Function get_detect_model

model.py:130–153

The same as the training model, except it acts on an arbitrarily sized input, and slides the 128x64 window across the image in 8x8 strides. The output is of the form `v`, where `v[i, j]` is equivalent to the output of the training model, for the window at coordinates `(8 * i, 4 * j

()

def get_detect_model():
    """
    The same as the training model, except it acts on an arbitrarily sized
    input, and slides the 128x64 window across the image in 8x8 strides.

    The output is of the form `v`, where `v[i, j]` is equivalent to the output
    of the training model, for the window at coordinates `(8 * i, 4 * j)`.

    """
    x, conv_layer, conv_vars = convolutional_layers()
    
    # Fourth layer
    W_fc1 = weight_variable([8 * 32 * 128, 2048])
    W_conv1 = tf.reshape(W_fc1, [8,  32, 128, 2048])
    b_fc1 = bias_variable([2048])
    h_conv1 = tf.nn.relu(conv2d(conv_layer, W_conv1,
                                stride=(1, 1), padding="VALID") + b_fc1) 
    # Fifth layer
    W_fc2 = weight_variable([2048, 1 + 7 * len(common.CHARS)])
    W_conv2 = tf.reshape(W_fc2, [1, 1, 2048, 1 + 7 * len(common.CHARS)])
    b_fc2 = bias_variable([1 + 7 * len(common.CHARS)])
    h_conv2 = conv2d(h_conv1, W_conv2) + b_fc2

    return (x, h_conv2, conv_vars + [W_fc1, b_fc1, W_fc2, b_fc2])