diff --git a/skluc/main/data/transformation/VGG19Transformer.py b/skluc/main/data/transformation/VGG19Transformer.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/skluc/main/data/transformation/VGG19Transformer/VGG19Cifar10CovAbs.py b/skluc/main/data/transformation/VGG19Transformer/VGG19Cifar10CovAbs.py
deleted file mode 100644
index 170260bd5e0d95fe7d00665d2ff28caf46e8d140..0000000000000000000000000000000000000000
--- a/skluc/main/data/transformation/VGG19Transformer/VGG19Cifar10CovAbs.py
+++ /dev/null
@@ -1,98 +0,0 @@
-import os
-
-import numpy as np
-from keras import Model
-from keras.models import load_model
-
-from skluc.main.data import VGG19Transformer
-from skluc.main.utils import logger, create_directory, download_data, check_file_md5, deprecated
-
-
-# todo check those deprecated things
-@deprecated
-class VGG19Cifar10CovAbs(VGG19Transformer):
- """
- Extend the vgg19transformer class with weights learned on CIFAR10.
- The covariance matrix is then computed on the transformed data image.
- """
- NAME = "vgg19_cifar10_cov"
- MODEL_URL = "https://pageperso.lis-lab.fr/~luc.giffon/models/1522967518.1916964_vgg19_cifar10.h5"
- MODEL_CHECKSUM = "0dbb4f02ceb1f4acb6e24831758106e5"
- # todo faire une fonction qui regarde directement le checksum sur le site ?
-
- def __init__(self):
- super().__init__(name=self.NAME)
-
- @staticmethod
- def _compute_cov_matrix(data):
- """
-
- :param data: (b x W x H x D)
- :type data: np.ndarray
- :return:
- """
- data = data.reshape((data.shape[0], data.shape[1] * data.shape[2], data.shape[3]))
- mean = np.mean(data, axis=1)
- mean = mean.reshape((mean.shape[0], 1, mean.shape[-1]))
- data_centered = data - mean
-
- cov_mat = []
- for i, mat in enumerate(data_centered):
- cov_mat.append(mat.T.dot(mat))
- if i % 1000 == 0:
- logger.debug("Computing covariance matrix - step {}/{}".format(i, len(data_centered)))
- cov_mat = 1. / data.shape[1] * np.array(cov_mat)
- logger.debug("Final covariance matrix shape: {}".format(str(cov_mat.shape)))
- return cov_mat
-
- @staticmethod
- def _compute_log_matrix(data):
- log_mat = []
- for i, mat in enumerate(data):
- U, S, V = np.linalg.svd(mat, full_matrices=False)
- log_mat.append(U.dot(np.diag(np.log(S))).dot(V))
- if i % 1000 == 0:
- logger.debug("Computing log matrix - step {}/{}".format(i, len(data)))
- log_mat = np.array(log_mat)
- logger.debug("Final log matrix shape: {}".format(str(log_mat.shape)))
- return log_mat
-
- def load(self):
- create_directory(self.s_download_dir)
- s_model_path = download_data(self.MODEL_URL, self.s_download_dir)
- check_file_md5(s_model_path, self.__class__.MODEL_CHECKSUM)
- if self.vgg_conv_model is None:
- logger.debug("Loading VGG19 model with cifar10 weights")
- self.vgg_conv_model = load_model(s_model_path)
- bloc3pool_layer = self.vgg_conv_model.get_layer('block3_pool')
- # this is weird but the index is actually the index of the layer just before the pooling layer
- # so this is what we want here: we don't want the pooling
- index_bloc3pool_layer = self.vgg_conv_model.layers.index(bloc3pool_layer)
- self.vgg_conv_model = Model(inputs=self.vgg_conv_model.input,
- outputs=self.vgg_conv_model.get_layer(index=index_bloc3pool_layer).output)
- else:
- logger.debug("Skip loading model VGG19 model with cifar10 weights. Already there.")
-
- def transform(self, data, labels):
- if len(data.shape) != 4:
- raise AssertionError("Data shape should be of size 4 (image batch with channel dimension). "
- "It is {}: {}. Maybe have you forgotten to reshape it to an image format?"
- "".format(len(data.shape), data.shape))
- self.load()
- transformed_data, labels = super().transform(data, labels)
- transformed_data = self._compute_cov_matrix(transformed_data)
- return transformed_data, labels
-
- def check_model(self):
- name = os.path.basename(os.path.normpath(self.__class__.MODEL_URL))
- s_file_path = os.path.join(self.s_download_dir, name)
- if os.path.exists(s_file_path) and check_file_md5(s_file_path,
- self.__class__.MODEL_CHECKSUM,
- raise_=False):
- return True
- else:
- return False
-
-
-
-
diff --git a/skluc/main/data/transformation/VGG19Transformer/VGG19ImageNetTransformer.py b/skluc/main/data/transformation/VGG19Transformer/VGG19ImageNetTransformer.py
deleted file mode 100644
index 4e3a4db28fa7c6059125fa73f27567ec67c3f4e4..0000000000000000000000000000000000000000
--- a/skluc/main/data/transformation/VGG19Transformer/VGG19ImageNetTransformer.py
+++ /dev/null
@@ -1,31 +0,0 @@
-from keras.applications import VGG19
-
-from skluc.main.data import VGG19Transformer
-from skluc.main.utils import logger, deprecated, Singleton
-
-
-@deprecated
-class VGG19ImagenetTransformer(VGG19Transformer, metaclass=Singleton):
- """
- Extend the vgg19transformer class with convolutional wieghts learned on the imagenet dataset.
