From a8e61de817e8aad365b8691a03262d051849fa34 Mon Sep 17 00:00:00 2001
From: Tiago Freitas Pereira <tiagofrepereira@gmail.com>
Date: Tue, 25 Oct 2016 17:00:41 +0200
Subject: [PATCH] Updated triplet trainer
---
bob/learn/tensorflow/datashuffler/Base.py | 11 ++++
bob/learn/tensorflow/datashuffler/Memory.py | 3 +-
.../tensorflow/datashuffler/OnlineSampling.py | 4 +-
bob/learn/tensorflow/datashuffler/Siamese.py | 18 ++---
.../tensorflow/datashuffler/SiameseDisk.py | 16 ++---
.../tensorflow/datashuffler/SiameseMemory.py | 24 ++++---
.../tensorflow/datashuffler/TripletDisk.py | 21 +++---
.../tensorflow/datashuffler/TripletMemory.py | 31 +++++----
.../TripletWithFastSelectionDisk.py | 25 ++-----
.../datashuffler/TripletWithSelectionDisk.py | 66 ++++++++-----------
bob/learn/tensorflow/loss/TripletLoss.py | 16 +++--
bob/learn/tensorflow/script/train_mobio.py | 26 ++++----
.../script/train_siamese_casia_webface.py | 4 +-
bob/learn/tensorflow/trainers/Trainer.py | 3 +-
.../tensorflow/trainers/TripletTrainer.py | 2 +-
buildout.cfg | 3 +-
16 files changed, 134 insertions(+), 139 deletions(-)
diff --git a/bob/learn/tensorflow/datashuffler/Base.py b/bob/learn/tensorflow/datashuffler/Base.py
index 1bdb2475..ae804e75 100644
--- a/bob/learn/tensorflow/datashuffler/Base.py
+++ b/bob/learn/tensorflow/datashuffler/Base.py
@@ -149,5 +149,16 @@ class Base(object):
shape = tuple([1] + list(data.shape))
return numpy.reshape(data, shape)
+ def normalize_sample(self, x):
+ """
+ Normalize the sample.
+
+ For the time being I'm only scaling from 0-1
+ """
+
+ if self.scale:
+ return x * self.scale_value
+ return x
+
diff --git a/bob/learn/tensorflow/datashuffler/Memory.py b/bob/learn/tensorflow/datashuffler/Memory.py
index 1a6e4584..31911e58 100644
--- a/bob/learn/tensorflow/datashuffler/Memory.py
+++ b/bob/learn/tensorflow/datashuffler/Memory.py
@@ -59,7 +59,6 @@ class Memory(Base):
img = self.data_augmentation(img)
selected_data[i, ...] = self.bob2skimage(img)
- if self.scale:
- selected_data *= self.scale_value
+ selected_data = self.normalize_sample(selected_data)
return [selected_data.astype("float32"), selected_labels.astype("int64")]
diff --git a/bob/learn/tensorflow/datashuffler/OnlineSampling.py b/bob/learn/tensorflow/datashuffler/OnlineSampling.py
index daf989de..781194dc 100644
--- a/bob/learn/tensorflow/datashuffler/OnlineSampling.py
+++ b/bob/learn/tensorflow/datashuffler/OnlineSampling.py
@@ -44,9 +44,11 @@ class OnLineSampling(object):
if self.feature_placeholder is None:
shape = tuple([None] + list(data.shape[1:]))
self.feature_placeholder = tf.placeholder(tf.float32, shape=shape, name="feature")
- self.graph = self.feature_extractor.compute_graph(self.feature_placeholder, self.feature_extractor.default_feature_layer,
+ embbeding = self.feature_extractor.compute_graph(self.feature_placeholder, self.feature_extractor.default_feature_layer,
training=False)
+ self.graph = tf.nn.l2_normalize(embbeding, 1, 1e-10, name='embeddings')
+
#if self.feature_placeholder.get_shape().as_list() != list(data.shape):
#tf.reshape(self.feature_placeholder, tf.pack([data.shape]))
#self.feature_placeholder.set_shape(data.shape)
diff --git a/bob/learn/tensorflow/datashuffler/Siamese.py b/bob/learn/tensorflow/datashuffler/Siamese.py
index 3d0d3e47..78ce6419 100644
--- a/bob/learn/tensorflow/datashuffler/Siamese.py
+++ b/bob/learn/tensorflow/datashuffler/Siamese.py
@@ -63,8 +63,8 @@ class Siamese(Base):
numpy.random.shuffle(indexes)
# Picking a pair
- data = input_data[indexes[0], ...]
