sergiomsilva
sergiomsilva
I think there is a small chance of the augmentation function generates the original images since everything is random... This is a common practice, darknet framework does the same to...
Hi @xiaowenhe , this is a good question. In the first 3 lines, the original corner points are transformed into a rectangular bounding box with aspect ratio varying between 2:1...
Usually a Python 3 issue with Darknet. Please use Python 2.7.
In the LP output volume from WPOD-NET, there are 8 channels. The first 2 are probabilities of being and not-being a LP. Take a look at the output volume in...
Hi @linzhi123 , sorry but we do not plan to publish this part anytime soon.
I see you are interested in the training script, and I am sorry for not being able to share it with you guys at this moment because I'm really out...
No, the modification is not in our repo.
Take a look at #19 , even with correct labels you will not be able to train the network with Darknet as is. You need to modify the data augmentation...
We trained with a high variety of sizes and license plate layouts to generalize as much as possible, but surely there is a maximum size. Can you post here one...
Hi, such kind of image cannot be detected indeed! The system works when the full car is appearing, not close captures. You can change this behaviour by lowering the input...