- """
- NAME = "vgg19_imagenet"
-
- def __init__(self):
- super().__init__(name=self.NAME)
-
- def load(self, input_shape):
- if self.vgg_conv_model is None:
- logger.debug("Loading VGG19 model with imagenet weights from keras")
- self.vgg_conv_model = VGG19(include_top=False, weights='imagenet', input_shape=input_shape)
- else:
- logger.debug("Skip loading model VGG19 model with imagenet weights. Already there.")
-
- def transform(self, data, labels):
- # todo trouver une solution pour ne pas avoir un copier collé entre cette classe et celle avec cifar
- if len(data.shape) != 4:
- raise AssertionError("Data shape should be of size 4 (image batch with channel dimension). "
- "It is {}: {}. Maybe have you forgotten to reshape it to an image format?"
- "".format(len(data.shape), data.shape))
- self.load(input_shape=data[0].shape)
- return super().transform(data, labels)
diff --git a/skluc/main/data/transformation/VGG19Transformer/__init__.py b/skluc/main/data/transformation/VGG19Transformer/__init__.py
deleted file mode 100644
index cfbbdde0cea5d83c0b65aac458c84cfe5d2b03d8..0000000000000000000000000000000000000000
--- a/skluc/main/data/transformation/VGG19Transformer/__init__.py
+++ /dev/null
@@ -1,93 +0,0 @@
-from keras import Model
-from keras.models import load_model
-
-from skluc.main.data.mldatasets.Cifar10Dataset import Cifar10Dataset
-from skluc.main.data.transformation.KerasModelTransformer import KerasModelTransformer
-from skluc.main.utils import logger, create_directory, download_data, check_file_md5, Singleton, DownloadableModel
-
-
-class VGG19Transformer(KerasModelTransformer, metaclass=Singleton):
- """
- Uses the vgg19 convolution network to transform data.
- """
-
- MAP_DATA_MODEL = {
- "svhn": DownloadableModel(
- url="https://pageperso.lis-lab.fr/~luc.giffon/models/1529968150.5454917_vgg19_svhn.h5",
- checksum="563a9ec2aad37459bd1ed0e329441b05"
- ),
- "cifar100": DownloadableModel(
- url="https://pageperso.lis-lab.fr/~luc.giffon/models/1530965727.781668_vgg19_cifar100fine.h5",
- checksum="edf43e263fec05e2c013dd5a2128fc38"
- ),
- "cifar10": DownloadableModel(
- url="https://pageperso.lis-lab.fr/~luc.giffon/models/1522967518.1916964_vgg19_cifar10.h5",
- checksum="0dbb4f02ceb1f4acb6e24831758106e5"
- ),
- "siamese_omniglot_28x28": DownloadableModel(
- url="https://pageperso.lis-lab.fr/~luc.giffon/models/1536244775.6502118_siamese_vgg19_omniglot_28x28_conv.h5",
- checksum="90aec06e688ec3248ba89544a10c9f1f"
- ),
- "omniglot_28x28": DownloadableModel(
- url="https://pageperso.lis-lab.fr/~luc.giffon/models/1536764034.66037_vgg19_omniglot.h5",
- checksum="ef1272e9c7ce070e8f70889ec58d1c33"
- )
- }
-
- def __init__(self, data_name, cut_layer_name=None, cut_layer_index=None):
- if data_name not in self.MAP_DATA_MODEL.keys():
- raise ValueError("Unknown data name. Can't load weights")
-
- if cut_layer_name is None and cut_layer_index is None:
- logger.warning(
- "Cut layer chosen automatically but it eventually will lead to an error in future: block5_pool should be specified explicitly")
- cut_layer_name = "block5_pool"
- if cut_layer_name is not None:
- transformation_name = str(data_name) + "_" + self.__class__.__name__ + "_" + str(cut_layer_name)
- elif cut_layer_index is not None:
- transformation_name = str(data_name) + "_" + self.__class__.__name__ \
- + "_" + str(cut_layer_index)
- # todo sauvegarder index / nom dans le meme dossier si c'est les meme
- else:
- raise AttributeError("Cut layer name or cut_layer index must be given to init VGG19Transformer.")
- self.__cut_layer_name = cut_layer_name
- self.__cut_layer_index = cut_layer_index
-
- self.keras_model = None
-
- super().__init__(data_name=data_name,
- transformation_name=transformation_name)
-
- def load(self):
- create_directory(self.s_download_dir)
- s_model_path = download_data(self.MAP_DATA_MODEL[self.data_name].url, self.s_download_dir)
- check_file_md5(s_model_path, self.MAP_DATA_MODEL[self.data_name].checksum)
- if self.keras_model is None:
- logger.debug("Loading VGG19 model for {} transformation with {} weights".format(self.transformation_name, self.data_name))
- self.keras_model = load_model(s_model_path)
-
- logger.debug("Layers of model {}".format([l.name for l in self.keras_model.layers]))
-
- if self.__cut_layer_index is not None:
- cut_layer = self.keras_model.layers[-1]
- self.__cut_layer_name = cut_layer.name
- logger.debug(
- "Found associated layer {} to layer index {}".format(self.__cut_layer_name, self.__cut_layer_index))
-
- self.keras_model = Model(inputs=self.keras_model.input,
- outputs=self.keras_model.get_layer(name=self.__cut_layer_name).output)
-
- else:
- logger.debug("Skip loading model VGG19 for {} transformation with {} weights. Already there.".format(
- self.transformation_name,
- self.data_name))
-
-
-if __name__ == '__main__':
- valsize = 10000
- d = Cifar10Dataset(validation_size=valsize)
-
- d.load()
- d.to_image()
- trans = VGG19Transformer(data_name="cifar10", cut_layer_name="block5_pool")
- d.apply_transformer(transformer=trans)