- data_p = input_data[indexes[1], ...]
+ sample_l = input_data[indexes[0], ...]
+ sample_r = input_data[indexes[1], ...]
else:
# Picking a pair of labels from different clients
@@ -73,13 +73,13 @@ class Siamese(Base):
index[1] = self.possible_labels[int(index[1])]
# Getting the indexes of the two clients
- indexes = numpy.where(input_labels == index[0])[0]
- indexes_p = numpy.where(input_labels == index[1])[0]
- numpy.random.shuffle(indexes)
- numpy.random.shuffle(indexes_p)
+ indexes_l = numpy.where(input_labels == index[0])[0]
+ indexes_r = numpy.where(input_labels == index[1])[0]
+ numpy.random.shuffle(indexes_l)
+ numpy.random.shuffle(indexes_r)
# Picking a pair
- data = input_data[indexes[0], ...]
- data_p = input_data[indexes_p[0], ...]
+ sample_l = input_data[indexes_l[0], ...]
+ sample_r = input_data[indexes_r[0], ...]
- return data, data_p
+ return sample_l, sample_r
diff --git a/bob/learn/tensorflow/datashuffler/SiameseDisk.py b/bob/learn/tensorflow/datashuffler/SiameseDisk.py
index 95b351d2..f04dba9f 100644
--- a/bob/learn/tensorflow/datashuffler/SiameseDisk.py
+++ b/bob/learn/tensorflow/datashuffler/SiameseDisk.py
@@ -63,22 +63,20 @@ class SiameseDisk(Siamese, Disk):
**Return**
"""
- data = numpy.zeros(shape=self.shape, dtype='float32')
- data_p = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_l = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_r = numpy.zeros(shape=self.shape, dtype='float32')
labels_siamese = numpy.zeros(shape=self.shape[0], dtype='float32')
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)
- data[i, ...] = self.load_from_file(str(file_name))
- data_p[i, ...] = self.load_from_file(str(file_name_p))
+ sample_l[i, ...] = self.load_from_file(str(file_name))
+ sample_r[i, ...] = 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)
- if self.scale:
- data *= self.scale_value
- data_p *= self.scale_value
-
- return data, data_p, labels_siamese
+ return sample_l, sample_r, labels_siamese
diff --git a/bob/learn/tensorflow/datashuffler/SiameseMemory.py b/bob/learn/tensorflow/datashuffler/SiameseMemory.py
index e5c99aa3..3fe85b74 100644
--- a/bob/learn/tensorflow/datashuffler/SiameseMemory.py
+++ b/bob/learn/tensorflow/datashuffler/SiameseMemory.py
@@ -55,13 +55,13 @@ class SiameseMemory(Siamese, Memory):
**Return**
"""
- data = numpy.zeros(shape=self.shape, dtype='float')
- data_p = numpy.zeros(shape=self.shape, dtype='float')
+ sample_l = numpy.zeros(shape=self.shape, dtype='float')
+ sample_r = numpy.zeros(shape=self.shape, dtype='float')
labels_siamese = numpy.zeros(shape=self.shape[0], dtype='float')
genuine = True
for i in range(self.shape[0]):
- data[i, ...], data_p[i, ...] = self.get_genuine_or_not(self.data, self.labels, genuine=genuine)
+ sample_l[i, ...], sample_r[i, ...] = self.get_genuine_or_not(self.data, self.labels, genuine=genuine)
if zero_one_labels:
labels_siamese[i] = not genuine
else:
@@ -70,16 +70,14 @@ class SiameseMemory(Siamese, Memory):
# Applying the data augmentation
if self.data_augmentation is not None:
- for i in range(data.shape[0]):
- d = self.bob2skimage(self.data_augmentation(self.skimage2bob(data[i, ...])))
- data[i, ...] = d
+ for i in range(sample_l.shape[0]):
+ d = self.bob2skimage(self.data_augmentation(self.skimage2bob(sample_l[i, ...])))
+ sample_l[i, ...] = d
- d = self.bob2skimage(self.data_augmentation(self.skimage2bob(data_p[i, ...])))
- data_p[i, ...] = d
+ d = self.bob2skimage(self.data_augmentation(self.skimage2bob(sample_r[i, ...])))
+ sample_r[i, ...] = d
- # Scaling
- if self.scale:
- data *= self.scale_value
- data_p *= self.scale_value
+ sample_l = self.normalize_sample(sample_l)
+ sample_r = self.normalize_sample(sample_r)
- return [data.astype("float32"), data_p.astype("float32"), labels_siamese]
+ return [sample_l.astype("float32"), sample_r.astype("float32"), labels_siamese]
diff --git a/bob/learn/tensorflow/datashuffler/TripletDisk.py b/bob/learn/tensorflow/datashuffler/TripletDisk.py
index 51f5d292..fb8610fc 100644
--- a/bob/learn/tensorflow/datashuffler/TripletDisk.py
+++ b/bob/learn/tensorflow/datashuffler/TripletDisk.py
@@ -67,19 +67,18 @@ class TripletDisk(Triplet, Disk):
**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')
+ sample_a = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_p = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_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))
- data_p[i, ...] = self.load_from_file(str(file_name_p))
- data_n[i, ...] = self.load_from_file(str(file_name_n))
+ 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))
- if self.scale:
- data_a *= self.scale_value
- data_p *= self.scale_value
- data_n *= self.scale_value
+ sample_a = self.normalize_sample(sample_a)
+ sample_p = self.normalize_sample(sample_p)
+ sample_n = self.normalize_sample(sample_n)
- return [data_a, data_p, data_n]
+ return [sample_a, sample_p, sample_n]
diff --git a/bob/learn/tensorflow/datashuffler/TripletMemory.py b/bob/learn/tensorflow/datashuffler/TripletMemory.py
index 3bc04299..aef02ee9 100644
--- a/bob/learn/tensorflow/datashuffler/TripletMemory.py
+++ b/bob/learn/tensorflow/datashuffler/TripletMemory.py
@@ -56,29 +56,28 @@ class TripletMemory(Triplet, Memory):
**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')
+ sample_a = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_p = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_n = numpy.zeros(shape=self.shape, dtype='float32')
for i in range(self.shape[0]):
- data_a[i, ...], data_p[i, ...], data_n[i, ...] = self.get_one_triplet(self.data, self.labels)
+ sample_a[i, ...], sample_p[i, ...], sample_n[i, ...] = self.get_one_triplet(self.data, self.labels)
# Applying the data augmentation
if self.data_augmentation is not None:
- for i in range(data_a.shape[0]):
- d = self.bob2skimage(self.data_augmentation(self.skimage2bob(data_a[i, ...])))
- data_a[i, ...] = d
+ for i in range(sample_a.shape[0]):
+ d = self.bob2skimage(self.data_augmentation(self.skimage2bob(sample_a[i, ...])))
+ sample_a[i, ...] = d
- d = self.bob2skimage(self.data_augmentation(self.skimage2bob(data_p[i, ...])))
- data_p[i, ...] = d
+ d = self.bob2skimage(self.data_augmentation(self.skimage2bob(sample_p[i, ...])))
+ sample_p[i, ...] = d
- d = self.bob2skimage(self.data_augmentation(self.skimage2bob(data_n[i, ...])))
- data_n[i, ...] = d
+ d = self.bob2skimage(self.data_augmentation(self.skimage2bob(sample_n[i, ...])))
+ sample_n[i, ...] = d
# Scaling
- if self.scale:
- data_a *= self.scale_value
- data_p *= self.scale_value
- data_n *= self.scale_value
+ sample_a = self.normalize_sample(sample_a)
+ sample_p = self.normalize_sample(sample_p)
+ sample_n = self.normalize_sample(sample_n)
- return [data_a.astype("float32"), data_p.astype("float32"), data_n.astype("float32")]
+ return [sample_a.astype("float32"), sample_p.astype("float32"), sample_n.astype("float32")]
diff --git a/bob/learn/tensorflow/datashuffler/TripletWithFastSelectionDisk.py b/bob/learn/tensorflow/datashuffler/TripletWithFastSelectionDisk.py
index 9f9eb707..98fb44c4 100644
--- a/bob/learn/tensorflow/datashuffler/TripletWithFastSelectionDisk.py
+++ b/bob/learn/tensorflow/datashuffler/TripletWithFastSelectionDisk.py
@@ -92,10 +92,9 @@ class TripletWithFastSelectionDisk(Triplet, Disk, OnLineSampling):
sample_p[i, ...] = self.load_from_file(str(file_name_p))
sample_n[i, ...] = self.load_from_file(str(file_name_n))
- if self.scale:
- sample_a *= self.scale_value
- sample_p *= self.scale_value
- sample_n *= self.scale_value
+ sample_a = self.normalize_sample(sample_a)
+ sample_p = self.normalize_sample(sample_p)
+ sample_n = self.normalize_sample(sample_n)
return [sample_a, sample_p, sample_n]
@@ -133,13 +132,6 @@ class TripletWithFastSelectionDisk(Triplet, Disk, OnLineSampling):
samples_p, embedding_p, d_anchor_positive = self.get_positives(anchor_labels, embedding_a)
samples_n = self.get_negative(anchor_labels, embedding_a, d_anchor_positive)
- #import bob.io.base
- #import bob.io.image
- #for i in range(self.shape[0]):
- #bob.io.base.save((self.skimage2bob(samples_a[i, ...]) / 0.00390625).astype("uint8"), "{0}_a.jpg".format(i))
- #bob.io.base.save((self.skimage2bob(samples_p[i, ...]) / 0.00390625).astype("uint8"), "{0}_p.jpg".format(i))
- #bob.io.base.save((self.skimage2bob(samples_n[i, ...]) / 0.00390625).astype("uint8"), "{0}_n.jpg".format(i))
-
return samples_a, samples_p, samples_n
def get_anchor(self, label):
@@ -154,8 +146,7 @@ class TripletWithFastSelectionDisk(Triplet, Disk, OnLineSampling):
file_name = self.data[indexes[0], ...]
anchor = self.load_from_file(str(file_name))
- if self.scale:
- anchor *= self.scale_value
+ anchor = self.normalize_sample(anchor)
return anchor
@@ -171,9 +162,7 @@ class TripletWithFastSelectionDisk(Triplet, Disk, OnLineSampling):
file_name = self.data[indexes[0], ...]
samples_p[i, ...] = self.load_from_file(str(file_name))
- if self.scale:
- samples_p *= self.scale_value
-
+ samples_p = self.normalize_sample(samples_p)
embedding_p = self.project(samples_p)
# Computing the distances
@@ -204,9 +193,7 @@ class TripletWithFastSelectionDisk(Triplet, Disk, OnLineSampling):
for i in range(shape[0]):
file_name = self.data[indexes[i], ...]
