You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
trying to run the colab code in linux but getting error
first:
libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
WARNING:root:WARNING: libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
Need to compile C++ extensions to get sparse attention suport. Please run python setup.py build develop
later:
RuntimeError: No such operator xformers::efficient_attention_forward_generic - did you forget to build xformers with python setup.py develop?
what am I doing wrong?
accelerate launch train_dreambooth.py
--pretrained_model_name_or_path=$MODEL_NAME
--instance_data_dir=$INSTANCE_DIR
--class_data_dir=$CLASS_DIR
--output_dir=$OUTPUT_DIR
--with_prior_preservation --prior_loss_weight=1.0
--instance_prompt="photo of sapirmo {CLASS_NAME}"
--class_prompt="photo of a {CLASS_NAME}"
--seed=1337
--resolution=512
--train_batch_size=1
--mixed_precision="fp16"
--use_8bit_adam
--gradient_accumulation_steps=1
--learning_rate=5e-6
--lr_scheduler="constant"
--lr_warmup_steps=0
--num_class_images=50
--sample_batch_size=4
--max_train_steps=1000
--gradient_checkpointing
Logs
bash train_booth.sh
libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
WARNING:root:WARNING: libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
Need to compile C++ extensions to get sparse attention suport. Please run python setup.py build develop
Fetching 16 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16/16 [00:00<00:00, 32832.13it/s]
The config attributes {'feature_extractor': ['transformers', 'CLIPFeatureExtractor'], 'safety_checker': ['stable_diffusion', 'StableDiffusionSafetyChecker']} were passed to StableDiffusionPipeline, but are not expected and will be ignored. Please verify your model_index.json configuration file.
Generating class images: 0%|| 0/13 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train_dreambooth.py", line 638, in<module>main()
File "train_dreambooth.py", line 381, in main
images = pipeline(example["prompt"]).images
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py", line 312, in __call__
noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/models/unet_2d_condition.py", line 286, in forward
encoder_hidden_states=encoder_hidden_states,
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/models/unet_blocks.py", line 565, in forward
hidden_states = attn(hidden_states, context=encoder_hidden_states)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/models/attention.py", line 154, in forward
hidden_states = block(hidden_states, context=context)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/models/attention.py", line 203, in forward
hidden_states = self.attn1(self.norm1(hidden_states)) + hidden_states
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/diffusers/models/attention.py", line 276, in forward
hidden_states = xformers.ops.memory_efficient_attention(query, key, value)
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/xformers/ops.py", line 575, in memory_efficient_attention
query=query, key=key, value=value, attn_bias=attn_bias, p=p
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/xformers/ops.py", line 196, in forward_no_grad
causal=isinstance(attn_bias, LowerTriangularMask),
File "/home/galgozes/anaconda3/envs/dreambooth/lib/python3.7/site-packages/xformers/ops.py", line 46, in no_such_operator
f"No such operator xformers::{name} - did you forget to build xformers with `python setup.py develop`?"
RuntimeError: No such operator xformers::efficient_attention_forward_generic - did you forget to build xformers with `python setup.py develop`?
Describe the bug
trying to run the colab code in linux but getting error
first:
libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
WARNING:root:WARNING: libtorch_cuda_cpp.so: cannot open shared object file: No such file or directory
Need to compile C++ extensions to get sparse attention suport. Please run python setup.py build develop
later:
RuntimeError: No such operator xformers::efficient_attention_forward_generic - did you forget to build xformers with
python setup.py develop
?what am I doing wrong?
Reproduction
created a new conda env and ran the lines:
pip install -qq git+https://github.com/ShivamShrirao/diffusers
pip install -q -U --pre triton
pip install -q accelerate==0.12.0 transformers ftfy bitsandbytes gradio
pip install https://github.com/metrolobo/xformers_wheels/releases/download/1d31a3ac_various_6/xformers-0.0.14.dev0-cp37-cp37m-linux_x86_64.whl
then ran the code (using bash):
accelerate launch train_dreambooth.py
--pretrained_model_name_or_path=$MODEL_NAME
--instance_data_dir=$INSTANCE_DIR
--class_data_dir=$CLASS_DIR
--output_dir=$OUTPUT_DIR
--with_prior_preservation --prior_loss_weight=1.0
--instance_prompt="photo of sapirmo {CLASS_NAME}"
--class_prompt="photo of a {CLASS_NAME}"
--seed=1337
--resolution=512
--train_batch_size=1
--mixed_precision="fp16"
--use_8bit_adam
--gradient_accumulation_steps=1
--learning_rate=5e-6
--lr_scheduler="constant"
--lr_warmup_steps=0
--num_class_images=50
--sample_batch_size=4
--max_train_steps=1000
--gradient_checkpointing
Logs
System Info
diffusers
version: 0.5.0.dev0The text was updated successfully, but these errors were encountered: