test_frcnn.py not working? about keras-fasterrcnn HOT 12 OPEN

@mkvashennikov I haven't looked a this since 2019. I don't remember fixing it. I think I used another implementation.

from keras-fasterrcnn.

I've also been facing the same problem, maybe the dataset is too small and the code is incapable of transfer learning

from keras-fasterrcnn.

i use the voc2012, i've also been facing the same problem.

from keras-fasterrcnn.

I went into checking the code of this file; found out that the bboxes dict is empty, thereafter, running a for loop on it will be nullified (which contains the bbox plotting). I guess reducing bbox threshold may fix it, tho I haven't tried it yet.

from keras-fasterrcnn.

I train VOC2012 epochs=126 loss rpn classifier = 3.22 oscillate around 3 without falling.

from keras-fasterrcnn.

Maybe the data set is too big? Or is there a problem with the parameters of the training?

from keras-fasterrcnn.

My model is currently only able to detect people and train for 8 hours. The current box is not very accurate

from keras-fasterrcnn.

Dataset is of 3471 images (originally of 267 images, increased by augmentation). Parameters of training are as default except I changed the learning rate to 0.01, and others optimizers, but same result.

from keras-fasterrcnn.

@3ST4R I have tested this and it seems even if the bbox threshold is set to zero there still is no bbox.

from keras-fasterrcnn.

@collinarnett I also checked your post about weights not loading, and I tried that, still there is no bbox.

So, what should be a possible solution to this problem. As, I see the blogs where people getting it working absolutely fine, without any digging into the code, I wonder how.

from keras-fasterrcnn.

@3ST4R have u fixed this problem? I'm facing this problem too.

from keras-fasterrcnn.

I train VOC2012 epochs=126 loss rpn classifier = 3.22 oscillate around 3 without falling.

@3ST4R, @collinarnett im facing with this problem too. Maybe you fix this problem..?

from keras-fasterrcnn.