temp_samples_n[i, ...] = self.load_from_file(str(file_name))
-
- if self.scale:
- temp_samples_n *= self.scale_value
+ temp_samples_n = self.normalize_sample(temp_samples_n)
# Computing all the embeddings
embedding_temp_n = self.project(temp_samples_n)
diff --git a/bob/learn/tensorflow/datashuffler/TripletWithSelectionDisk.py b/bob/learn/tensorflow/datashuffler/TripletWithSelectionDisk.py
index 0b1fffff..2faa181c 100644
--- a/bob/learn/tensorflow/datashuffler/TripletWithSelectionDisk.py
+++ b/bob/learn/tensorflow/datashuffler/TripletWithSelectionDisk.py
@@ -80,22 +80,21 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
**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')
+ sample_a = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_p = numpy.zeros(shape=self.shape, dtype='float32')
+ sample_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))
- data_p[i, ...] = self.load_from_file(str(file_name_p))
- data_n[i, ...] = self.load_from_file(str(file_name_n))
+ 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))
- if self.scale:
- data_a *= self.scale_value
- data_p *= self.scale_value
- data_n *= self.scale_value
+ sample_a = self.normalize_sample(sample_a)
+ sample_p = self.normalize_sample(sample_p)
+ sample_n = self.normalize_sample(sample_n)
- return [data_a, data_p, data_n]
+ return [sample_a, sample_p, sample_n]
def get_batch(self):
"""
@@ -120,9 +119,6 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
anchor_labels = numpy.hstack((anchor_labels,numpy.ones(samples_per_identity) * self.possible_labels[indexes[i]]))
anchor_labels = anchor_labels[0:self.batch_size]
-
-
-
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')
@@ -167,14 +163,12 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
numpy.random.shuffle(indexes)
file_name = self.data[indexes[0], ...]
- anchor = self.load_from_file(str(file_name))
-
- if self.scale:
- anchor *= self.scale_value
+ sample_a = self.load_from_file(str(file_name))
- return anchor
+ sample_a = self.normalize_sample(sample_a)
+ return sample_a
- def get_positive(self, label, anchor_feature):
+ def get_positive(self, label, embedding_a):
"""
Get the best positive sample given the anchor.
The best positive sample for the anchor is the farthest from the anchor
@@ -188,31 +182,30 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
0:self.batch_size] # Limiting to the batch size, otherwise the number of comparisons will explode
distances = []
shape = tuple([len(indexes)] + list(self.shape[1:]))
- data_p = numpy.zeros(shape=shape, dtype='float32')
+ sample_p = numpy.zeros(shape=shape, dtype='float32')
#logger.info("****************** search")
for i in range(shape[0]):
#logger.info("****************** fetch")
file_name = self.data[indexes[i], ...]
#logger.info("****************** load")
- data_p[i, ...] = self.load_from_file(str(file_name))
+ sample_p[i, ...] = self.load_from_file(str(file_name))
- if self.scale:
- data_p *= self.scale_value
+ sample_p = self.normalize_sample(sample_p)
#logger.info("****************** project")
- positive_features = self.project(data_p)
+ embedding_p = self.project(sample_p)
#logger.info("****************** distances")
# Projecting the positive instances
- for p in positive_features:
- distances.append(euclidean(anchor_feature, p))
+ for p in embedding_p:
+ distances.append(euclidean(embedding_a, p))
# Geting the max
index = numpy.argmax(distances)
#logger.info("****************** return")
- return data_p[index, ...], distances[index]
+ return sample_p[index, ...], distances[index]
- def get_negative(self, label, anchor_feature, distance_anchor_positive):
+ def get_negative(self, label, embedding_a, distance_anchor_positive):
"""
Get the best negative sample for a pair anchor-positive
"""
@@ -227,24 +220,23 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
0:self.batch_size*3] # Limiting to the batch size, otherwise the number of comparisons will explode
shape = tuple([len(indexes)] + list(self.shape[1:]))
- data_n = numpy.zeros(shape=shape, dtype='float32')
+ sample_n = numpy.zeros(shape=shape, dtype='float32')
#logger.info("****************** search")
for i in range(shape[0]):
#logger.info("****************** fetch")
file_name = self.data[indexes[i], ...]
#logger.info("****************** load")
- data_n[i, ...] = self.load_from_file(str(file_name))
+ sample_n[i, ...] = self.load_from_file(str(file_name))
- if self.scale:
- data_n *= self.scale_value
+ sample_n = self.normalize_sample(sample_n)
#logger.info("****************** project")
- negative_features = self.project(data_n)
+ embedding_n = self.project(sample_n)
distances = []
#logger.info("****************** distances")
- for n in negative_features:
- d = euclidean(anchor_feature, n)
+ for n in embedding_n:
+ d = euclidean(embedding_a, n)
# Semi-hard samples criteria
if d > distance_anchor_positive:
@@ -260,4 +252,4 @@ class TripletWithSelectionDisk(Triplet, Disk, OnLineSampling):
logger.info("SEMI-HARD negative not found, took the first one")
index = 0
#logger.info("****************** return")
- return data_n[index, ...]
