Skip to content
GitLab
Commit b16aa7c5 authored by Tiago de Freitas Pereira's avatar Tiago de Freitas Pereira
Browse files

Fixed issues with the siamese

parent b85a344a
Hide whitespace changes
Inline Side-by-side
bob/learn/tensorflow/script/train_mnist.py deleted 100644 → 0
View file @ b85a344a
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Wed 11 May 2016 09:39:36 CEST
"""
Simple script that trains MNIST with LENET using Tensor flow
Usage:
train_mnist.py [--batch-size=<arg> --validation-batch-size=<arg> --iterations=<arg> --validation-interval=<arg> --use-gpu]
train_mnist.py -h | --help
Options:
-h --help Show this screen.
--batch-size=<arg> [default: 1]
--validation-batch-size=<arg> [default:128]
--iterations=<arg> [default: 30000]
--validation-interval=<arg> [default: 100]
"""
from docopt import docopt
import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.datashuffler import Memory, SiameseMemory, TripletMemory
from bob.learn.tensorflow.network import Lenet, MLP, Dummy, Chopra
from bob.learn.tensorflow.trainers import Trainer
from bob.learn.tensorflow.loss import BaseLoss
import bob.io.base
from ..analyzers import ExperimentAnalizer, SoftmaxAnalizer
import numpy
def main():
args = docopt(__doc__, version='Mnist training with TensorFlow')
BATCH_SIZE = int(args['--batch-size'])
VALIDATION_BATCH_SIZE = int(args['--validation-batch-size'])
ITERATIONS = int(args['--iterations'])
VALIDATION_TEST = int(args['--validation-interval'])
USE_GPU = args['--use-gpu']
perc_train = 0.9
mnist = True
train_data, train_labels, validation_data, validation_labels = \
util.load_mnist(data_dir="./src/bob.db.mnist/bob/db/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],
batch_size=BATCH_SIZE)
validation_data_shuffler = Memory(validation_data, validation_labels,
input_shape=[28, 28, 1],
batch_size=VALIDATION_BATCH_SIZE)
# Preparing the architecture
cnn = True
if cnn:
architecture = Chopra(seed=SEED, fc1_output=10, batch_norm=False)
loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
trainer = Trainer(architecture=architecture,
loss=loss,
iterations=ITERATIONS,
prefetch=False, temp_dir="./temp/cnn/no-batch-norm")
#prefetch = False, temp_dir = "./temp/cnn/batch-norm-2convs-all-relu")
trainer.train(train_data_shuffler, validation_data_shuffler)
#trainer.train(train_data_shuffler)
else:
mlp = MLP(10, hidden_layers=[15, 20])
loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
trainer = Trainer(architecture=mlp, loss=loss, iterations=ITERATIONS, temp_dir="./LOGS/dnn")
trainer.train(train_data_shuffler, validation_data_shuffler)
# Loading
#test_data_shuffler = Memory(validation_data, validation_labels,
# input_shape=[28, 28, 1],
# batch_size=400)
#with tf.Session() as session:
#new_net = Chopra(seed=SEED, fc1_output=10)
#new_net.load(bob.io.base.HDF5File("./temp/cnn/model.hdf5"), shape=[400, 28, 28, 1], session=session)
#[data, labels] = test_data_shuffler.get_batch()
#print new_net(data, session)
bob/learn/tensorflow/script/train_mnist_siamese.py deleted 100644 → 0
View file @ b85a344a
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Wed 11 May 2016 09:39:36 CEST
"""
Simple script that trains MNIST with LENET using Tensor flow
Usage:
train_mnist_siamese.py [--batch-size=<arg> --validation-batch-size=<arg> --iterations=<arg> --validation-interval=<arg> --use-gpu]
train_mnist_siamese.py -h | --help
Options:
-h --help Show this screen.
