Squashed 'keras_visualize_activations/' content from commit 576a4bf

git-subtree-dir: keras_visualize_activations
git-subtree-split: 576a4bff8eed8ccf9e673ec75d8cc2b0074a3de6

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+.DS_Store
+.idea/
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/

LICENSE

+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright {yyyy} {name of copyright owner}
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

+# Extract the activation maps of your Keras models
+[![license](https://img.shields.io/badge/License-Apache_2.0-brightgreen.svg)](https://github.com/philipperemy/keras-attention-mechanism/blob/master/LICENSE) [![dep1](https://img.shields.io/badge/Tensorflow-1.2+-blue.svg)](https://www.tensorflow.org/) [![dep2](https://img.shields.io/badge/Keras-2.0+-blue.svg)](https://keras.io/) 
+
+*Short code and useful examples to show how to get the activations for each layer for Keras.*
+
+**-> Works for any kind of model (recurrent, convolutional, residuals...). Not only for images!**
+
+## Example of MNIST
+
+Shapes of the activations (one sample) on Keras CNN MNIST:
+```
+----- activations -----
+(1, 26, 26, 32)
+(1, 24, 24, 64)
+(1, 12, 12, 64)
+(1, 12, 12, 64)
+(1, 9216)
+(1, 128)
+(1, 128)
+(1, 10) # softmax output!
+```
+
+Shapes of the activations (batch of 200 samples) on Keras CNN MNIST:
+```
+----- activations -----
+(200, 26, 26, 32)
+(200, 24, 24, 64)
+(200, 12, 12, 64)
+(200, 12, 12, 64)
+(200, 9216)
+(200, 128)
+(200, 128)
+(200, 10)
+```
+
+<p align="center">
+  <img src="assets/0.png" width="50">
+  <br><i>A random seven from MNIST</i>
+</p>
+
+
+<p align="center">
+  <img src="assets/1.png">
+  <br><i>Activation map of CONV1 of LeNet</i>
+</p>
+
+<p align="center">
+  <img src="assets/2.png" width="200">
+  <br><i>Activation map of FC1 of LeNet</i>
+</p>
+
+
+<p align="center">
+  <img src="assets/3.png" width="300">
+  <br><i>Activation map of Softmax of LeNet. <b>Yes it's a seven!</b></i>
+</p>
+
+<hr/>
+
+The function for visualizing the activations is in the script [read_activations.py](https://github.com/philipperemy/keras-visualize-activations/blob/master/read_activations.py)
+
+Inputs:
+- `model`: Keras model
+- `model_inputs`: Model inputs for which we want to get the activations (for example 200 MNIST images)
+- `print_shape_only`: If set to True, will print the entire activations arrays (might be very verbose!)
+- `layer_name`: Will retrieve the activations of a specific layer, if the name matches one of the existing layers of the model.
+
+Outputs:
+- returns a list of each layer (by order of definition) and its corresponding activations.
+
+I provide a simple example to see how it works with the MNIST model. I separated the training and the visualizations because if the two were to be done sequentially, we would have to re-train the model every time we would like to visualize the activations! Not very practical! Here are the main steps:
+
+Running `python model_train.py` will do:
+
+- define the model
+- if no checkpoints are detected:
+  - train the model
+  - save the best model in checkpoints/
+- load the model from the best checkpoint
+- read the activations
+
+`model_multi_inputs_train.py` contains very simple examples to visualize activations with multi inputs models. 

data.py

+import keras
+import keras.backend as K
+from keras.datasets import mnist
+
+# input image dimensions
+img_rows, img_cols = 28, 28
+input_shape = (img_rows, img_cols, 1)
+num_classes = 10
+
+
+def get_mnist_data():
+
+    # the data, shuffled and split between train and test sets
+    (x_train, y_train), (x_test, y_test) = mnist.load_data()
+
+    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
+    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
+
+    x_train = x_train.astype('float32')
+    x_test = x_test.astype('float32')
+    x_train /= 255
+    x_test /= 255
+    print('x_train shape:', x_train.shape)
+    print(x_train.shape[0], 'train samples')
+    print(x_test.shape[0], 'test samples')
+
+    # convert class vectors to binary class matrices
+    y_train = keras.utils.to_categorical(y_train, num_classes)
+    y_test = keras.utils.to_categorical(y_test, num_classes)
+    return x_train, y_train, x_test, y_test
\ No newline at end of file

model_multi_inputs_train.py

+import keras.backend as K
+import numpy as np
+from keras.layers import merge, Dense
+from keras.models import Input, Model, Sequential
+
+
+def get_multi_inputs_model():
+    a = Input(shape=(10,))
+    b = Input(shape=(10,))
+    c = merge([a, b], mode='mul')
+    c = Dense(1, activation='sigmoid', name='only_this_layer')(c)
+    m_multi = Model(inputs=[a, b], outputs=c)
+    return m_multi
+
+
+def get_single_inputs_model():
+    m_single = Sequential()
+    m_single.add(Dense(1, activation='sigmoid', input_shape=(10,)))
+    return m_single
+
+
+if __name__ == '__main__':
+
+    m = get_multi_inputs_model()
+    m.compile(optimizer='adam',
+              loss='binary_crossentropy')
+
+    inp_a = np.random.uniform(size=(100, 10))
+    inp_b = np.random.uniform(size=(100, 10))
+    inp_o = np.random.randint(low=0, high=2, size=(100, 1))
+    m.fit([inp_a, inp_b], inp_o)
+
+    from read_activations import *
+
+    get_activations(m, [inp_a[0:1], inp_b[0:1]], print_shape_only=True)
+    get_activations(m, [inp_a[0:1], inp_b[0:1]], print_shape_only=True, layer_name='only_this_layer')
+
+    m2 = get_single_inputs_model()
+    m2.compile(optimizer='adam',
+               loss='binary_crossentropy')
+    m2.fit([inp_a], inp_o)
+
+    get_activations(m2, [inp_a[0]], print_shape_only=True)

model_train.py

+from __future__ import print_function
+
+from glob import glob
+
+import keras
+from keras.callbacks import ModelCheckpoint
+from keras.layers import Conv2D, MaxPooling2D
+from keras.layers import Dense, Dropout, Flatten
+from keras.models import Sequential
+
+from data import get_mnist_data, num_classes, input_shape
+from read_activations import get_activations, display_activations
+
+if __name__ == '__main__':
+
+    checkpoints = glob('checkpoints/*.h5')
+    # pip3 install natsort
+    from natsort import natsorted
+
+    from keras.models import load_model
+
+    if len(checkpoints) > 0:
+
+        checkpoints = natsorted(checkpoints)
+        assert len(checkpoints) != 0, 'No checkpoints found.'
+        checkpoint_file = checkpoints[-1]
+        print('Loading [{}]'.format(checkpoint_file))
+        model = load_model(checkpoint_file)
+
+        model.compile(optimizer='adam',
+                      loss='categorical_crossentropy',
+                      metrics=['accuracy'])
+
+        print(model.summary())
+
+        x_train, y_train, x_test, y_test = get_mnist_data()
+
+        # checking that the accuracy is the same as before 99% at the first epoch.
+        test_loss, test_acc = model.evaluate(x_test, y_test, verbose=1, batch_size=128)
+        print('')
+        assert test_acc > 0.98
+
+        a = get_activations(model, x_test[0:1], print_shape_only=True)  # with just one sample.
+        display_activations(a)
+
+        get_activations(model, x_test[0:200], print_shape_only=True)  # with 200 samples.
+
+        # import numpy as np
+        # import matplotlib.pyplot as plt
+        # plt.imshow(np.squeeze(x_test[0:1]), interpolation='None', cmap='gray')
+    else:
+        x_train, y_train, x_test, y_test = get_mnist_data()
+
+        model = Sequential()
+        model.add(Conv2D(32, kernel_size=(3, 3),
+                         activation='relu',
+                         input_shape=input_shape))
+        model.add(Conv2D(64, (3, 3), activation='relu'))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+        model.add(Dropout(0.25))
+        model.add(Flatten())
+        model.add(Dense(128, activation='relu'))
+        model.add(Dropout(0.5))
+        model.add(Dense(num_classes, activation='softmax'))
+
+        model.compile(loss=keras.losses.categorical_crossentropy,
+                      optimizer=keras.optimizers.Adadelta(),
+                      metrics=['accuracy'])
+
+        # Change starts here
+        import shutil
+        import os
+
+        # delete folder and its content and creates a new one.
+        try:
+            shutil.rmtree('checkpoints')
+        except:
+            pass
+        os.mkdir('checkpoints')
+
+        checkpoint = ModelCheckpoint(monitor='val_acc',
+                                     filepath='checkpoints/model_{epoch:02d}_{val_acc:.3f}.h5',
+                                     save_best_only=True)
+
+        model.fit(x_train, y_train,
+                  batch_size=128,
+                  epochs=12,
+                  verbose=1,
+                  validation_data=(x_test, y_test),
+                  callbacks=[checkpoint])
+
+        # Change finishes here
+
+        score = model.evaluate(x_test, y_test, verbose=0)
+        print('Test loss:', score[0])
+        print('Test accuracy:', score[1])

