Closed kuwt closed 4 years ago
I changed the crop image aspect ratio. The result is better.
Yes, I assume you used the aae_image.py script to generate these results? In contrast to the other test scripts, it does not pad the input images before inserting them into the AAE but simply resizes them to a quadratic fixed size. This introduces strong distortions if your original input is not quadratic and therefore the pose estimation fails. So simply padding with black pixels up to a quadratic aspect ratio should prevent that. I will add the padding also to aae_image.py.
.
Thanks for the code for evaluation. I have trained it on a custom object:![image](https://user-images.githubusercontent.com/20258451/66034499-ecc9f380-e53b-11e9-82ac-0b3043f0b00b.png)
I tested it on 3 samples(first row) and the result is (second row):![image](https://user-images.githubusercontent.com/20258451/66035415-aaa1b180-e53d-11e9-8bd8-5ab729415181.png)
The middle object has an incorrect output. What is your idea on this issue?