see--
see--
I will add training scripts for smaller models on COCO. Training the hourglass network with 2 stacks won't be possible. It takes quite long and Keras/Tensorflow is not as fast...
No, there isn't a plan for adding training code. Sorry for the false promise. In terms of performance, I didn't get close to PyTorch. Here is a great summary of...
There is no code to do this automatically. The network is defined here: https://github.com/see--/keras-centernet/blob/master/keras_centernet/models/networks/hourglass.py. I named the layers so that they match with PyTorch weights. Maybe you mean the weight...
Hmmm, I only found debugging stuff.
Yeah I found that. It looks like debugging to me. You seem to be more familiar. Does it reproduce the VOC results?
Aha, the answer is no it doesn't.
Typically, ImageNet models produce 1/32 tensors, if you remove the top. For CenterNet 2D-detection you need three 1/4 tensors. E.g. image: 512, 512, 3 -> hm: 128, 128, 80, reg:...
Sounds like a version mismatch problem. Did you install the transformers version from this repo? I.e. this part from the readme: ``` # get the code git clone https://github.com/see--/natural-question-answering.git #...