mtcnn

mtcnn copied to clipboard

I am trying to optimise this model from `keras tensorflow` to `tensorflow tensorrt` I was able to extract `pb` file from `PNET` and `ONET` models from the file [factory.py](https://github.com/ipazc/mtcnn/blob/master/mtcnn/network/factory.py) When...

Santhosh1509

Running example.py gives no result

2

Hi, I'm trying to use `mtcnn` and upon running `example.py`, the only output I get is : ``` Using TensorFlow backend. ``` after this, the execution stops without any further...

harshithdwivedi

Could the pre-trained model work on gray-scale images?

1

I tried it on gray-scale images but it just returned '[]', could it work on gray scale images or it can only work on RGB images?

fcs203

threshold

1

i am using this in images, what is the point of the threshold value? my results are the same with 0.1 and 0.9?

ftfajardo

As mentioned by Nvidia here: https://devblogs.nvidia.com/speed-up-inference-tensorrt/ I am trying to implement TensorRT in this project, but unfortunately I am unable to find the .pb file. I am new to machine...

sibidharan

Found lagging if frame size goes beyond 100KB. Face detection accuracy affects if resolution comes down. What could be the optimal frame resolution and size for the face detect method?...

jboundaries

Hi I need to get tflite model of weights here to work with Android NNAPI . Could someone please help ? regards Avaish

avaish1

marcomerc

Folks, How can I train with the current available code? Thanks,

RoboEvangelist

Benchmark information?

1

@ipazc , could provide more details about the [benchmark](https://github.com/ipazc/mtcnn#benchmark) setup? In particular: - What minFaceSize, scaleFactor and stepsThreshold where used? - Could you please share the benchmark test images, so...

tzolov