Skip to content
GitLab
Commit 13e2bcaf authored by Tiago Pereira's avatar Tiago Pereira
Browse files

[sphinx] Fixing issues

parent 95e084d6
Pipeline #10738 failed with stages
in 5 minutes and 22 seconds
Hide whitespace changes
Inline Side-by-side
bob/learn/tensorflow/datashuffler/OnlineSampling.py
View file @ 13e2bcaf
......@@ -5,8 +5,6 @@
import tensorflow as tf
from .Base import Base
from bob.learn.tensorflow.network import SequenceNetwork
class OnlineSampling(object):
"""
......@@ -32,8 +30,8 @@ class OnlineSampling(object):
"""
Set the current feature extraction used in the sampling
"""
if not isinstance(feature_extractor, SequenceNetwork):
raise ValueError("Feature extractor must be a `bob.learn.tensoflow.network.SequenceNetwork` object")
#if not isinstance(feature_extractor, SequenceNetwork):
# raise ValueError("Feature extractor must be a `bob.learn.tensoflow.network.SequenceNetwork` object")
self.feature_extractor = feature_extractor
self.session = session
......
bob/learn/tensorflow/network/SequenceNetwork.py deleted 100644 → 0
View file @ 95e084d6
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# @author: Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
# @date: Thu 11 Aug 2016 09:39:36 CEST
import tensorflow as tf
import abc
import six
import numpy
import pickle
from bob.learn.tensorflow.layers import Layer, MaxPooling, Dropout, Conv2D, FullyConnected
from bob.learn.tensorflow.utils.session import Session
class SequenceNetwork(six.with_metaclass(abc.ABCMeta, object)):
"""
Sequential model is a linear stack of :py:mod:`bob.learn.tensorflow.layers`.
**Parameters**
default_feature_layer: Default layer name (:py:obj:`str`) used as a feature layer.
use_gpu: If ``True`` uses the GPU in the computation.
"""
def __init__(self,
graph=None,
default_feature_layer=None,
use_gpu=False):
self.base_graph = graph
self.default_feature_layer = default_feature_layer
self.use_gpu = use_gpu
def __del__(self):
tf.reset_default_graph()
def __call__(self, data, feature_layer=None):
"""Run a graph and compute the embeddings
**Parameters**
data: tensorflow placeholder as input data
session: tensorflow `session <https://www.tensorflow.org/versions/r0.11/api_docs/python/client.html#Session>`_
feature_layer: Name of the :py:class:`bob.learn.tensorflow.layer.Layer` that you want to "cut".
If `None` will run the graph until the end.
"""
session = Session.instance().session
# Feeding the placeholder
if self.inference_placeholder is None:
self.compute_inference_placeholder(data.shape[1:])
feed_dict = {self.inference_placeholder: data}
if self.inference_graph is None:
self.compute_inference_graph(self.inference_placeholder, feature_layer)
embedding = session.run([self.inference_graph], feed_dict=feed_dict)[0]
return embedding
def predict(self, data):
return numpy.argmax(self(data), 1)
"""
def variable_summaries(self, var, name):
#Attach a lot of summaries to a Tensor.
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean/' + name, mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))
tf.summary.scalar('sttdev/' + name, stddev)
tf.summary.scalar('max/' + name, tf.reduce_max(var))
tf.summary.scalar('min/' + name, tf.reduce_min(var))
tf.summary.histogram(name, var)
"""
def compute_magic_number(self, hypothetic_image_dimensions=(28, 28, 1)):
"""
Here it is done an estimative of the capacity of DNN.