--batch-size=<arg> [default: 1]
--validation-batch-size=<arg> [default:128]
--iterations=<arg> [default: 30000]
--validation-interval=<arg> [default: 100]
"""
from docopt import docopt
import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.datashuffler import SiameseMemory
from bob.learn.tensorflow.network import Lenet, MLP, LenetDropout, VGG, Chopra, Dummy
from bob.learn.tensorflow.trainers import SiameseTrainer
from bob.learn.tensorflow.loss import ContrastiveLoss
import numpy
def main():
args = docopt(__doc__, version='Mnist training with TensorFlow')
BATCH_SIZE = int(args['--batch-size'])
VALIDATION_BATCH_SIZE = int(args['--validation-batch-size'])
ITERATIONS = int(args['--iterations'])
VALIDATION_TEST = int(args['--validation-interval'])
USE_GPU = args['--use-gpu']
perc_train = 0.9
# Loading data
train_data, train_labels, validation_data, validation_labels = \
util.load_mnist(data_dir="./src/bob.db.mnist/bob/db/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))
train_data_shuffler = SiameseMemory(train_data, train_labels,
input_shape=[28, 28, 1],
scale=True,
batch_size=BATCH_SIZE)
validation_data_shuffler = SiameseMemory(validation_data, validation_labels,
input_shape=[28, 28, 1],
scale=True,
batch_size=VALIDATION_BATCH_SIZE)
# Preparing the architecture
n_classes = len(train_data_shuffler.possible_labels)
cnn = True
if cnn:
# LENET PAPER CHOPRA
architecture = Chopra(seed=SEED, fc1_output=n_classes)
loss = ContrastiveLoss(contrastive_margin=4.)
#optimizer = tf.train.GradientDescentOptimizer(0.000001)
trainer = SiameseTrainer(architecture=architecture,
loss=loss,
iterations=ITERATIONS,
snapshot=VALIDATION_TEST,
prefetch=False,
temp_dir="./LOGS/siamese-cnn-prefetch")
trainer.train(train_data_shuffler, validation_data_shuffler)
else:
mlp = MLP(n_classes, hidden_layers=[15, 20])
loss = ContrastiveLoss()
trainer = SiameseTrainer(architecture=mlp,
loss=loss,
iterations=ITERATIONS,
snapshot=VALIDATION_TEST,
temp_dir="./LOGS/siamese-dnn")
trainer.train(train_data_shuffler, validation_data_shuffler)
bob/learn/tensorflow/script/train_mnist_triplet.py deleted 100644 → 0
View file @ b85a344a
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Wed 11 May 2016 09:39:36 CEST
"""
Simple script that trains MNIST with LENET using Tensor flow
Usage:
train_mnist_triplet.py [--batch-size=<arg> --validation-batch-size=<arg> --iterations=<arg> --validation-interval=<arg> --use-gpu]
train_mnist_triplet.py -h | --help
Options:
-h --help Show this screen.
--batch-size=<arg> [default: 1]
--validation-batch-size=<arg> [default:128]
--iterations=<arg> [default: 30000]
--validation-interval=<arg> [default: 100]
"""
from docopt import docopt
import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.datashuffler import TripletMemory, TripletWithSelectionMemory
from bob.learn.tensorflow.network import Lenet, MLP, LenetDropout, VGG, Chopra, Dummy, FaceNet
from bob.learn.tensorflow.trainers import TripletTrainer
from bob.learn.tensorflow.loss import TripletLoss
import numpy
def main():
args = docopt(__doc__, version='Mnist training with TensorFlow')
BATCH_SIZE = int(args['--batch-size'])
VALIDATION_BATCH_SIZE = int(args['--validation-batch-size'])
ITERATIONS = int(args['--iterations'])
VALIDATION_TEST = int(args['--validation-interval'])
USE_GPU = args['--use-gpu']
perc_train = 0.9
# Loading data
train_data, train_labels, validation_data, validation_labels = \
util.load_mnist(data_dir="./src/bob.db.mnist/bob/db/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))
#train_data_shuffler = MemoryDataShuffler(train_data, train_labels,
# input_shape=[28, 28, 1],
# scale=True,
# batch_size=BATCH_SIZE)
#validation_data_shuffler = MemoryDataShuffler(validation_data, validation_labels,
# input_shape=[28, 28, 1],
# scale=True,
# batch_size=VALIDATION_BATCH_SIZE)
validation_data_shuffler = TripletMemory(train_data, train_labels,
input_shape=[28, 28, 1],
scale=True,
batch_size=VALIDATION_BATCH_SIZE)
train_data_shuffler = TripletWithSelectionMemory(train_data, train_labels,
input_shape=[28, 28, 1],
scale=True,
batch_size=BATCH_SIZE)
#train_data_shuffler = TripletMemory(train_data, train_labels,
