search

junyanz / interactive-deep-colorization

Deep learning software for colorizing black and white images with a few clicks.
https://richzhang.github.io/ideepcolor/
MIT License
2.69k stars 447 forks source link

On Windows 10 with pytorch, it will only use the CPU despite saying it's using the GPU #86

Open Sister-Perish opened 3 years ago

Sister-Perish commented 3 years ago

Here's the output it gives when run:

MatplotlibDeprecationWarning: The support for Qt4 was deprecated in Matplotlib 3.3 and will be removed two minor releases later. from matplotlib.backends.qt_compat import QtGui [win_size] = 512 [image_file] = test_imgs/mortar_pestle.jpg [gpu] = 0 [cpu_mode] = False [color_prototxt] = ./models/reference_model/deploy_nodist.prototxt [color_caffemodel] = ./models/reference_model/model.caffemodel [dist_prototxt] = ./models/reference_model/deploy_nopred.prototxt [dist_caffemodel] = ./models/reference_model/model.caffemodel [color_model] = ./models/pytorch/caffemodel.pth [backend] = pytorch [pytorch_maskcent] = False [load_size] = 256 ColorizeImageTorch instantiated path = ./models/pytorch/caffemodel.pth Model set! dist mode? False ColorizeImageTorch instantiated path = ./models/pytorch/caffemodel.pth Model set! dist mode? True test_imgs/mortar_pestle.jpg scale = 2.000000

But the GPU does nothing, while the CPU is maxed out and the colorization is very slow. I have installed all of the GPU stuff and verified it's working, so I don't see what the problem is.

semel1 commented 3 years ago

The same with me. GPU utilization = 0