**Parameters**
hypothetic_image_dimensions: Possible image dimentions `w, h, c` (width x height x channels)
"""
stride = 1# ALWAYS EQUALS TO ONE
current_image_dimensions = list(hypothetic_image_dimensions)
samples_per_sample = 0
flatten_dimension = numpy.prod(current_image_dimensions)
for k in self.sequence_net.keys():
current_layer = self.sequence_net[k]
if isinstance(current_layer, Conv2D):
#samples_per_sample += current_layer.filters * current_layer.kernel_size * current_image_dimensions[0] + current_layer.filters
#samples_per_sample += current_layer.filters * current_layer.kernel_size * current_image_dimensions[1] + current_layer.filters
samples_per_sample += current_layer.filters * current_image_dimensions[0] * current_image_dimensions[1] + current_layer.filters
current_image_dimensions[2] = current_layer.filters
flatten_dimension = numpy.prod(current_image_dimensions)
if isinstance(current_layer, MaxPooling):
current_image_dimensions[0] /= 2
current_image_dimensions[1] /= 2
flatten_dimension = current_image_dimensions[0] * current_image_dimensions[1] * current_image_dimensions[2]
if isinstance(current_layer, FullyConnected):
samples_per_sample += flatten_dimension * current_layer.output_dim + current_layer.output_dim
flatten_dimension = current_layer.output_dim
return samples_per_sample
def save(self, saver, path):
session = Session.instance().session
open(path+"_sequence_net.pickle", 'wb').write(self.pickle_architecture)
return saver.save(session, path)
def load(self, path, clear_devices=False, session_from_scratch=False):
session = Session.instance(new=session_from_scratch).session
self.sequence_net = pickle.loads(open(path+"_sequence_net.pickle", 'rb').read())
if clear_devices:
saver = tf.train.import_meta_graph(path + ".meta", clear_devices=clear_devices)
else:
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]
return saver
bob/learn/tensorflow/network/__init__.py
View file @ 13e2bcaf
from .SequenceNetwork import SequenceNetwork
from .Chopra import Chopra
from .Dummy import Dummy
from .MLP import MLP
from .Embedding import Embedding
#from .Input import Input
# gets sphinx autodoc done right - don't remove it
def __appropriate__(*args):
......@@ -20,7 +18,6 @@ def __appropriate__(*args):
for obj in args: obj.__module__ = __name__
__appropriate__(
SequenceNetwork,
Chopra,
Dummy,
MLP,
......
bob/learn/tensorflow/test/test_cnn_load.py deleted 100644 → 0
View file @ 95e084d6
#!/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
import tensorflow as tf
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():
tf.reset_default_graph()
_, _, 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'), session_from_scratch=True)
accuracy = validate_network(validation_data, validation_labels, network)
assert accuracy > 80
del network
bob/learn/tensorflow/test/test_cnn_scratch.py
View file @ 13e2bcaf
......@@ -25,21 +25,20 @@ directory = "./temp/cnn_scratch"
slim = tf.contrib.slim
def scratch_network():
# Creating a random network
inputs = dict()
inputs['data'] = tf.placeholder(tf.float32, shape=[None, 28, 28, 1], name="train_data")
inputs['label'] = tf.placeholder(tf.int64, shape=[None], name="train_label")
def scratch_network(train_data_shuffler):
inputs = train_data_shuffler("data", from_queue=False)
# Creating a random network
initializer = tf.contrib.layers.xavier_initializer(seed=seed)
graph = slim.conv2d(inputs['data'], 10, [3, 3], activation_fn=tf.nn.relu, stride=1, scope='conv1',
graph = slim.conv2d(inputs, 10, [3, 3], activation_fn=tf.nn.relu, stride=1, scope='conv1',
weights_initializer=initializer)
graph = slim.max_pool2d(graph, [4, 4], scope='pool1')
graph = slim.flatten(graph, scope='flatten1')
graph = slim.fully_connected(graph, 10, activation_fn=None, scope='fc1',
weights_initializer=initializer)
return inputs, graph
return graph
def validate_network(embedding, validation_data, validation_labels):
......@@ -69,20 +68,12 @@ def test_cnn_trainer_scratch():
data_augmentation=data_augmentation,
normalizer=ScaleFactor())
#validation_data_shuffler = Memory(train_data, train_labels,
# input_shape=[28, 28, 1],
# batch_size=batch_size,
# data_augmentation=data_augmentation,
# normalizer=ScaleFactor())
validation_data = numpy.reshape(validation_data, (validation_data.shape[0], 28, 28, 1))
# Create scratch network
inputs, scratch = scratch_network()
graph = scratch_network(train_data_shuffler)
# Setting the placeholders
train_data_shuffler.data_ph = inputs['data']
train_data_shuffler.label_ph = inputs['label']
embedding = Embedding(inputs['data'], scratch)
embedding = Embedding(train_data_shuffler("data", from_queue=False), graph)
# Loss for the softmax
loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
......@@ -93,7 +84,7 @@ def test_cnn_trainer_scratch():
analizer=None,
temp_dir=directory)
trainer.create_network_from_scratch(graph=scratch,
trainer.create_network_from_scratch(graph=graph,
loss=loss,
learning_rate=constant(0.01, name="regular_lr"),
optimizer=tf.train.GradientDescentOptimizer(0.01),
......
