trainers/SiameseTrainer.py b/bob/learn/tensorflow/trainers/SiameseTrainer.py
index ad7b558a..7b3b3764 100644
--- a/bob/learn/tensorflow/trainers/SiameseTrainer.py
+++ b/bob/learn/tensorflow/trainers/SiameseTrainer.py
@@ -49,9 +49,6 @@ class SiameseTrainer(Trainer):
temp_dir="cnn",
# Learning rate
- #base_learning_rate=0.001,
- #weight_decay=0.9,
- #decay_steps=1000,
learning_rate=constant(),
###### training options ##########
@@ -76,9 +73,6 @@ class SiameseTrainer(Trainer):
temp_dir=temp_dir,
# Learning rate
- #base_learning_rate=base_learning_rate,
- #weight_decay=weight_decay,
- #decay_steps=decay_steps,
learning_rate=learning_rate,
###### training options ##########
@@ -207,7 +201,7 @@ class SiameseTrainer(Trainer):
return feed_dict
- def fit(self, session, step):
+ def fit(self, step):
"""
Run one iteration (`forward` and `backward`)
@@ -217,19 +211,19 @@ class SiameseTrainer(Trainer):
"""
if self.prefetch:
- _, l, bt_class, wt_class, lr, summary = session.run([self.optimizer,
- self.training_graph, self.between_class_graph_train, self.within_class_graph_train,
- self.learning_rate, self.summaries_train])
+ _, l, bt_class, wt_class, lr, summary = self.session.run([self.optimizer,
+ self.training_graph, self.between_class_graph_train, self.within_class_graph_train,
+ self.learning_rate, self.summaries_train])
else:
feed_dict = self.get_feed_dict(self.train_data_shuffler)
- _, l, bt_class, wt_class, lr, summary = session.run([self.optimizer,
+ _, l, bt_class, wt_class, lr, summary = self.session.run([self.optimizer,
self.training_graph, self.between_class_graph_train, self.within_class_graph_train,
self.learning_rate, self.summaries_train], feed_dict=feed_dict)
logger.info("Loss training set step={0} = {1}".format(step, l))
self.train_summary_writter.add_summary(summary, step)
- def compute_validation(self, session, data_shuffler, step):
+ def compute_validation(self, data_shuffler, step):
"""
Computes the loss in the validation set
@@ -245,9 +239,9 @@ class SiameseTrainer(Trainer):
self.validation_graph = self.compute_graph(data_shuffler, name="validation", training=False)
feed_dict = self.get_feed_dict(data_shuffler)
- l, bt_class, wt_class = session.run([self.validation_graph,
- self.between_class_graph_validation, self.within_class_graph_validation],
- feed_dict=feed_dict)
+ l, bt_class, wt_class = self.session.run([self.validation_graph,
+ self.between_class_graph_validation, self.within_class_graph_validation],
+ feed_dict=feed_dict)
summaries = []
summaries.append(summary_pb2.Summary.Value(tag="loss", simple_value=float(l)))
@@ -268,7 +262,7 @@ class SiameseTrainer(Trainer):
tf.scalar_summary('lr', self.learning_rate, name="train")
return tf.merge_all_summaries()
- def load_and_enqueue(self, session):
+ def load_and_enqueue(self):
"""
Injecting data in the place holder queue
@@ -285,4 +279,4 @@ class SiameseTrainer(Trainer):
placeholder_right_data: batch_right,
placeholder_label: labels}
- session.run(self.enqueue_op, feed_dict=feed_dict)
+ self.session.run(self.enqueue_op, feed_dict=feed_dict)
diff --git a/bob/learn/tensorflow/trainers/Trainer.py b/bob/learn/tensorflow/trainers/Trainer.py
index 47e4f54f..c648c7e4 100644
--- a/bob/learn/tensorflow/trainers/Trainer.py
+++ b/bob/learn/tensorflow/trainers/Trainer.py
@@ -306,7 +306,7 @@ class Trainer(object):
"""
- saver = self.architecture.load(self.session, self.model_from_file)
+ saver = self.architecture.load(self.model_from_file)
# Loading training graph
self.training_graph = tf.get_collection("training_graph")[0]
@@ -357,21 +357,16 @@ class Trainer(object):
logger.info("Initializing !!")
