Open junxnone opened 5 years ago
Trains a simple convnet on the MNIST dataset.
Trains a simple deep multi-layer perceptron on the MNIST dataset.
Trains a Hierarchical RNN (HRNN) to classify MNIST digits.
Input() 用于实例化 Keras 张量。 Keras 张量是底层后端(Theano, TensorFlow or CNTK) 的张量对象,我们增加了一些特性,使得能够通过了解模型的输入 和输出来构建Keras模型。
Input(shape=None, batch_shape=None,
name=None, dtype=None, sparse=False,
tensor=None):
长短期记忆网络层 - Hochreiter 1997. recurrent.py
keras.layers.LSTM(units, activation='tanh', recurrent_activation='hard_sigmoid', use_bias=True, kernel_initializer='glorot_uniform', recurrent_initializer='orthogonal', bias_initializer='zeros', unit_forget_bias=True, kernel_regularizer=None, recurrent_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None, bias_constraint=None, dropout=0.0, recurrent_dropout=0.0, implementation=1, return_sequences=False, return_state=False, go_backwards=False, stateful=False, unroll=False)
https://blog.csdn.net/jiangpeng59/article/details/77646186 http://deeplearning.net/tutorial/lstm.html
这个封装器将一个层应用于输入的每个时间片。 输入至少为 3D,且第一个维度应该是时间所表示的维度。
keras.layers.TimeDistributed(layer)
https://blog.csdn.net/oQiCheng1234567/article/details/73051251
就是普通的全连接层。 Dense 实现以下操作: output = activation(dot(input, kernel) + bias) 其中 activation 是按逐个元素计算的激活函数,kernel 是由网络层创建的权值矩阵,以及 bias 是其创建的偏置向量 (只在 use_bias 为 True 时才有用)。
keras.layers.Dense(units, activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)
Train an Auxiliary Classifier Generative Adversarial Network (ACGAN) on the MNIST dataset.
MNIST classification with TensorFlow's Dataset API.
Trains a stacked what-where autoencoder built on residual blocks on the MNIST dataset.
Transfer learning toy example. 1 - Train a simple convnet on the MNIST dataset the first 5 digits [0..4]. 2 - Freeze convolutional layers and fine-tune dense layers for the classification of digits [5..9].
--> #8
Index