# input_shape=[28, 28, 1],
# scale=True,
# batch_size=BATCH_SIZE)
# Preparing the architecture
n_classes = len(train_data_shuffler.possible_labels)
#n_classes = 200
cnn = True
if cnn:
architecture = FaceNet(seed=SEED, use_gpu=USE_GPU)
#architecture = Chopra(seed=SEED, fc1_output=n_classes, use_gpu=USE_GPU)
#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)
#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(0.000001)
trainer = TripletTrainer(architecture=architecture,
loss=loss,
iterations=ITERATIONS,
snapshot=VALIDATION_TEST,
temp_dir="triplet/cnn-triplet-SELECTION",
prefetch=False,
optimizer=optimizer
)
trainer.train(train_data_shuffler, validation_data_shuffler)
#trainer.train(train_data_shuffler)
else:
mlp = MLP(n_classes, hidden_layers=[15, 20])
loss = TripletLoss()
trainer = TripletTrainer(architecture=mlp,
loss=loss,
temp_dir="dnn-triplet",
iterations=ITERATIONS,
snapshot=VALIDATION_TEST)
#trainer.train(train_data_shuffler, validation_data_shuffler)
trainer.train(train_data_shuffler)
bob/learn/tensorflow/script/train_mobio.py deleted 100644 → 0
View file @ b85a344a
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Wed 11 May 2016 09:39:36 CEST
"""
Simple script that trains CASIA WEBFACE
Usage:
train_mobio.py [--batch-size=<arg> --validation-batch-size=<arg> --iterations=<arg> --validation-interval=<arg> --use-gpu]
train_mobio.py -h | --help
Options:
-h --help Show this screen.
--batch-size=<arg> [default: 1]
--validation-batch-size=<arg> [default:128]
--iterations=<arg> [default: 30000]
--validation-interval=<arg> [default: 100]
"""
from docopt import docopt
import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.datashuffler import TripletWithSelectionDisk, TripletDisk, TripletWithFastSelectionDisk
from bob.learn.tensorflow.network import Lenet, MLP, LenetDropout, VGG, Chopra, Dummy, FaceNet, FaceNetSimple, VGG16
from bob.learn.tensorflow.trainers import SiameseTrainer, Trainer, TripletTrainer, constant
from bob.learn.tensorflow.loss import ContrastiveLoss, BaseLoss, TripletLoss
import numpy
import os
#os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2,3"
os.environ["CUDA_VISIBLE_DEVICES"] = ""
def main():
args = docopt(__doc__, version='Mnist training with TensorFlow')
BATCH_SIZE = int(args['--batch-size'])
VALIDATION_BATCH_SIZE = int(args['--validation-batch-size'])
ITERATIONS = int(args['--iterations'])
VALIDATION_TEST = int(args['--validation-interval'])
USE_GPU = args['--use-gpu']
perc_train = 0.9
import bob.db.mobio
db_mobio = bob.db.mobio.Database()
directory = "/idiap/temp/tpereira/DEEP_FACE/CASIA_WEBFACE/mobio/preprocessed/"
#directory = "./preprocessed/"
# Preparing train set
#train_objects = db_mobio.objects(protocol="male", groups="world")
train_objects = sorted(db_mobio.objects(protocol="male", groups="world"), key=lambda x: x.id)
train_labels = [int(o.client_id) for o in train_objects]
n_classes = len(set(train_labels))
train_file_names = [o.make_path(
directory=directory,
extension=".hdf5")
for o in train_objects]
#train_data_shuffler = TripletWithSelectionDisk(train_file_names, train_labels,
# input_shape=[56, 56, 3],
# total_identities=8,
# batch_size=BATCH_SIZE)
train_data_shuffler = TripletWithFastSelectionDisk(train_file_names, train_labels,
input_shape=[224, 224, 3],
batch_size=BATCH_SIZE,
total_identities=8)
# Preparing train set
validation_objects = sorted(db_mobio.objects(protocol="male", groups="dev"), key=lambda x: x.id)
#validation_objects = db_mobio.objects(protocol="male", groups="world")
validation_labels = [o.client_id for o in validation_objects]
validation_file_names = [o.make_path(
directory=directory,
extension=".hdf5")
for o in validation_objects]
validation_data_shuffler = TripletDisk(validation_file_names, validation_labels,
input_shape=[224, 224, 3],
batch_size=VALIDATION_BATCH_SIZE)
# Preparing the architecture
#architecture = Chopra(seed=SEED, fc1_output=n_classes)
#architecture = FaceNet(seed=SEED, use_gpu=USE_GPU)
architecture = VGG16(seed=SEED, use_gpu=USE_GPU)
#loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
#trainer = Trainer(architecture=architecture, loss=loss,
# iterations=ITERATIONS,
# prefetch=False,
# optimizer=optimizer,
# temp_dir="./LOGS/cnn")
#loss = ContrastiveLoss(contrastive_margin=4.)
