ram.py 文件源码

def calc_reward(outputs):

    # consider the action at the last time step
    outputs = outputs[-1] # look at ONLY THE END of the sequence
    outputs = tf.reshape(outputs, (batch_size, cell_out_size))

    # get the baseline
    b = tf.pack(baselines)
    b = tf.concat(2, [b, b])
    b = tf.reshape(b, (batch_size, (nGlimpses) * 2))
    no_grad_b = tf.stop_gradient(b)

    # get the action(classification)
    p_y = tf.nn.softmax(tf.matmul(outputs, Wa_h_a) + Ba_h_a)
    max_p_y = tf.arg_max(p_y, 1)
    correct_y = tf.cast(labels_placeholder, tf.int64)

    # reward for all examples in the batch
    R = tf.cast(tf.equal(max_p_y, correct_y), tf.float32)
    reward = tf.reduce_mean(R) # mean reward
    R = tf.reshape(R, (batch_size, 1))
    R = tf.tile(R, [1, (nGlimpses)*2])

    # get the location
    p_loc = gaussian_pdf(mean_locs, sampled_locs)
    p_loc = tf.tanh(p_loc)
    p_loc_orig = p_loc
    p_loc = tf.reshape(p_loc, (batch_size, (nGlimpses) * 2))

    # define the cost function
    J = tf.concat(1, [tf.log(p_y + SMALL_NUM) * (onehot_labels_placeholder), tf.log(p_loc + SMALL_NUM) * (R - no_grad_b)])
    J = tf.reduce_sum(J, 1)
    J = J - tf.reduce_sum(tf.square(R - b), 1)
    J = tf.reduce_mean(J, 0)
    cost = -J

    # define the optimizer
    optimizer = tf.train.MomentumOptimizer(lr, momentumValue)
    train_op = optimizer.minimize(cost, global_step)

    return cost, reward, max_p_y, correct_y, train_op, b, tf.reduce_mean(b), tf.reduce_mean(R - b), lr