Error Locating Target

[ModeratePrawn]

Hello,

I upgraded the trainer and audio diffusion to the latest releases. I am now getting this error when trying to run experiments:

[2022-10-19 09:47:41,538][main][INFO] - Instantiating model <main.module_base.Model>.
Error executing job with overrides: ['exp=base_youtube_l_3.yaml']
Error locating target 'audio_diffusion_pytorch.VDistribution', see chained exception above.
full_key: model.model.diffusion_sigma_distribution

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

I deleted the conda environment and reinstalled all of the requirements from scratch, and I am still getting the above. Any help would be appreciated.

Thanks,
MP

[flavioschneider]

You have to use diffusion_type='vk' with audio_diffusion_pytorch.VKDistribution, I still have to delete those old experiments that are not up to date

[flavioschneider]

The old experiments have been archived and the new updated, you should be able to run the current version.

[ModeratePrawn]

Seems to be working now! Thank you!

[2022-10-19 12:41:18,081][main][INFO] - Logging hyperparameters!
[2022-10-19 12:41:18,122][main][INFO] - Starting training.
┏━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┓
┃ ┃ Name ┃ Type ┃ Params ┃
┡━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━┩
│ 0 │ model │ AudioDiffusionModel │ 640 M │
│ 1 │ model.unet │ UNet1d │ 640 M │
│ 2 │ model.diffusion │ VDiffusion │ 640 M │
│ 3 │ model_ema │ EMA │ 1.3 B │
│ 4 │ model_ema.ema_model │ AudioDiffusionModel │ 640 M │
└───┴─────────────────────┴─────────────────────┴────────┘
Trainable params: 640 M
Non-trainable params: 640 M
Total params: 1.3 B
Total estimated model params size (MB): 5.1 K