- config = tf.ConfigProto(log_device_placement=True,
- gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.333))
- config.gpu_options.allow_growth = True
-
# Pickle the architecture to save
self.architecture.pickle_net(train_data_shuffler.deployment_shape)
- #with tf.Session(config=config) as session:
-
+ Session.create()
self.session = Session.instance().session
# Loading a pretrained model
if self.model_from_file != "":
logger.info("Loading pretrained model from {0}".format(self.model_from_file))
- saver = self.bootstrap_graphs_fromfile(self.session, train_data_shuffler, validation_data_shuffler)
+ saver = self.bootstrap_graphs_fromfile(train_data_shuffler, validation_data_shuffler)
else:
# Bootstraping all the graphs
self.bootstrap_graphs(train_data_shuffler, validation_data_shuffler)
@@ -408,7 +403,7 @@ class Trainer(object):
for step in range(self.iterations):
start = time.time()
- self.fit(self.session, step)
+ self.fit(step)
end = time.time()
summary = summary_pb2.Summary.Value(tag="elapsed_time", simple_value=float(end-start))
self.train_summary_writter.add_summary(summary_pb2.Summary(value=[summary]), step)
diff --git a/bob/learn/tensorflow/trainers/TripletTrainer.py b/bob/learn/tensorflow/trainers/TripletTrainer.py
index 093bd45c..4c287a72 100644
--- a/bob/learn/tensorflow/trainers/TripletTrainer.py
+++ b/bob/learn/tensorflow/trainers/TripletTrainer.py
@@ -49,9 +49,6 @@ class TripletTrainer(Trainer):
temp_dir="cnn",
# Learning rate
- #base_learning_rate=0.001,
- #weight_decay=0.9,
- #decay_steps=1000,
learning_rate=constant(),
###### training options ##########
@@ -76,9 +73,6 @@ class TripletTrainer(Trainer):
temp_dir=temp_dir,
# Learning rate
- #base_learning_rate=base_learning_rate,
- #weight_decay=weight_decay,
- #decay_steps=decay_steps,
learning_rate=learning_rate,
###### training options ##########
@@ -213,7 +207,7 @@ class TripletTrainer(Trainer):
return feed_dict
- def fit(self, session, step):
+ def fit(self, step):
"""
Run one iteration (`forward` and `backward`)
@@ -223,21 +217,21 @@ class TripletTrainer(Trainer):
"""
if self.prefetch:
- _, l, bt_class, wt_class, lr, summary = session.run([self.optimizer,
- self.training_graph, self.between_class_graph_train,
- self.within_class_graph_train, self.learning_rate,
- self.summaries_train])
+ _, l, bt_class, wt_class, lr, summary = self.session.run([self.optimizer,
+ self.training_graph, self.between_class_graph_train,
+ self.within_class_graph_train, self.learning_rate,
+ self.summaries_train])
else:
feed_dict = self.get_feed_dict(self.train_data_shuffler)
- _, l, bt_class, wt_class, lr, summary = session.run([self.optimizer,
- self.training_graph, self.between_class_graph_train,
- self.within_class_graph_train,
- self.learning_rate, self.summaries_train],
- feed_dict=feed_dict)
+ _, l, bt_class, wt_class, lr, summary = self.session.run([self.optimizer,
+ self.training_graph, self.between_class_graph_train,
+ self.within_class_graph_train,
+ self.learning_rate, self.summaries_train],
+ feed_dict=feed_dict)
logger.info("Loss training set step={0} = {1}".format(step, l))
self.train_summary_writter.add_summary(summary, step)
- def compute_validation(self, session, data_shuffler, step):
+ def compute_validation(self, data_shuffler, step):
"""
Computes the loss in the validation set
@@ -250,13 +244,13 @@ class TripletTrainer(Trainer):
if self.validation_summary_writter is None:
self.validation_summary_writter = tf.train.SummaryWriter(os.path.join(self.temp_dir, 'validation'),
- session.graph)
+ self.session.graph)
self.validation_graph = self.compute_graph(data_shuffler, name="validation", training=False)
feed_dict = self.get_feed_dict(data_shuffler)
- l, bt_class, wt_class = session.run([self.validation_graph,
- self.between_class_graph_validation, self.within_class_graph_validation],
- feed_dict=feed_dict)
+ l, bt_class, wt_class = self.session.run([self.validation_graph,
+ self.between_class_graph_validation, self.within_class_graph_validation],
+ feed_dict=feed_dict)
summaries = []
summaries.append(summary_pb2.Summary.Value(tag="loss", simple_value=float(l)))
@@ -277,7 +271,7 @@ class TripletTrainer(Trainer):
tf.scalar_summary('lr', self.learning_rate, name="train")
return tf.merge_all_summaries()
- def load_and_enqueue(self, session):
+ def load_and_enqueue(self):
"""
Injecting data in the place holder queue
@@ -294,4 +288,4 @@ class TripletTrainer(Trainer):
placeholder_positive_data: batch_positive,
placeholder_negative_data: batch_negative}
- session.run(self.enqueue_op, feed_dict=feed_dict)
+ self.session.run(self.enqueue_op, feed_dict=feed_dict)
diff --git a/bob/learn/tensorflow/utils/session.py b/bob/learn/tensorflow/utils/session.py
index cd123bd5..a539eb32 100644
--- a/bob/learn/tensorflow/utils/session.py
+++ b/bob/learn/tensorflow/utils/session.py
@@ -15,6 +15,3 @@ class Session(object):
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.333))
config.gpu_options.allow_growth = True
self.session = tf.Session()
-
- #def __del__(self):
- # self.session.close()
\ No newline at end of file
diff --git a/doc/py_api.rst b/doc/py_api.rst
index 576cedf4..99b9b0c7 100644
--- a/doc/py_api.rst
+++ b/doc/py_api.rst
@@ -2,6 +2,8 @@
.. Tiago de Freitas Pereira <laurent.el-shafey@idiap.ch>
.. Tue 28 Aug 2012 18:09:40 CEST
+.. _py_api:
+
============
Python API
============
diff --git a/doc/user_guide.rst b/doc/user_guide.rst
index e5732845..6f4fb7de 100644
--- a/doc/user_guide.rst
+++ b/doc/user_guide.rst
@@ -8,8 +8,8 @@
===========
-Getting started
----------------
+Quick start
+-----------
Before explain the base elements of this library, lets first do a simple example.
