search

SeungjunNah / DeepDeblur-PyTorch

Deep Multi-scale CNN for Dynamic Scene Deblurring
MIT License
262 stars 42 forks source link

Inquiry into the usage of trained result #23

Closed yorklyb closed 3 years ago

yorklyb commented 3 years ago

Hi，

I‘m wondering if I can use the trained result just like YOLO, e.g. :

import python.darknet as dn

dn.set_gpu(0) net = dn.load_net(str.encode("cfg/tiny-yolo.cfg"), str.encode("weights/tiny-yolo.weights"), 0) meta = dn.load_meta(str.encode("cfg/coco.data")) r = dn.detect(net, meta, str.encode("data/dog.jpg")) print(r)

I'm doing some research on pose estimation and I feel like deblurring will improve the accuracy. I need to implement it on an autonomous vehicle, so it would be great if I can use the trained result directly in my script.

SeungjunNah commented 3 years ago

Sure, you can use the trained weights for your purposes.