about the STN loss

[Fangction]

Is there any STN loss to constraint the transformation angle？I didn't find it in your code. If there is no one, how do the net know the how to transfer a picture?

[wushilian]

@Fangction There is no stn loss,stn was supervised by ctc loss.However,if you have more supersied information,you can add constraint.For example,monitoring the coordinates regressed by the STN.

[Fangction]

@wushilian thank you. And I have another question. In your code W = tf.Variable(tf.zeros([128, 20])) b = tf.Variable(initial_value=[-1, -0.2, -0.5, -0.35, 0, -0.5, 0.5, -0.67, 1, -0.8, -1, 0.8, -0.5, 0.65, 0, 0.5, 0.5, 0.33, 1, 0.2], dtype=tf.float32)

fc3_loc=tf.layers.dense(fc2_loc,20,activation=tf.nn.tanh,kernel_initializer=tf.zeros_initializer)

            # fc3_loc = slim.fully_connected(fc2_loc, 8, activation_fn=tf.nn.tanh, scope='fc3_loc')
            # spatial transformer
            fc3_loc = tf.nn.tanh(tf.matmul(fc2_loc, W) + b)#激活函数结果
            loc = tf.reshape(fc3_loc, [-1, 10, 2])#将fc3_loc的结果按照-1 10 2的结构reshape
            # spatial transformer
            s = np.array([[-0.95, -0.95], [-0.5, -0.95], [0, -0.95], [0.5, -0.95], [0.95, -0.95], [-0.95, 0.95], [-0.5, 0.95], [0, 0.95], [0.5, 0.95],
                          [0.95,0.95]] * 256)
            s = tf.constant(s.reshape([256, 10, 2]), dtype=tf.float32)

how did you decide the value of variable b and s?

[wushilian]

@Fangction b means Specific initialization，for details,you need to read the paper:Robust Scene Text Recognition with Automatic Rectification

[Fangction]

@wushilian thank you again. And I also want to ask one more question. Do you think the STN's output image size must be fixed size？I see you define the output as image_width=120 image_height=32. Can i keep the size of output image same as the input image?

[wushilian]

@Fangction Yes，you can change the size.

[daming98]

@Fangction Yes，you can change the size.

I change the size and it cause a error like "InvalidArgumentError (see above for traceback): len(seq_lens) != input.dims(0), (256 vs. 1536)"

What can I do to solve this error?