trained on custom dataset about self-correction-human-parsing HOT 6 OPEN

@conan2333
There are several things you can have a try to boost the inference speed.

1. replace a lightweight model as the backbone, e.g. MobileNetV3
2. network pruning
3. deploy on TensorRT or TVM

However, have to notice, all these approaches may slightly decrease the model performance.

from self-correction-human-parsing.

Thank you for your fast reply.

I will have a look for your advices.

from self-correction-human-parsing.

I search the TensorRT. But it need a onnx model. Can you please provide the onnx model?

from self-correction-human-parsing.

Please refer to #6 when you want to export the model to onnx. And also welcome to pull request if you have finished it.

from self-correction-human-parsing.

Please refer to #6 when you want to export the model to onnx. And also welcome to pull request if you have finished it.

@conan2333
There are several things you can have a try to boost the inference speed.

1. replace a lightweight model as the backbone, e.g. MobileNetV3
2. network pruning
3. deploy on TensorRT or TVM

However, have to notice, all these approaches may slightly decrease the model performance.

Please refer to #6 when you want to export the model to onnx. And also welcome to pull request if you have finished it.

Hi， I find you have offered the lightweight model of mobilenetv2, but only do a classification job. refer to some comment "invert residual network layer2,layer3,layer4,layer5" in backbone/mobilenet. So i think i should modify this script according AugumentCE2P.py . Am I right?
Can you offer the mIoU score of MobileNetV2 ?
Thank you very much!

from self-correction-human-parsing.

@conan2333 How did you create the custom dataset? All I could find were some colors for labels mentioned in the paper. Can you kinldy explain which tool you used for annotation and how did you select the exact color with the corresponding label.

from self-correction-human-parsing.