def test_to_categorical(self, size, num_labels):
label = np.random.randint(low=0, high=num_labels, size=(size, ))
categorical_tf = tf.keras.utils.to_categorical(label, num_classes=None)
categorical_np = to_categorical(label)
np.testing.assert_allclose(categorical_tf, categorical_np)
def test_from_categorical(self, size, num_labels):
label = np.random.uniform(low=0, high=num_labels, size=(size, ))
categorical_tf = tf.keras.utils.to_categorical(label, num_classes=None)
categorical_np = to_categorical(label)
np.testing.assert_allclose(categorical_tf, categorical_np)
fromlabel_tf = tf.math.argmax(categorical_tf, axis=-1)
fromlabel_np = from_categorical(categorical_np)
np.testing.assert_allclose(fromlabel_tf, fromlabel_np)
train_size = 512
test_size = 300
X_train = X_train[:train_size, ...]
y_train = y_train[:train_size]
X_test = X_test[:test_size, ...]
y_test = y_test[:test_size]
############################################
n_train = X_train.shape[0]
n_test = X_test.shape[0]
# transform y to array of dimension 10 and in 4 dimension
y_train = to_categorical(y_train).reshape(n_train, 1, 1, -1)
y_test = to_categorical(y_test).reshape(n_test, 1, 1, -1)
# Create the model and training
model = Network(batch=batch, input_shape=X_train.shape[1:])
model.add(
Convolutional_layer(size=3,
filters=32,
stride=1,
pad=True,
activation='Relu'))
model.add(BatchNorm_layer())
model.add(Maxpool_layer(size=2, stride=1, padding=True))
'this was very sad earlier': False,
'i was good and not bad earlier': True,
'i was not good and not happy earlier': False,
# 'i am not at all bad or sad right now': True,
# 'i am not at all good or happy right now': False,
'this was not happy and not good earlier': False,
}
# TODO: Up to now it works only if the number of samples is perfectly divisible by batch!!!
words = set((w for text in data.keys() for w in text.split(' ')))
print('{:d} unique words found'.format(len(words)))
coding = {k : v for k, v in enumerate(words)}
one_hot_encoding = to_categorical(list(data.keys()))
batch, size = one_hot_encoding.shape
one_hot_encoding = one_hot_encoding.reshape(batch, 1, 1, size)
outputs = 8
# Model initialization
layer = LSTM_layer(outputs, steps=3, input_shape=one_hot_encoding.shape)
print(layer)
layer.forward(one_hot_encoding)
forward_out = layer.output.copy()
layer.wf.delta = np.ones(shape=(layer.wf.out_shape), dtype=float)
layer.wi.delta = np.ones(shape=(layer.wi.out_shape), dtype=float)
layer.wg.delta = np.ones(shape=(layer.wg.out_shape), dtype=float)