knoopx
commented
1 year ago not a bug, you are using the upstream example script on diffusers 0.12, thats why there's a check_min_version("0.13.0.dev0"). install diffusers from main branch or use the 0.12.1 revision of the script (https://github.com/huggingface/diffusers/blob/v0.12.1/examples/dreambooth/train_dreambooth_lora.py)
treasuraid
Describe the bug
I followed the readme, but it showed
AttributeError: 'FrozenDict' object has no attribute 'scaling_factor'
what is wrong with it..?
Reproduction
"""Fine-tuning script for Stable Diffusion for text2image with support for LoRA.""" """Copy from diffuser and vessl logger"""
import argparse import logging import math import os import random from pathlib import Path from typing import Optional
import numpy as np import torch import torch.nn.functional as F import torch.utils.checkpoint
import datasets import diffusers import transformers from accelerate import Accelerator from accelerate.logging import get_logger from accelerate.utils import set_seed from datasets import load_dataset from diffusers import AutoencoderKL, DDPMScheduler, DiffusionPipeline, UNet2DConditionModel from diffusers.loaders import AttnProcsLayers from diffusers.models.cross_attention import LoRACrossAttnProcessor from diffusers.optimization import get_scheduler from diffusers.utils import check_min_version, is_wandb_available from diffusers.utils.import_utils import is_xformers_available from huggingface_hub import HfFolder, Repository, create_repo, whoami from torchvision import transforms from tqdm.auto import tqdm from transformers import CLIPTextModel, CLIPTokenizer
Will error if the minimal version of diffusers is not installed. Remove at your own risks.
check_min_version("0.13.0.dev0")
logger = get_logger(name, log_level="INFO")
def save_model_card(repo_name, images=None, base_model=str, dataset_name=str, repo_folder=None): img_str = "" for i, image in enumerate(images): image.save(os.path.join(repofolder, f"image{i}.png")) imgstr += f"\n"
license: creativeml-openrail-m base_model: {base_model} tags:
lora inference: true
""" model_card = f"""
LoRA text2image fine-tuning - {repo_name}
These are LoRA adaption weights for {base_model}. The weights were fine-tuned on the {dataset_name} dataset. You can find some example images in the following. \n {img_str} """ with open(os.path.join(repo_folder, "README.md"), "w") as f: f.write(yaml + model_card)
def parse_args(): parser = argparse.ArgumentParser(description="Simple example of a training script.") parser.add_argument( "--pretrained_model_name_or_path", type=str, default=None, required=True, help="Path to pretrained model or model identifier from huggingface.co/models.", ) parser.add_argument( "--revision", type=str, default=None, required=False, help="Revision of pretrained model identifier from huggingface.co/models.", ) parser.add_argument( "--dataset_name", type=str, default="lambdalabs/pokemon-blip-captions", help=( "The name of the Dataset (from the HuggingFace hub) to train on (could be your own, possibly private," " dataset). It can also be a path pointing to a local copy of a dataset in your filesystem," " or to a folder containing files that ๐ค Datasets can understand." ), ) parser.add_argument( "--dataset_config_name", type=str, default=None, help="The config of the Dataset, leave as None if there's only one config.", ) parser.add_argument( "--train_data_dir", type=str, default=None, help=( "A folder containing the training data. Folder contents must follow the structure described in" " https://huggingface.co/docs/datasets/image_dataset#imagefolder. In particular, a
metadata.jsonlfile" " must exist to provide the captions for the images. Ignored ifdataset_nameis specified." ), ) parser.add_argument( "--image_column", type=str, default="image", help="The column of the dataset containing an image." ) parser.add_argument( "--caption_column", type=str, default="text", help="The column of the dataset containing a caption or a list of captions.", ) parser.add_argument( "--validation_prompt", type=str, default=None, help="A prompt that is sampled during training for inference." ) parser.add_argument( "--num_validation_images", type=int, default=4, help="Number of images that should be generated during validation withvalidation_prompt.", ) parser.add_argument( "--validation_epochs", type=int, default=1, help=( "Run fine-tuning validation every X epochs. The validation process consists of running the prompt" "args.validation_promptmultiple times:args.num_validation_images." ), ) parser.add_argument( "--max_train_samples", type=int, default=None, help=( "For debugging purposes or quicker training, truncate the number of training examples to this " "value if set." ), ) parser.add_argument( "--output_dir", type=str, default="sd-model-finetuned-lora", help="The output directory where the model predictions and checkpoints will be written.", ) parser.add_argument( "--cache_dir", type=str, default=None, help="The directory where the downloaded models and datasets will be stored.", ) parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.") parser.add_argument( "--resolution", type=int, default=512, help=( "The resolution for input images, all