Vijay Anand

Is there any script to test custom image on the pretrained model or to train a custom dataset to predict the joints? This is already mentioned in https://github.com/mitmul/deeppose/issues/10.

How to binarize the features from fc8_kevin layer

1

I am trying to deploy the network with python. Can someone help me with converting converting the features from fc8_kevin to binary. For example, the output from fc8 is like...

Training custom dataset

3

Are there any detailed instructions on how to train custom dataset (apart from Imagenet and ALOV dataset) ? And are there any python implementation to train the tracker?

I found that generating a gaussian map (in[12]) consumes around 0.5 seconds. So I did something like this `gaussian_map=np.fromfunction(lambda x_p,y_p: np.exp(-1*((x_p - model['boxsize']/2) * (x_p - model['boxsize']/2) +(y_p - model['boxsize']/2)...

Extracting features from trained model

12

@anvaysrivastava : I found script to extract features but any instructions on how to convert train.prototxt to deploy.prototxt would be appreciated.