#trainer = SiameseTrainer(architecture=architecture, loss=loss,
# iterations=ITERATIONS,
# prefetch=False,
# optimizer=optimizer,
# temp_dir="./LOGS_MOBIO/siamese-cnn-prefetch")
loss = TripletLoss(margin=0.2)
optimizer = tf.train.GradientDescentOptimizer(0.05)
trainer = TripletTrainer(architecture=architecture, loss=loss,
iterations=ITERATIONS,
learning_rate=constant(0.05),
prefetch=False,
optimizer=optimizer,
snapshot=200,
temp_dir="/idiap/temp/tpereira/VGG16/mobio_world")
#trainer.train(train_data_shuffler, validation_data_shuffler)
trainer.train(train_data_shuffler)
bob/learn/tensorflow/script/train_siamese_casia_webface.py deleted 100644 → 0
View file @ b85a344a
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Wed 11 May 2016 09:39:36 CEST
"""
Simple script that trains CASIA WEBFACE
Usage:
train_siamese_casia_webface.py [--batch-size=<arg> --validation-batch-size=<arg> --iterations=<arg> --validation-interval=<arg> --use-gpu]
train_siamese_casia_webface.py -h | --help
Options:
-h --help Show this screen.
--batch-size=<arg> [default: 1]
--validation-batch-size=<arg> [default:128]
--iterations=<arg> [default: 30000]
--validation-interval=<arg> [default: 100]
"""
from docopt import docopt
import tensorflow as tf
from .. import util
SEED = 10
from bob.learn.tensorflow.datashuffler import TripletDisk, TripletWithSelectionDisk, TripletWithFastSelectionDisk
from bob.learn.tensorflow.network import Lenet, MLP, LenetDropout, VGG, Chopra, Dummy, FaceNet, FaceNetSimple, VGG16
from bob.learn.tensorflow.trainers import SiameseTrainer, TripletTrainer, constant
from bob.learn.tensorflow.loss import ContrastiveLoss, TripletLoss
import numpy
def main():
args = docopt(__doc__, version='Mnist training with TensorFlow')
BATCH_SIZE = int(args['--batch-size'])
VALIDATION_BATCH_SIZE = int(args['--validation-batch-size'])
ITERATIONS = int(args['--iterations'])
VALIDATION_TEST = int(args['--validation-interval'])
USE_GPU = args['--use-gpu']
perc_train = 0.9
import bob.db.mobio
db_mobio = bob.db.mobio.Database()
import bob.db.casia_webface
db_casia = bob.db.casia_webface.Database()
# Preparing train set
train_objects = sorted(db_casia.objects(groups="world"), key=lambda x: x.id)
#train_objects = db.objects(groups="world")
train_labels = [int(o.client_id) for o in train_objects]
directory = "/idiap/temp/tpereira/DEEP_FACE/CASIA_WEBFACE/casia_webface/preprocessed"
train_file_names = [o.make_path(
directory=directory,
extension=".hdf5")
for o in train_objects]
#train_data_shuffler = TripletWithFastSelectionDisk(train_file_names, train_labels,
# input_shape=[224, 224, 3],
# batch_size=BATCH_SIZE,
# total_identities=16)
train_data_shuffler = TripletDisk(train_file_names, train_labels,
input_shape=[224, 224, 3],
batch_size=VALIDATION_BATCH_SIZE)
# Preparing train set
directory = "/idiap/temp/tpereira/DEEP_FACE/CASIA_WEBFACE/mobio/preprocessed"
validation_objects = sorted(db_mobio.objects(protocol="male", groups="dev"), key=lambda x: x.id)
validation_labels = [o.client_id for o in validation_objects]
validation_file_names = [o.make_path(
directory=directory,
extension=".hdf5")
for o in validation_objects]
validation_data_shuffler = TripletDisk(validation_file_names, validation_labels,
input_shape=[224, 224, 3],
batch_size=VALIDATION_BATCH_SIZE)
# Preparing the architecture
# LENET PAPER CHOPRA
#architecture = FaceNetSimple(seed=SEED, use_gpu=USE_GPU)
architecture = VGG16(seed=SEED, use_gpu=USE_GPU)
optimizer = tf.train.GradientDescentOptimizer(0.05)
loss = TripletLoss(margin=0.2)
trainer = TripletTrainer(architecture=architecture, loss=loss,
iterations=ITERATIONS,
learning_rate=constant(),
optimizer=optimizer,
prefetch=False,
temp_dir="/idiap/temp/tpereira/CNN_MODELS_GRAD_DESC/triplet-cnn-selection-gpu")
#import ipdb; ipdb.set_trace()
#trainer.train(train_data_shuffler, validation_data_shuffler)
trainer.train(train_data_shuffler)
bob/learn/tensorflow/trainers/SiameseTrainer.py
View file @ b16aa7c5
......@@ -138,7 +138,7 @@ class SiameseTrainer(Trainer):
tf.get_collection("validation_placeholder_data2")[0],
tf.get_collection("validation_placeholder_label")[0])
def compute_graph(self, data_shuffler, prefetch=False, name="", train=True):
def compute_graph(self, data_shuffler, prefetch=False, name="", training=True):
"""
Computes the graph for the trainer.
