-
Notifications
You must be signed in to change notification settings - Fork 75
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I have some problems when training model by myself #4
Comments
The values predicted by the network should be multiplied by -20 to get the real disparity since it was trained by scaling the gt disparity by -20.
In our tests, this strategy is worse than scaling the predictions to full res and computing the loss at that resolution. In the end, at test time, what we want is good full-scale disparity, so that's what we try to optimize during training. |
Thank you for your answer, it's very helpful for me. But I would like to ask if you have trained MADNet on the Monkaa dataset.
|
I'm sorry that I made a mistake. First, the loss weights mentioned in paper should be 0, 0.005, 0.01, 0.02, |
No never tried. The base model was trained on Flying Things 3D
384 x 768
No actually we used sum_l1 |
Thank you for your answer, I will verify what happens to the experimental results when these parameters change. |
Thank you for sharing the code first. But when I read your code (Train.py), I found some things that confused me, as follows:
I don't understand the function of "-20" and "20" in these two lines of code
op = tf.image.resize_images(tf.nn.relu(op * -20), [self._left_input_batch.get_shape()[1].value, self._left_input_batch.get_shape()[2].value])
lines in 70 of Train.pyu5 = tf.image.resize_images(V6, [image_height // scales[5], image_width // scales[5]]) * 20. / scales[5]
lines in 282 of Train.pyrescaled_prediction = tf.image.resize_images(self._get_layer_as_input('final_disp'), [image_height, image_width]) * -20.
lines in 371 of Train.pyWhen I trained on the Monkaa data set, I found that the value of loss always jumped back and forth, and the model did not converge. After many times of failures, I found that some code confused me in the process of network construction.
rescaled_prediction = tf.image.resize_images(self._get_layer_as_input('final_disp'), [image_height, image_width]) * -20.
lines in 371 of Train.pyIn my understand, this code pad the final disparity map to the size of groundtruth. Then use the padded map compute the loss. I think it is easier to converge by reducing the size of groudtruth in the process of computing the loss. I would appreciate it if you could answer my questions. Thank you very much.
The text was updated successfully, but these errors were encountered: