LIP_JPPNet

LIP_JPPNet copied to clipboard

Training New Data

5

Would it be possible to train using a completely new set of data? Why is it necessary to download a pre-trained model for training?

chnanc001

I am working on Person-ReID and I have to create part maps for it. However I am not getting how to preprocess custom dataset i.e. Market-1501 ? Need assistance in...

FatimaZulfiqar

I want to load the model only once. Can you tell me how to do that?

anantaarora

Time

3

What is the expected runtime for pose and parsing? When I'm testing with multiple images, >4secs is taken for the first followed by 1sec(apprx.) for the remaining images excluding the...

b121351

Create get_maximum_square_from_segmented_image.py

1

This is a useful function when you want to get the maximum possible square from the segmented image which can be later passed as embedding in combination with text features...

Vickyilango

pb file

4

Hi,Engineering-Course: I freeze your model to a pb file for inference,but the first node is a fifo,not a input type,Can the code change to make the first layer is a...

zhly0

Is cuda environment necessary for running evaluate_parsing_JPPNet-s2.py?

1

ujjawalcse

GrayXu

Hi, thanks for your excellent work. I found the GPU utilization was quit low when running the evaluate_parsing_JPPNet-s2.py even though I changed the batch_size to 8. Could you tell me...

QQQYang

Unsatisfactory results about testing the pre-trained model on jumpsuits

1

Hi, When testing with your pre-trained model, the model did not perform well in jumpsuits, detecting the jumpsuit as a top and a pair of pants. Is this because the...

zengwei1302