RameenAbdal / StyleFlow

StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)
http://rameenabdal.github.io/StyleFlow
2.42k stars 342 forks source link

Execution freezes after some steps #145

Closed ujjawalcse closed 1 year ago

ujjawalcse commented 1 year ago

Hey @RameenAbdal , Thanks for this amazing repo. I'm trying to execute this repo for different lighting conditions.

Earlier it raises a different error when i run python main.py,

----------------- Options ---------------
                batchSize: 1                             
          checkpoints_dir: ./checkpoints                 
                 dataroot: ./data/datasetX               
                  gpu_ids: 0                             
     max_result_snapshots: 30                            
                    model: xxxx                          
                     name: XXXX                          
              network_pkl: gdrive:networks/stylegan2-ffhq-config-f.pkl
            only_for_test: ...                           
                    phase: test                          
----------------- End -------------------
QObject::moveToThread: Current thread (0x5567aaaaa0a0) is not the object's thread (0x5567aff44920).
Cannot move to target thread (0x5567aaaaa0a0)

qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/ujjawal/miniconda2/envs/caffe2/lib/python3.7/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: xcb, eglfs, linuxfb, minimal, minimalegl, offscreen, vnc, wayland-egl, wayland, wayland-xcomposite-egl, wayland-xcomposite-glx, webgl.

Then, I tried the following and error get resolved, export QT_QPA_PLATFORM=offscreen

Then I tried executing as following and getting freezed after a certain steps,

python main.py 
----------------- Options ---------------
                batchSize: 1                             
          checkpoints_dir: ./checkpoints                 
                 dataroot: ./data/datasetX               
                  gpu_ids: 0                             
     max_result_snapshots: 30                            
                    model: xxxx                          
                     name: XXXX                          
              network_pkl: gdrive:networks/stylegan2-ffhq-config-f.pkl
            only_for_test: ...                           
                    phase: test                          
----------------- End -------------------
Loading networks from "gdrive:networks/stylegan2-ffhq-config-f.pkl"...
Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Loading... Done.
Setting up TensorFlow plugin "upfirdn_2d.cu": Preprocessing... Loading... Done.
Training T : 1.0
Number of trainable parameters of Point CNF: 1691649

No gui/prompt is being presented. is any process running(training,optimization) in backround that's why taking time? Please suggest some way out.

ujjawalcse commented 1 year ago

Resolved. It was using qt library inside cv2 site-package. Just modified to used original qt5 sitepackage.