Hi, I finished wflw dataset using face-mesh-generator in colab environment. I just got tfrecord and what is that? How can I use it for training on hrnet? do I have to save heatmapped image indivisually like figs??
when I check train.py file, train dir path is wflw_cropped folder. how can I access crop? that means need to use face detector?
Hi, I finished wflw dataset using face-mesh-generator in colab environment. I just got tfrecord and what is that? How can I use it for training on hrnet? do I have to save heatmapped image indivisually like figs??
when I check train.py file, train dir path is wflw_cropped folder. how can I access crop? that means need to use face detector?