galaktyk

@khanh1412 in misc.py line29 change it to your custom labels file. file = 'labels.txt' P.S. It's a temporary solution.

I did try convert lite_0 model to tfkeras model [here](https://drive.google.com/drive/folders/1aohDcEFJFMkv6rCQ1Gw4uJCyAFEexBp8?usp=sharing) ⚠ input normalization is (image/127.5) -1.

> > > I really appreciate someone converts the model from tf but I lose the ability to tune my input_shape without having a model class. Does someone know how...

Did you normalized with (image/127.5) -1. ?

> > I am using https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG and got top 5 Predicted: [[('n04501370', 'turnstile', 0.0046648816), ('n02108089', 'boxer', 0.0037645926), ('n04325704', 'stole', 0.0035586052), ('n07583066', 'guacamole', 0.0034703321), ('n04357314', 'sunscreen', 0.0033295394)]] > […](#) > On...

@l0stpenguin It's a tensorflow.keras model... ...But you can convert tfkeras to keras anyway. ``` 1. In TFKeras, Load and save tfkeras in .json model with model.to_json() 2. save weights with...

@l0stpenguin yes. Tested with tfkeras1.14, tfkeras2.0, tfkeras2.1, tfkeras2.2, Keras2.3(backend tf1.14), Keras2.3(backend tf2.0), Keras2.3(backend tf2.1), Keras2.3(backend tf2.2)

It because colab now use tensorflow2 as default and the 'contrib' module is not available anymore. So I've made a Tensorflow lite-version of this repo here --> https://github.com/galaktyk/mocap-hmr-tflite

What is your input tensor resolution? Can you try (257,257) first. I've checked output offsets and displacement and found that it is directly predicted in pixel unit.

Use FFmpeg to capture RTSP stream then feed image to YOLO in cv2.VideoCapture(img) (darkflow/darkflow/net/help.py) I hope it will work out well for you