read_activations.py

+import keras.backend as K
+
+
+def get_activations(model, model_inputs, print_shape_only=False, layer_name=None):
+    print('----- activations -----')
+    activations = []
+    inp = model.input
+
+    model_multi_inputs_cond = True
+    if not isinstance(inp, list):
+        # only one input! let's wrap it in a list.
+        inp = [inp]
+        model_multi_inputs_cond = False
+
+    outputs = [layer.output for layer in model.layers if
+               layer.name == layer_name or layer_name is None]  # all layer outputs
+
+    funcs = [K.function(inp + [K.learning_phase()], [out]) for out in outputs]  # evaluation functions
+
+    if model_multi_inputs_cond:
+        list_inputs = []
+        list_inputs.extend(model_inputs)
+        list_inputs.append(0.)
+    else:
+        list_inputs = [model_inputs, 0.]
+
+    # Learning phase. 0 = Test mode (no dropout or batch normalization)
+    # layer_outputs = [func([model_inputs, 0.])[0] for func in funcs]
+    layer_outputs = [func(list_inputs)[0] for func in funcs]
+    for layer_activations in layer_outputs:
+        activations.append(layer_activations)
+        if print_shape_only:
+            print(layer_activations.shape)
+        else:
+            print(layer_activations)
+    return activations
+
+
+def display_activations(activation_maps):
+    import numpy as np
+    import matplotlib.pyplot as plt
+    """
+    (1, 26, 26, 32)
+    (1, 24, 24, 64)
+    (1, 12, 12, 64)
+    (1, 12, 12, 64)
+    (1, 9216)
+    (1, 128)
+    (1, 128)
+    (1, 10)
+    """
+    batch_size = activation_maps[0].shape[0]
+    assert batch_size == 1, 'One image at a time to visualize.'
+    for i, activation_map in enumerate(activation_maps):
+        print('Displaying activation map {}'.format(i))
+        shape = activation_map.shape
+        if len(shape) == 4:
+            activations = np.hstack(np.transpose(activation_map[0], (2, 0, 1)))
+        elif len(shape) == 2:
+            # try to make it square as much as possible. we can skip some activations.
+            activations = activation_map[0]
+            num_activations = len(activations)
+            if num_activations > 1024:  # too hard to display it on the screen.
+                square_param = int(np.floor(np.sqrt(num_activations)))
+                activations = activations[0: square_param * square_param]
+                activations = np.reshape(activations, (square_param, square_param))
+            else:
+                activations = np.expand_dims(activations, axis=0)
+        else:
+            raise Exception('len(shape) = 3 has not been implemented.')
+        plt.imshow(activations, interpolation='None', cmap='jet')
+        plt.show()

requirements.txt

+Keras==2.0.2
+natsort==5.0.2
+numpy==1.12.1
+h5py
\ No newline at end of file