bob/learn/tensorflow/trainers/SiameseTrainer.py
View file @ 13e2bcaf
......@@ -21,43 +21,25 @@ class SiameseTrainer(Trainer):
**Parameters**
architecture:
The architecture that you want to run. Should be a :py:class`bob.learn.tensorflow.network.SequenceNetwork`
train_data_shuffler:
The data shuffler used for batching data for training
optimizer:
One of the tensorflow optimizers https://www.tensorflow.org/versions/r0.10/api_docs/python/train.html
use_gpu: bool
Use GPUs in the training
loss: :py:class:`bob.learn.tensorflow.loss.BaseLoss`
Loss function
temp_dir: str
The output directory
learning_rate: `bob.learn.tensorflow.trainers.learning_rate`
Initial learning rate
convergence_threshold:
iterations: int
iterations:
Maximum number of iterations
snapshot: int
snapshot:
Will take a snapshot of the network at every `n` iterations
prefetch: bool
Use extra Threads to deal with the I/O
model_from_file: str
If you want to use a pretrained model
validation_snapshot:
Test with validation each `n` iterations
analizer:
Neural network analizer :py:mod:`bob.learn.tensorflow.analyzers`
verbosity_level:
temp_dir: str
The output directory
verbosity_level:
"""
......
bob/learn/tensorflow/trainers/Trainer.py
View file @ 13e2bcaf
......@@ -4,7 +4,6 @@
# @date: Tue 09 Aug 2016 15:25:22 CEST
import tensorflow as tf
from ..network import SequenceNetwork
import threading
import os
import bob.io.base
......@@ -29,41 +28,24 @@ class Trainer(object):
**Parameters**
architecture:
The architecture that you want to run. Should be a :py:class`bob.learn.tensorflow.network.SequenceNetwork`
train_data_shuffler:
The data shuffler used for batching data for training
optimizer:
One of the tensorflow optimizers https://www.tensorflow.org/versions/r0.10/api_docs/python/train.html
use_gpu: bool
Use GPUs in the training
loss: :py:class:`bob.learn.tensorflow.loss.BaseLoss`
Loss function
temp_dir: str
The output directory
learning_rate: `bob.learn.tensorflow.trainers.learning_rate`
Initial learning rate
convergence_threshold:
iterations: int
iterations:
Maximum number of iterations
snapshot: int
snapshot:
Will take a snapshot of the network at every `n` iterations
prefetch: bool
Use extra Threads to deal with the I/O
model_from_file: str
If you want to use a pretrained model
validation_snapshot:
Test with validation each `n` iterations
analizer:
Neural network analizer :py:mod:`bob.learn.tensorflow.analyzers`
temp_dir: str
The output directory
verbosity_level:
"""
......
bob/learn/tensorflow/trainers/TripletTrainer.py
View file @ 13e2bcaf
......@@ -7,7 +7,6 @@ import tensorflow as tf
from tensorflow.core.framework import summary_pb2
import threading
from ..analyzers import ExperimentAnalizer
from ..network import SequenceNetwork
from .Trainer import Trainer
from ..analyzers import SoftmaxAnalizer
import os
......@@ -23,45 +22,29 @@ class TripletTrainer(Trainer):
**Parameters**
architecture:
The architecture that you want to run. Should be a :py:class`bob.learn.tensorflow.network.SequenceNetwork`
train_data_shuffler:
The data shuffler used for batching data for training
optimizer:
One of the tensorflow optimizers https://www.tensorflow.org/versions/r0.10/api_docs/python/train.html
use_gpu: bool
Use GPUs in the training
loss: :py:class:`bob.learn.tensorflow.loss.BaseLoss`
Loss function
temp_dir: str
The output directory
learning_rate: `bob.learn.tensorflow.trainers.learning_rate`
Initial learning rate
convergence_threshold:
iterations: int
iterations:
Maximum number of iterations
snapshot: int
snapshot:
Will take a snapshot of the network at every `n` iterations
prefetch: bool
Use extra Threads to deal with the I/O
model_from_file: str
If you want to use a pretrained model
validation_snapshot:
Test with validation each `n` iterations
analizer:
Neural network analizer :py:mod:`bob.learn.tensorflow.analyzers`
temp_dir: str
The output directory
verbosity_level:
"""
def __init__(self,
train_data_shuffler,
......
doc/nitpick-exceptions.txt
View file @ 13e2bcaf
py:class bob.learn.tensorflow.datashuffler.OnlineSampling
py:class bob.learn.tensorflow.datashuffler.OnlineSampling.OnlineSampling
\ No newline at end of file
py:class list
\ No newline at end of file
doc/py_api.rst
View file @ 13e2bcaf
......@@ -14,14 +14,9 @@ Architectures
.. autosummary::
bob.learn.tensorflow.network.SequenceNetwork
bob.learn.tensorflow.network.Chopra
bob.learn.tensorflow.network.Dummy
bob.learn.tensorflow.network.Lenet
bob.learn.tensorflow.network.LenetDropout
bob.learn.tensorflow.network.MLP
bob.learn.tensorflow.network.VGG16
bob.learn.tensorflow.network.VGG16_mod
Trainers
......
doc/user_guide.rst
View file @ 13e2bcaf
......@@ -18,27 +18,48 @@ The example consists in training a very simple **CNN** with `MNIST` dataset in 4
.. code-block:: python
>>> import tensorflow as tf
>>> import bob.learn.tensorflow
>>> from bob.learn.tensorflow.loss import BaseLoss
>>> from bob.learn.tensorflow.trainers import Trainer, constant
>>> from bob.learn.tensorflow.utils import load_mnist
>>> from bob.learn.tensorflow.datashuffler import Memory
>>> from bob.learn.tensorflow.network import Embedding
>>> import numpy
>>> # Loading raw data
>>> train_data, train_labels, _, _ = bob.learn.tensorflow.util.load_mnist()
>>> train_data = numpy.reshape(train_data, (train_data.shape[0], 28, 28, 1))
>>> train_data_shuffler = bob.learn.tensorflow.datashuffler.Memory(train_data, train_labels, input_shape=[28, 28, 1], batch_size=16)
>>> # Preparing the datashuffler (our batching engine)
>>> train_data_shuffler = Memory(train_data, train_labels, input_shape=[None, 28, 28, 1], batch_size=16)
>>>
2. Create an architecture
.. code-block:: python
>>> architecture = bob.learn.tensorflow.network.SequenceNetwork()
>>> architecture.add(bob.learn.tensorflow.layers.Conv2D(name="conv1", kernel_size=3, filters=10, activation=tf.nn.tanh))
>>> architecture.add(bob.learn.tensorflow.layers.FullyConnected(name="fc1", output_dim=10, activation=None))
>>> # Create a function or a class with the graph definition in the `__call__` method
>>> def create_dummy_architecture(placeholder):
>>> initializer = tf.contrib.layers.xavier_initializer(seed=10) # Weights initializer
