(inputs, in_size, out_size, activation_function=None)
| 11 | import numpy as np |
| 12 | |
| 13 | def add_layer(inputs, in_size, out_size, activation_function=None): |
| 14 | # add one more layer and return the output of this layer |
| 15 | Weights = tf.Variable(tf.random_normal([in_size, out_size])) |
| 16 | biases = tf.Variable(tf.zeros([1, out_size]) + 0.1) |
| 17 | Wx_plus_b = tf.matmul(inputs, Weights) + biases |
| 18 | if activation_function is None: |
| 19 | outputs = Wx_plus_b |
| 20 | else: |
| 21 | outputs = activation_function(Wx_plus_b) |
| 22 | return outputs |
| 23 | |
| 24 | # Make up some real data |
| 25 | x_data = np.linspace(-1,1,300)[:, np.newaxis] |
no outgoing calls
no test coverage detected