......@@ -173,14 +173,14 @@ class SiameseTrainer(Trainer):
[feature_left_batch, feature_right_batch, label_batch] = data_shuffler.get_placeholders(name=name)
# Creating the siamese graph
train_left_graph = self.architecture.compute_graph(feature_left_batch)
train_right_graph = self.architecture.compute_graph(feature_right_batch)
train_left_graph = self.architecture.compute_graph(feature_left_batch, training=training)
train_right_graph = self.architecture.compute_graph(feature_right_batch, training=training)
graph, between_class_graph, within_class_graph = self.loss(label_batch,
train_left_graph,
train_right_graph)
if train:
if training:
self.between_class_graph_train = between_class_graph
self.within_class_graph_train = within_class_graph
else:
......@@ -243,7 +243,7 @@ class SiameseTrainer(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.validation_graph = self.compute_graph(data_shuffler, name="validation", train=False)
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],
......
bob/learn/tensorflow/trainers/Trainer.py
View file @ b16aa7c5
......@@ -266,10 +266,6 @@ class Trainer(object):
self.validation_graph = self.compute_graph(validation_data_shuffler, name="validation", training=False)
tf.add_to_collection("validation_graph", self.validation_graph)
batch, label = validation_data_shuffler.get_placeholders()
tf.add_to_collection("validation_placeholder_data", batch)
tf.add_to_collection("validation_placeholder_label", label)
self.bootstrap_placeholders(train_data_shuffler, validation_data_shuffler)
def bootstrap_placeholders(self, train_data_shuffler, validation_data_shuffler):
......
bob/learn/tensorflow/trainers/TripletTrainer.py
View file @ b16aa7c5
......@@ -137,7 +137,7 @@ class TripletTrainer(Trainer):
tf.get_collection("validation_placeholder_data2")[0],
tf.get_collection("validation_placeholder_data3")[0])
def compute_graph(self, data_shuffler, prefetch=False, name="", train=True):
def compute_graph(self, data_shuffler, prefetch=False, name="", training=True):
"""
Computes the graph for the trainer.
......@@ -177,15 +177,15 @@ class TripletTrainer(Trainer):
data_shuffler.get_placeholders(name=name)
# Creating the siamese graph
train_anchor_graph = self.architecture.compute_graph(feature_anchor_batch)
train_positive_graph = self.architecture.compute_graph(feature_positive_batch)
train_negative_graph = self.architecture.compute_graph(feature_negative_batch)
train_anchor_graph = self.architecture.compute_graph(feature_anchor_batch, training=training)
train_positive_graph = self.architecture.compute_graph(feature_positive_batch, training=training)
train_negative_graph = self.architecture.compute_graph(feature_negative_batch, training=training)
graph, between_class_graph, within_class_graph = self.loss(train_anchor_graph,
train_positive_graph,
train_negative_graph)
if train:
if training:
self.between_class_graph_train = between_class_graph
self.within_class_graph_train = within_class_graph
else:
......@@ -252,7 +252,7 @@ class TripletTrainer(Trainer):
self.validation_summary_writter = tf.train.SummaryWriter(os.path.join(self.temp_dir, 'validation'),
session.graph)
self.validation_graph = self.compute_graph(data_shuffler, name="validation", train=False)
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,