search

NagabhushanSN95 / ViP-NeRF

Official code release accompanying the paper - "ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields"
MIT License
68 stars 7 forks source link

Error while testing on NeRF LLFF dataset using pre-trained models #8

Open HarshaMupparaju opened 1 year ago

HarshaMupparaju commented 1 year ago

I have downloaded the pre-trained models for NeRF-LLFF and put them into the respective folders which is train0011/scene_name/saved_models , when I ran NerfLlffTrainerTester01.py after commenting out the train calls in the code, I got this error:

Traceback (most recent call last):
  File "NerfLlffTrainerTester01.py", line 999, in <module>
    main()
  File "NerfLlffTrainerTester01.py", line 986, in main
    demo1a()
  File "NerfLlffTrainerTester01.py", line 349, in demo1a
    start_testing_videos(test_configs)
  File "NerfLlffTrainerTester01.py", line 156, in start_testing_videos
    output_dirpath = Tester.start_testing(test_configs, scenes_data, output_dir_suffix)
  File "/mnt/2tb-hdd/harshaM/ViP-NeRF/src/Tester01.py", line 210, in start_testing
    predictions = tester.predict_frame(tgt_pose, view_tgt_pose, secondary_poses,
  File "/mnt/2tb-hdd/harshaM/ViP-NeRF/src/Tester01.py", line 59, in predict_frame
    input_dict = self.data_preprocessor.create_test_data(camera_pose, view_camera_pose, secondary_poses, True,
  File "/mnt/2tb-hdd/harshaM/ViP-NeRF/src/data_preprocessors/DataPreprocessor01.py", line 798, in create_test_data
    intrinsic = numpy.array(self.model_configs['intrinsic'])
KeyError: 'intrinsic'

Please look into this.