the images in the train/validation dataset will be resized to this" " resolution" ), ) parser.add_argument( "--center_crop", default=False, action="store_true", help=( "Whether to center crop the input images to the resolution. If not set, the images will be randomly" " cropped. The images will be resized to the resolution first before cropping." ), ) parser.add_argument( "--random_flip", action="store_true", help="whether to randomly flip images horizontally", ) parser.add_argument( "--train_batch_size", type=int, default=16, help="Batch size (per device) for the training dataloader." ) parser.add_argument("--num_train_epochs", type=int, default=100) parser.add_argument( "--max_train_steps", type=int, default=None, help="Total number of training steps to perform. If provided, overrides num_train_epochs.", ) parser.add_argument( "--gradient_accumulation_steps", type=int, default=1, help="Number of updates steps to accumulate before performing a backward/update pass.", ) parser.add_argument( "--gradient_checkpointing", action="store_true", help="Whether or not to use gradient checkpointing to save memory at the expense of slower backward pass.", ) parser.add_argument( "--learning_rate", type=float, default=1e-4, help="Initial learning rate (after the potential warmup period) to use.", ) parser.add_argument( "--scale_lr", action="store_true", default=False, help="Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.", ) parser.add_argument( "--lr_scheduler", type=str, default="constant", help=( 'The scheduler type to use. Choose between ["linear", "cosine", "cosine_with_restarts", "polynomial",' ' "constant", "constant_with_warmup"]' ), ) parser.add_argument( "--lr_warmup_steps", type=int, default=500, help="Number of steps for the warmup in the lr scheduler." ) parser.add_argument( "--use_8bit_adam", action="store_true", help="Whether or not to use 8-bit Adam from bitsandbytes." ) parser.add_argument( "--allow_tf32", action="store_true", help=( "Whether or not to allow TF32 on Ampere GPUs. Can be used to speed up training. For more information, see" " https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices" ), ) parser.add_argument( "--dataloader_num_workers", type=int, default=0, help=( "Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process." ), ) parser.add_argument("--adam_beta1", type=float, default=0.9, help="The beta1 parameter for the Adam optimizer.") parser.add_argument("--adam_beta2", type=float, default=0.999, help="The beta2 parameter for the Adam optimizer.") parser.add_argument("--adam_weight_decay", type=float, default=1e-2, help="Weight decay to use.") parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer") parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.") parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.") parser.add_argument("--hub_token", type=str, default=None, help="The token to use to push to the Model Hub.") parser.add_argument( "--hub_model_id", type=str, default=None, help="The name of the repository to keep in sync with the localoutput_dir.", ) parser.add_argument( "--logging_dir", type=str, default="logs", help=( "TensorBoard log directory. Will default to" " output_dir/runs/CURRENT_DATETIME_HOSTNAME." ), ) parser.add_argument( "--mixed_precision", type=str, default=None, choices=["no", "fp16", "bf16"], help=( "Whether to use mixed precision. Choose between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >=" " 1.10.and an Nvidia Ampere GPU. Default to the value of accelerate config of the current system or the" " flag passed with theaccelerate.launchcommand. Use this argument to override the accelerate config." ), ) parser.add_argument( "--report_to", type=str, default="tensorboard", help=( 'The integration to report the results and logs to. Supported platforms are"tensorboard"' ' (default),"wandb"and"comet_ml". Use"all"to report to all integrations.' ), ) parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank") parser.add_argument( "--checkpointing_steps", type=int, default=500, help=( "Save a checkpoint of the training state every X updates. These checkpoints are only suitable for resuming" " training using--resume_from_checkpoint." ), ) parser.add_argument( "--resume_from_checkpoint", type=str, default=None, help=( "Whether training should be resumed from a previous checkpoint. Use a path saved by" '--checkpointing_steps, or"latest"to automatically select the last available checkpoint.' ), ) parser.add_argument( "--enable_xformers_memory_efficient_attention", action="store_true", help="Whether or not to use xformers." )์ผ๋ถ ํน์ default ๊ฐ๋ค์ ๋ฐ๊พธ๋ฉด ์ข์ ๋ฏ
log with wandb ใ ใ
def get_full_repo_name(model_id: str, organization: Optional[str] = None, token: Optional[str] = None): if token is None: token = HfFolder.get_token() if organization is None: username = whoami(token)["name"] return f"{username}/{model_id}" else: return f"{organization}/{model_id}"
DATASET_NAME_MAPPING = { "lambdalabs/pokemon-blip-captions": ("image", "text"), "input/my_own_datasets" : ("image", "text")
jin - ์ด๋ฐ์์ผ๋ก ๋ฐ์ดํฐ๋ฅผ ๋ฃ์ด์ผ๋๋๊ฑธ๋ก
}
def main(): args = parse_args()
if name == "main": main()
Logs
No response
System Info
diffusersversion: 0.12.1