>>> slim = tf.contrib.slim
>>> graph = slim.conv2d(placeholder, 10, [3, 3], activation_fn=tf.nn.relu, stride=1, scope='conv1', weights_initializer=initializer)
>>> graph = slim.flatten(graph, scope='flatten1')
>>> graph = slim.fully_connected(graph, 10, activation_fn=None, scope='fc1', weights_initializer=initializer)
>>> return graph
>>>
3. Defining a loss and training algorithm
.. code-block:: python
>>> loss = bob.learn.tensorflow.loss.BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
>>> from bob.learn.tensorflow.trainers import Trainer
>>> architecture = create_dummy_architecture
>>>
>>> loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
>>>
>>> optimizer = tf.train.GradientDescentOptimizer(0.001)
>>>
>>> learning_rate = constant(base_learning_rate=0.001)
>>>
>>> trainer = Trainer
Now that you have defined your data, architecture, loss and training algorithm you can save this in a python file,
......@@ -46,7 +67,7 @@ let's say `softmax.py`, and run:
.. code-block:: shell
>>> ./bin/train.py softmax.py
>>> ./bin/train.py softmax.py --iterations 100 --output-dir ./my_first_net
4. Predicting and computing the accuracy
......@@ -55,15 +76,17 @@ Run the following code to evalutate the network that was just trained.
.. code-block:: python
>>> # 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
>>> # Loading the trained model
>>> trainer = Trainer(train_data_shuffler)
>>> directory = "./my_first_net/"
>>> trainer.create_network_from_file(os.path.join(directory, "model.ckp"))
>>> # Prediction
>>> embedding = Embedding(trainer.data_ph, trainer.graph)
>>> [data, labels] = train_data_shuffler.get_batch()
>>> predictions = embedding(data)
>>> accuracy = 100. * numpy.sum(numpy.argmax(predictions, axis=1) == labels) / predictions.shape[0]
87.5
Understanding what you have done
......@@ -73,8 +96,7 @@ Understanding what you have done
Preparing your input data
.........................
In this library datasets are wrapped in **data shufflers**. Data shufflers are elements designed to shuffle
the input data for stochastic training.
In this library datasets are wrapped in **data shufflers**. Data shufflers are elements designed to do batching.
It has one basic functionality which is :py:meth:`bob.learn.tensorflow.datashuffler.Base.get_batch` functionality.
It is possible to either use Memory (:py:class:`bob.learn.tensorflow.datashuffler.Memory`) or
......@@ -89,9 +111,10 @@ number of channels.
Creating the architecture
.........................
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>`_.
Architectures are assembled using the Tensorflow graphs.
There are plenty of ways to doing it; you can either use the `tensorflow <https://www.tensorflow.org/api_docs/python/tf/Graph>`_ API directly
or use one of the several available contribs such as `tf-slim <https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim>`_,
`TFLearn <http://tflearn.org/>`_, etc...
Defining a loss and training
......@@ -169,28 +192,6 @@ here :py:class:`bob.learn.tensorflow.datashuffler.TripletWithSelectionDisk` and
This triplet selection relies in the current state of the network and are extensions of `bob.learn.tensorflow.datashuffler.OnlineSampling`.
Architecture
............
As described above, 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>`_.
It is also possible to craft simple MLPs with this library using the class :py:class:`bob.learn.tensorflow.network.MLP`.
The example bellow shows how to create a simple MLP with 10 putputs and 2 hidden layers.
.. code-block:: python
>>> architecture = bob.learn.tensorflow.network.MLP(10, hidden_layers=[20, 40])