pytti-tools / pytti-core

https://pytti-tools.github.io/pytti-book/intro.html
MIT License
79 stars 23 forks source link

Error in colab beta 5. ConfigAttributeError: Missing key use_tensorboard #127

Closed randywreed closed 2 years ago

randywreed commented 2 years ago

Running Beta 5 in colab. GPU p100. Data preceeding error:

2022-04-10 19:01:39.180 | DEBUG    | pytti.workhorse:_main:179 - {'scenes': 'A animated scene of the eiffel tower on top of the roman colloseum', 'scene_prefix': 'cartoon | animation', 'scene_suffix': '', 'interpolation_steps': 0, 'steps_per_scene': 60100, 'direct_image_prompts': '', 'init_image': '', 'direct_init_weight': '', 'semantic_init_weight': '', 'image_model': 'Limited Palette', 'width': 60, 'height': 60, 'pixel_size': 1, 'smoothing_weight': 0.02, 'vqgan_model': 'sflckr', 'random_initial_palette': False, 'palette_size': 6, 'palettes': 9, 'gamma': 1, 'hdr_weight': 0.01, 'palette_normalization_weight': 0.2, 'show_palette': False, 'target_palette': '', 'lock_palette': False, 'animation_mode': 'off', 'sampling_mode': 'bicubic', 'infill_mode': 'wrap', 'pre_animation_steps': 100, 'steps_per_frame': 50, 'frames_per_second': 30, 'direct_stabilization_weight': '', 'semantic_stabilization_weight': '', 'depth_stabilization_weight': '', 'edge_stabilization_weight': '', 'flow_stabilization_weight': '', 'video_path': '', 'frame_stride': 1, 'reencode_each_frame': True, 'flow_long_term_samples': 1, 'translate_x': '-1700*sin(radians(1.5))', 'translate_y': '0', 'translate_z_3d': '(50+10*t)*sin(t/10*pi)**2', 'rotate_3d': '[cos(radians(1.5)), 0, -sin(radians(1.5))/sqrt(2), sin(radians(1.5))/sqrt(2)]', 'rotate_2d': '5', 'zoom_x_2d': '0', 'zoom_y_2d': '0', 'lock_camera': True, 'field_of_view': 60, 'near_plane': 1, 'far_plane': 10000, 'file_namespace': 'colloseum_avatar', 'allow_overwrite': False, 'display_every': 50, 'clear_every': 0, 'display_scale': 1, 'save_every': 50, 'backups': 5, 'show_graphs': False, 'approximate_vram_usage': False, 'ViTB32': True, 'ViTB16': True, 'RN50': False, 'RN50x4': False, 'ViTL14': False, 'RN101': False, 'RN50x16': False, 'RN50x64': False, 'learning_rate': None, 'reset_lr_each_frame': True, 'seed': -2526010157354800381, 'cutouts': 40, 'cut_pow': 2, 'cutout_border': 0.25, 'gradient_accumulation_steps': 1, 'border_mode': 'clamp', 'models_parent_dir': '.'}
2022-04-10 19:01:39.186 | DEBUG    | pytti.workhorse:_main:180 - {'scenes': 'A animated scene of the eiffel tower on top of the roman colloseum', 'scene_prefix': 'cartoon | animation', 'scene_suffix': '', 'interpolation_steps': 0, 'steps_per_scene': 60100, 'direct_image_prompts': '', 'init_image': '', 'direct_init_weight': '', 'semantic_init_weight': '', 'image_model': 'Limited Palette', 'width': 60, 'height': 60, 'pixel_size': 1, 'smoothing_weight': 0.02, 'vqgan_model': 'sflckr', 'random_initial_palette': False, 'palette_size': 6, 'palettes': 9, 'gamma': 1, 'hdr_weight': 0.01, 'palette_normalization_weight': 0.2, 'show_palette': False, 'target_palette': '', 'lock_palette': False, 'animation_mode': 'off', 'sampling_mode': 'bicubic', 'infill_mode': 'wrap', 'pre_animation_steps': 100, 'steps_per_frame': 50, 'frames_per_second': 30, 'direct_stabilization_weight': '', 'semantic_stabilization_weight': '', 'depth_stabilization_weight': '', 'edge_stabilization_weight': '', 'flow_stabilization_weight': '', 'video_path': '', 'frame_stride': 1, 'reencode_each_frame': True, 'flow_long_term_samples': 1, 'translate_x': '-1700*sin(radians(1.5))', 'translate_y': '0', 'translate_z_3d': '(50+10*t)*sin(t/10*pi)**2', 'rotate_3d': '[cos(radians(1.5)), 0, -sin(radians(1.5))/sqrt(2), sin(radians(1.5))/sqrt(2)]', 'rotate_2d': '5', 'zoom_x_2d': '0', 'zoom_y_2d': '0', 'lock_camera': True, 'field_of_view': 60, 'near_plane': 1, 'far_plane': 10000, 'file_namespace': 'colloseum_avatar', 'allow_overwrite': False, 'display_every': 50, 'clear_every': 0, 'display_scale': 1, 'save_every': 50, 'backups': 5, 'show_graphs': False, 'approximate_vram_usage': False, 'ViTB32': True, 'ViTB16': True, 'RN50': False, 'RN50x4': False, 'ViTL14': False, 'RN101': False, 'RN50x16': False, 'RN50x64': False, 'learning_rate': None, 'reset_lr_each_frame': True, 'seed': -2526010157354800381, 'cutouts': 40, 'cut_pow': 2, 'cutout_border': 0.25, 'gradient_accumulation_steps': 1, 'border_mode': 'clamp', 'models_parent_dir': '.'}

Error traceback:

ConfigAttributeError                      Traceback (most recent call last)
[<ipython-input-20-b83fac8072d0>](https://localhost:8080/#) in <module>()
      5 
      6 # function wraps step 2.3 of the original p5 notebook
----> 7 render_frames(cfg)

8 frames
[/usr/local/lib/python3.7/dist-packages/omegaconf/dictconfig.py](https://localhost:8080/#) in _get_node(self, key, validate_access, throw_on_missing_value, throw_on_missing_key)
    468         if value is None:
    469             if throw_on_missing_key:
--> 470                 raise ConfigKeyError(f"Missing key {key}")
    471         elif throw_on_missing_value and value._is_missing():
    472             raise MissingMandatoryValue("Missing mandatory value: $KEY")

ConfigAttributeError: Missing key use_tensorboard
    full_key: use_tensorboard
    object_type=dict
dmarx commented 2 years ago

just to be concrete: could you add a link to the notebook you were using?

randywreed commented 2 years ago

https://colab.research.google.com/drive/1pNvlEvNObTxMawWftGnhFcFi0P1deqFn?usp=sharing

dmarx commented 2 years ago

looks like you were using an older version of the notebook, which broke because of a new feature I added in an unfortunately backwards-incompatible manner. I'll try to keep backwards compatibility in mind moving forward. This URL will always take you to the latest version of the notebook (the URL is constructed to pull the latest notebook directly from github): https://colab.research.google.com/github/pytti-tools/pytti-notebook/blob/main/pyttitools-PYTTI.ipynb