+ return sample_n[index, ...]
diff --git a/bob/learn/tensorflow/loss/TripletLoss.py b/bob/learn/tensorflow/loss/TripletLoss.py
index cacc1e31..66118a4c 100644
--- a/bob/learn/tensorflow/loss/TripletLoss.py
+++ b/bob/learn/tensorflow/loss/TripletLoss.py
@@ -33,12 +33,18 @@ class TripletLoss(BaseLoss):
def __init__(self, margin=5.0):
self.margin = margin
- def __call__(self, anchor_feature, positive_feature, negative_feature):
+ def __call__(self, anchor_embedding, positive_embedding, negative_embedding):
with tf.name_scope("triplet_loss"):
+ # Normalize
+ anchor_embedding = tf.nn.l2_normalize(anchor_embedding, 1, 1e-10)
+ positive_embedding = tf.nn.l2_normalize(positive_embedding, 1, 1e-10)
+ negative_embedding = tf.nn.l2_normalize(negative_embedding, 1, 1e-10)
- d_positive = tf.square(compute_euclidean_distance(anchor_feature, positive_feature))
- d_negative = tf.square(compute_euclidean_distance(anchor_feature, negative_feature))
+ d_positive = tf.reduce_sum(tf.square(tf.sub(anchor_embedding, positive_embedding)), 1)
+ d_negative = tf.reduce_sum(tf.square(tf.sub(anchor_embedding, negative_embedding)), 1)
- loss = tf.maximum(0., d_positive - d_negative + self.margin)
- return tf.reduce_mean(loss), tf.reduce_mean(d_negative), tf.reduce_mean(d_positive)
+ basic_loss = tf.add(tf.sub(d_positive, d_negative), self.margin)
+ loss = tf.reduce_mean(tf.maximum(basic_loss, 0.0), 0)
+
+ return loss, tf.reduce_mean(d_negative), tf.reduce_mean(d_positive)
diff --git a/bob/learn/tensorflow/script/train_mobio.py b/bob/learn/tensorflow/script/train_mobio.py
index c6bca5e4..6c456161 100644
--- a/bob/learn/tensorflow/script/train_mobio.py
+++ b/bob/learn/tensorflow/script/train_mobio.py
@@ -45,7 +45,7 @@ def main():
# Preparing train set
#train_objects = db_mobio.objects(protocol="male", groups="world")
- 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))
@@ -54,16 +54,17 @@ def main():
extension=".hdf5")
for o in train_objects]
#train_data_shuffler = TripletWithSelectionDisk(train_file_names, train_labels,
- # input_shape=[125, 125, 3],
+ # 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],
+ input_shape=[112, 112, 3],
batch_size=BATCH_SIZE,
total_identities=8)
# Preparing train set
- validation_objects = db_mobio.objects(protocol="male", groups="dev")
+ 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]
@@ -72,13 +73,13 @@ def main():
extension=".hdf5")
for o in validation_objects]
validation_data_shuffler = TripletDisk(validation_file_names, validation_labels,
- input_shape=[224, 224, 3],
+ input_shape=[112, 112, 3],
batch_size=VALIDATION_BATCH_SIZE)
# Preparing the architecture
+ architecture = Chopra(seed=SEED, fc1_output=n_classes)
#architecture = Chopra(seed=SEED, fc1_output=n_classes)
- #architecture = Chopra(seed=SEED, fc1_output=n_classes)
- architecture = FaceNet(seed=SEED, use_gpu=USE_GPU)
- optimizer = tf.train.GradientDescentOptimizer(0.00000001)
+ #architecture = FaceNet(seed=SEED, use_gpu=USE_GPU)
+ #optimizer = tf.train.GradientDescentOptimizer(0.0005)
#loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
@@ -95,13 +96,14 @@ def main():
# optimizer=optimizer,
# temp_dir="./LOGS_MOBIO/siamese-cnn-prefetch")
- loss = TripletLoss(margin=1.)
