first commit

Author: jcburnel

.gitignore

@@ -0,0 +1,183 @@
+# Compiled source #
+###################
+*.com
+*.class
+*.dll
+*.exe
+*.o
+*.so
+
+# Packages #
+############
+# it's better to unpack these files and commit the raw source
+# git has its own built in compression methods
+*.7z
+*.dmg
+*.gz
+*.iso
+*.jar
+*.rar
+*.tar
+*.zip
+
+# Logs and databases #
+######################
+*.log
+*.sql
+*.sqlite
+
+# OS generated files #
+######################
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Perso #
+#########
+*.mat*
+data/
+saved_models/
+checkpoints/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

AdvGAN/activations.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Jan 17 08:39:05 2019
+
+@author: vicari
+"""
+import tensorflow as tf
+import numpy as np
+
+def MaxMin():
+    def f(x):
+        shape = x.get_shape().as_list()
+        shape[0] = -1
+        group = tf.reshape(x,[-1, 2])
+        a,b = tf.split(group, 2, 1)
+        c = tf.concat((tf.minimum(a,b), tf.maximum(b,a)), axis=1)
+        res = tf.reshape(c,shape) 
+        return res
+    
+    return lambda x : f(x)
+
+def FullSort():
+    def f(x):
+        shape = x.get_shape().as_list()
+        res = -tf.nn.top_k(-x, k=shape[-1])[0]
+        return res
+    
+    return lambda x : f(x)
+
+def lrelu(l=0.2):
+    return lambda x : tf.nn.leaky_relu(x,l)
+
+def relu():
+    return lambda x : tf.nn.relu(x)

AdvGAN/classifiers.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Apr  1 09:40:23 2019
+
+@author: vicari
+"""
+
+from AdvGAN import utils, dataset, cyclegan, models, print_functions, activations, layers
+
+import tensorflow as tf
+from tensorflow.layers import Flatten
+
+from tensorflow import keras
+
+from tensorflow.python.keras.datasets import cifar10
+from tensorflow.python.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.python.keras.models import Sequential
+from tensorflow.python.keras.layers import Dense, Dropout, Activation, Flatten
+from tensorflow.python.keras.layers import Conv2D, MaxPooling2D
+
+def keras_conv_net(input_shape, num_classes=10):
+    model = Sequential()
+    model.add(Conv2D(32, (3, 3), padding='same',
+                     input_shape=input_shape))
+    model.add(Activation('relu'))
+    model.add(Conv2D(32, (3, 3)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Dropout(0.25))
+    
+    model.add(Conv2D(64, (3, 3), padding='same'))
+    model.add(Activation('relu'))
+    model.add(Conv2D(64, (3, 3)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Dropout(0.25))
+    
+    model.add(Flatten())
+    model.add(Dense(512))
+    model.add(Activation('relu'))
+    model.add(Dropout(0.5))
+    model.add(Dense(num_classes))
+    model.add(Activation('softmax'))
+    
+    # initiate RMSprop optimizer
+    opt = keras.optimizers.RMSprop(lr=0.0001, decay=1e-6)
+    
+    # Let's train the model using RMSprop
+    model.compile(loss='categorical_crossentropy',
+                  optimizer=opt,
+                  metrics=['accuracy'])
+    
+    return model
+
+def make_simple_conv_net(nb_class=10):
+    def simple_conv_net(X, scope_name='classifier_conv_net', reuse=False):
+        
+        with tf.variable_scope(scope_name, reuse) as scope:
+        
+            if reuse:
+                scope.reuse_variables()
+                
+            net = layers.conv2D(X, 3, 64, 1, name='conv0_1', batch_normed=True)
+            net = tf.nn.relu(net)
+            
+            net = layers.conv2D(net, 4, 64, 2, name='conv0_2', batch_normed=True)
+            net = tf.nn.relu(net)
+                           
+            net = layers.conv2D(X, 3, 128, 1, name='conv1_1', batch_normed=True)
+            net = tf.nn.relu(net)
+            
+            net = layers.conv2D(net, 4, 128, 2, name='conv1_2', batch_normed=True)
+            net = tf.nn.relu(net)
+                     
+            net = layers.conv2D(X, 3, 256, 1, name='conv2_1', batch_normed=True)
+            net = tf.nn.relu(net)
+            
+            net = layers.conv2D(net, 4, 256, 2, name='conv2_2', batch_normed=True)
+            net = tf.nn.relu(net)     
+            net = Flatten()(net)
+            
+            net = layers.linear(net, nb_class, name='dense_layer')
+            
+            net = tf.nn.softmax(net)
+            
+            return net
+    
+    return simple_conv_net