The example consists in training a very simple **CNN** with `MNIST` dataset in 4 steps.
@@ -48,18 +48,19 @@ The example consists in training a very simple **CNN** with `MNIST` dataset in 4
.. doctest::
- >>> with tf.Session() as session:
- >>> # Loading the model
- >>> architecture = bob.learn.tensorflow.network.SequenceNetwork()
- >>> architecture.load(session, "./cnn/model.ckp")
- >>> # Predicting
- >>> predictions = scratch.predict(validation_data, session=session)
- >>> # Computing an awesome accuracy for a simple network and 100 iterations
- >>> accuracy = 100. * numpy.sum(predictions == validation_labels) / predictions.shape[0]
- >>> print accuracy
+ >>> # Loading the model
+ >>> architecture = bob.learn.tensorflow.network.SequenceNetwork()
+ >>> architecture.load("./cnn/model.ckp")
+ >>> # Predicting
+ >>> predictions = scratch.predict(validation_data, session=session)
+ >>> # Computing an awesome accuracy for a simple network and 100 iterations
+ >>> accuracy = 100. * numpy.sum(predictions == validation_labels) / predictions.shape[0]
+ >>> print accuracy
90.4714285714
-Now lets describe each step in detail.
+
+Understanding what you have done
+--------------------------------
Preparing your input data
@@ -81,9 +82,9 @@ number of channels.
Creating the architecture
.........................
-Architectures are assembled as a :py:class:`bob.learn.tensorflow.network.SequenceNetwork` object.
-Once the objects are created it is necessary to fill it up with `Layers`_.
-The library has already some crafted networks implemented in `Architectures`_
+Architectures are assembled in the :py:class:`bob.learn.tensorflow.network.SequenceNetwork` object.
+Once the objects are created it is necessary to fill it up with `Layers <py_api.html#layers>`_
+The library has already some crafted networks implemented in `Architectures <py_api.html#architectures>`_
Defining a loss and training
@@ -99,6 +100,80 @@ As for the loss, we have specific trainers for Siamese (:py:class:`bob.learn.ten
nd Triplet networks (:py:class:`bob.learn.tensorflow.trainers.TripletTrainer`).
+Components in detail
+--------------------
+
+If you have reached this point it means that you want to understand a little bit more on how this library works.
+The next sections give some details of each element.
+
+Data Shufflers
+..............
+
+As mentioned before, datasets are wrapped in **data shufflers**.
+Data shufflers were designed to shuffle the input data for stochastic training.
+It has one basic functionality which is :py:meth:`bob.learn.tensorflow.datashuffler.Base.get_batch` functionality.
+
+The shufflers are categorized with respect to:
+ 1. How the data is fetched
+ 2. The type of the trainer
+ 3. How the data is sampled
+
+How do you want to fetch your data?
+```````````````````````````````````
+
+The data can be fetched either from the memory (:py:class:`bob.learn.tensorflow.datashuffler.Memory`), as in out example, or from
+disk (:py:class:`bob.learn.tensorflow.datashuffler.Disk`).
+To train networks fetched from the disk, your training data must be a list of paths like in the example below:
+
+.. doctest::
+
+ >>> train_data = ['./file/id1_0.jpg', './file/id1_1.jpg', './file/id2_1.jpg']
+ >>> train_labels = [0, 0, 1]
+
+With disk data shufflers, the data is loaded on the fly.
+
+
+How is the shape of your trainer?
+`````````````````````````````````
+
+Here we have one data shuffler for each type of the trainer.
+
+You will see in the section `Trainers`_ that we have three types of trainer.
+The first one is the regular trainer, which deals with one graph only.
+The data shuflers for this type of trainer must be a direct instance of either :py:class:`bob.learn.tensorflow.datashuffler.Memory`
+or :py:class:`bob.learn.tensorflow.datashuffler.Disk`.
+
+The second one is the :py:class:`bob.learn.tensorflow.trainers.Siamese` trainer, which is designed to train Siamese networks.
+The data shuflers for this type of trainer must be a direct instance of either
+
+The third one is the :py:class:`bob.learn.tensorflow.trainers.Triplet` trainer, which is designed to train Triplet networks.
+
+
+
+Architecture
+............
+
+Trainers
+........
+
+
+Layers
+......
+
+
+Initialization
+..............
+
+
+Loss
+....
+
+Analyzers
+.........
+
+
+
+
Sandbox
-------
--
GitLab