Watch Question
Use Your Own Images Video - Step 17
Related to: AI Unlimited
Date: 29/01/2023 19:06
User: Tony Dunne
Awards:
User: Tony Dunne
Awards:
Hi Jorge,
I've been struggling with the training and have made lots of false starts, going back to the beginning several times.
My latest attempt got me to Step 17, after I loaded the photos of myself to experiment with.
Unfortunately I got the following error message:
The following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes` was set to a value of `1`
`--num_machines` was set to a value of `1`
`--mixed_precision` was set to a value of `'no'`
`--num_cpu_threads_per_process` was set to `1` to improve out-of-box performance
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Traceback (most recent call last):
File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 24, in
from transformers import CLIPTextModel, CLIPTokenizer
ModuleNotFoundError: No module named 'transformers'
Traceback (most recent call last):
File "/usr/local/bin/accelerate", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/accelerate_cli.py", line 43, in main
args.func(args)
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/launch.py", line 837, in launch_command
simple_launcher(args)
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/launch.py", line 354, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--save_starting_step=500', '--save_n_steps=0', '--train_text_encoder', '--pretrained_model_name_or_path=/content/stable-diffusion-v1-5', '--instance_data_dir=/content/data/lalalal2', '--class_data_dir=/content/regularization_images/person_ddim', '--output_dir=/content/models/lalalal2', '--with_prior_preservation', '--prior_loss_weight=1.0', '--instance_prompt=photo of lalalal2 person', '--class_prompt=a photo of a person, ultra detailed', '--seed=75576', '--resolution=512', '--mixed_precision=fp16', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--gradient_checkpointing', '--use_8bit_adam', '--learning_rate=1e-6', '--lr_scheduler=constant', '--lr_warmup_steps=0', '--center_crop', '--max_train_steps=1600', '--num_class_images=500']' returned non-zero exit status 1.
Something went wrong
I'm afraid this means nothing to me. Could you explain? Should I delete everything and try again, or is there a work around that's less trouble?
I'm no computer programmer and need help in plain language so I can make sense of what needs to be done.
Your help would be most appreciated.
Many thanks.
Tony Dunne
I've been struggling with the training and have made lots of false starts, going back to the beginning several times.
My latest attempt got me to Step 17, after I loaded the photos of myself to experiment with.
Unfortunately I got the following error message:
The following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes` was set to a value of `1`
`--num_machines` was set to a value of `1`
`--mixed_precision` was set to a value of `'no'`
`--num_cpu_threads_per_process` was set to `1` to improve out-of-box performance
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Traceback (most recent call last):
File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 24, in
from transformers import CLIPTextModel, CLIPTokenizer
ModuleNotFoundError: No module named 'transformers'
Traceback (most recent call last):
File "/usr/local/bin/accelerate", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/accelerate_cli.py", line 43, in main
args.func(args)
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/launch.py", line 837, in launch_command
simple_launcher(args)
File "/usr/local/lib/python3.8/dist-packages/accelerate/commands/launch.py", line 354, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--save_starting_step=500', '--save_n_steps=0', '--train_text_encoder', '--pretrained_model_name_or_path=/content/stable-diffusion-v1-5', '--instance_data_dir=/content/data/lalalal2', '--class_data_dir=/content/regularization_images/person_ddim', '--output_dir=/content/models/lalalal2', '--with_prior_preservation', '--prior_loss_weight=1.0', '--instance_prompt=photo of lalalal2 person', '--class_prompt=a photo of a person, ultra detailed', '--seed=75576', '--resolution=512', '--mixed_precision=fp16', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--gradient_checkpointing', '--use_8bit_adam', '--learning_rate=1e-6', '--lr_scheduler=constant', '--lr_warmup_steps=0', '--center_crop', '--max_train_steps=1600', '--num_class_images=500']' returned non-zero exit status 1.
Something went wrong
I'm afraid this means nothing to me. Could you explain? Should I delete everything and try again, or is there a work around that's less trouble?
I'm no computer programmer and need help in plain language so I can make sense of what needs to be done.
Your help would be most appreciated.
Many thanks.
Tony Dunne
Answers
Date: 16/01/2023 16:57
User: Jorge Vila
Awards:
User: Jorge Vila
Awards:
No problem, you don't need to understand, it's just that Golab is updated frequently and some stuff there must be updated.
Can yo let me know the Colab link you are using?
Is the one that's in the training?
Thanks
Jorge
Can yo let me know the Colab link you are using?
Is the one that's in the training?
Thanks
Jorge
Date: 16/01/2023 17:44
User: Tony Dunne
Awards:
User: Tony Dunne
Awards:
Hi Jorge,
Yes, the link I used was the one in the training.
Hope this helps.
Tony
Yes, the link I used was the one in the training.
Hope this helps.
Tony
Date: 16/01/2023 17:53
User: Jorge Vila
Awards:
User: Jorge Vila
Awards:
Ok, I 'll check everything and will come back to you
Date: 29/01/2023 19:06
User: Jorge Vila
Awards:
User: Jorge Vila
Awards:
Respuesta Aprobada
Just updated the Create your own images Colab, please access again and try to retrain!
Let me know!
Jorge
Let me know!
Jorge