+ loss = TripletLoss(margin=0.5)
+ #optimizer = tf.train.GradientDescentOptimizer(0.000000000001)
#optimizer = optimizer,
-
trainer = TripletTrainer(architecture=architecture, loss=loss,
iterations=ITERATIONS,
+ base_learning_rate=0.0001,
prefetch=False,
temp_dir="./LOGS_MOBIO/triplet-cnn")
- trainer.train(train_data_shuffler, validation_data_shuffler)
- #trainer.train(train_data_shuffler)
+ #trainer.train(train_data_shuffler, validation_data_shuffler)
+ trainer.train(train_data_shuffler)
diff --git a/bob/learn/tensorflow/script/train_siamese_casia_webface.py b/bob/learn/tensorflow/script/train_siamese_casia_webface.py
index 5d1f6e9c..f433dcc4 100644
--- a/bob/learn/tensorflow/script/train_siamese_casia_webface.py
+++ b/bob/learn/tensorflow/script/train_siamese_casia_webface.py
@@ -46,7 +46,7 @@ def main():
db_casia = bob.db.casia_webface.Database()
# Preparing train set
- train_objects = db_casia.objects(groups="world")
+ 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"
@@ -67,7 +67,7 @@ def main():
# Preparing train set
directory = "/idiap/temp/tpereira/DEEP_FACE/CASIA_WEBFACE/mobio/preprocessed"
- validation_objects = db_mobio.objects(protocol="male", groups="dev")
+ 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(
diff --git a/bob/learn/tensorflow/trainers/Trainer.py b/bob/learn/tensorflow/trainers/Trainer.py
index c3959e10..affd9188 100644
--- a/bob/learn/tensorflow/trainers/Trainer.py
+++ b/bob/learn/tensorflow/trainers/Trainer.py
@@ -14,7 +14,8 @@ from tensorflow.core.framework import summary_pb2
import time
from bob.learn.tensorflow.datashuffler.OnlineSampling import OnLineSampling
-os.environ["CUDA_VISIBLE_DEVICES"] = "1,2,3,0"
+#os.environ["CUDA_VISIBLE_DEVICES"] = "1,2,3,0"
+os.environ["CUDA_VISIBLE_DEVICES"] = ""
logger = bob.core.log.setup("bob.learn.tensorflow")
diff --git a/bob/learn/tensorflow/trainers/TripletTrainer.py b/bob/learn/tensorflow/trainers/TripletTrainer.py
index 24da94ab..5ae2e8f0 100644
--- a/bob/learn/tensorflow/trainers/TripletTrainer.py
+++ b/bob/learn/tensorflow/trainers/TripletTrainer.py
@@ -187,7 +187,7 @@ class TripletTrainer(Trainer):
self.training_graph, self.between_class_graph_train,
self.within_class_graph_train,
self.learning_rate, self.summaries_train],
- feed_dict=feed_dict)
+ feed_dict=feed_dict)
logger.info("Loss training set step={0} = {1}".format(step, l))
self.train_summary_writter.add_summary(summary, step)
diff --git a/buildout.cfg b/buildout.cfg
index 95369876..678aa74b 100644
--- a/buildout.cfg
+++ b/buildout.cfg
@@ -6,6 +6,7 @@
parts = scripts
eggs = bob.learn.tensorflow
bob.db.casia_webface
+ bob.db.mobio
gridtk
extensions = bob.buildout
@@ -30,7 +31,7 @@ bob.db.base = git git@gitlab.idiap.ch:bob/bob.db.base.git
bob.db.mobio = git git@gitlab.idiap.ch:bob/bob.db.mobio.git
bob.db.lfw = git git@gitlab.idiap.ch:bob/bob.db.lfw.git
bob.db.casia_webface = git git@gitlab.idiap.ch:bob/bob.db.casia_webface.git
-gridtk = git git@github.com:bioidiap/gridtk
+gridtk = git git@gitlab.idiap.ch:bob/gridtk
[scripts]
--
GitLab