Skip to content

GitLab

Commit e532679c authored by oahzxl's avatar oahzxl
Browse files

Merge branch 'main' of https://github.com/oahzxl/ColossalAI into chunk

parents c1492e50 7d5640b9
Hide whitespace changes
Inline Side-by-side
Showing with 1753 additions and 0 deletions
examples/README.md 0 → 100644
View file @ e532679c
## Examples folder document
## Table of Contents
<ul>
<li><a href="#Example-folder-description">Example folder description</a> </li>
<li><a href="#Integrate-Your-Example-With-System-Testing">Integrate Your Example With System Testing</a> </li>
</ul>
## Example folder description
This folder provides several examples using colossalai. The images folder includes model like diffusion, dreambooth and vit. The language folder includes gpt, opt, palm and roberta. The tutorial folder is for concept illustration, such as auto-parallel, hybrid-parallel and so on.
## Integrate Your Example With System Testing
For example code contributor, to meet the expectation and test your code automatically using github workflow function, here are several steps:
- (must) Have a test_ci.sh file in the folder like shown below in 'File Structure Chart'
- The dataset should be located in the company's machine and can be announced using environment variable and thus no need for a separate terminal command.
- The model parameters should be small to allow fast testing.
- File Structure Chart
└─examples
└─images
└─vit
└─requirements.txt
└─test_ci.sh
examples/images/diffusion/LICENSE 0 → 100644
View file @ e532679c
Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
CreativeML Open RAIL-M
dated August 22, 2022
Section I: PREAMBLE
Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from AI or ML technologies as a tool for content creation.
Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the Model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for art and content generation.
Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this License aims to strike a balance between both in order to enable responsible open-science in the field of AI.
This License governs the use of the model (and its derivatives) and is informed by the model card associated with the model.
NOW THEREFORE, You and Licensor agree as follows:
1. Definitions
- "License" means the terms and conditions for use, reproduction, and Distribution as defined in this document.
- "Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
- "Output" means the results of operating a Model as embodied in informational content resulting therefrom.
- "Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
- "Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
- "Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any.
- "Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
- "Licensor" means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model.
- "You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
- "Third Parties" means individuals or legal entities that are not under common control with Licensor or You.
- "Contribution" means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
- "Contributor" means Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
Section II: INTELLECTUAL PROPERTY RIGHTS
Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III.
2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Model to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Work shall terminate as of the date such litigation is asserted or filed.
Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions:
Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material.
You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License;
You must cause any modified files to carry prominent notices stating that You changed the files;
You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model.
You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5).
6. The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
Section IV: OTHER PROVISIONS
7. Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License, update the Model through electronic means, or modify the Output of the Model based on updates. You shall undertake reasonable efforts to use the latest version of the Model.
8. Trademarks and related. Nothing in this License permits You to make use of Licensors’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensors.
9. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
10. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Model and the Complementary Material (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
11. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
12. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
END OF TERMS AND CONDITIONS
Attachment A
Use Restrictions
You agree not to use the Model or Derivatives of the Model:
- In any way that violates any applicable national, federal, state, local or international law or regulation;
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
- To generate or disseminate personal identifiable information that can be used to harm an individual;
- To defame, disparage or otherwise harass others;
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
- To provide medical advice and medical results interpretation;
- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
examples/images/diffusion/README.md 0 → 100644
View file @ e532679c
# ColoDiffusion: Stable Diffusion with Colossal-AI
Acceleration of AIGC (AI-Generated Content) models such as [Stable Diffusion v1](https://github.com/CompVis/stable-diffusion) and [Stable Diffusion v2](https://github.com/Stability-AI/stablediffusion).
<p id="diffusion_train" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/Stable%20Diffusion%20v2.png" width=800/>
</p>
- [Training](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion): Reduce Stable Diffusion memory consumption by up to 5.6x and hardware cost by up to 46x (from A100 to RTX3060).
<p id="diffusion_demo" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/DreamBooth.png" width=800/>
</p>
- [DreamBooth Fine-tuning](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/dreambooth): Personalize your model using just 3-5 images of the desired subject.
<p id="inference" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/Stable%20Diffusion%20Inference.jpg" width=800/>
</p>
- [Inference](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion): Reduce inference GPU memory consumption by 2.5x.
More details can be found in our [blog of Stable Diffusion v1](https://www.hpc-ai.tech/blog/diffusion-pretraining-and-hardware-fine-tuning-can-be-almost-7x-cheaper) and [blog of Stable Diffusion v2](https://www.hpc-ai.tech/blog/colossal-ai-0-2-0).
## Installation
### Option #1: install from source
#### Step 1: Requirements
A suitable [conda](https://conda.io/) environment named `ldm` can be created
and activated with:
```
conda env create -f environment.yaml
conda activate ldm
```
You can also update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running
```
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch
pip install transformers==4.19.2 diffusers invisible-watermark
pip install -e .
```
##### Step 2: install lightning
Install Lightning version later than 2022.01.04. We suggest you install lightning from source.
https://github.com/Lightning-AI/lightning.git
##### Step 3:Install [Colossal-AI](https://colossalai.org/download/) From Our Official Website
For example, you can install v0.1.12 from our official website.
```
pip install colossalai==0.1.12+torch1.12cu11.3 -f https://release.colossalai.org
```
### Option #2: Use Docker
To use the stable diffusion Docker image, you can either build using the provided the [Dockerfile](./docker/Dockerfile) or pull a Docker image from our Docker hub.
```
# 1. build from dockerfile
cd docker
docker build -t hpcaitech/diffusion:0.2.0 .
# 2. pull from our docker hub
docker pull hpcaitech/diffusion:0.2.0
```
Once you have the image ready, you can launch the image with the following command:
```bash
########################
# On Your Host Machine #
########################
# make sure you start your image in the repository root directory
cd Colossal-AI
# run the docker container
docker run --rm \
-it --gpus all \
-v $PWD:/workspace \
-v <your-data-dir>:/data/scratch \
-v <hf-cache-dir>:/root/.cache/huggingface \
hpcaitech/diffusion:0.2.0 \
/bin/bash
########################
# Insider Container #
########################
# Once you have entered the docker container, go to the stable diffusion directory for training
cd examples/images/diffusion/
# start training with colossalai
bash train_colossalai.sh
```
It is important for you to configure your volume mapping in order to get the best training experience.
1. **Mandatory**, mount your prepared data to `/data/scratch` via `-v <your-data-dir>:/data/scratch`, where you need to replace `<your-data-dir>` with the actual data path on your machine.
2. **Recommended**, store the downloaded model weights to your host machine instead of the container directory via `-v <hf-cache-dir>:/root/.cache/huggingface`, where you need to repliace the `<hf-cache-dir>` with the actual path. In this way, you don't have to repeatedly download the pretrained weights for every `docker run`.
3. **Optional**, if you encounter any problem stating that shared memory is insufficient inside container, please add `-v /dev/shm:/dev/shm` to your `docker run` command.
## Download the model checkpoint from pretrained
### stable-diffusion-v1-4
Our default model config use the weight from [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4?text=A+mecha+robot+in+a+favela+in+expressionist+style)
```
git lfs install
git clone https://huggingface.co/CompVis/stable-diffusion-v1-4
```
### stable-diffusion-v1-5 from runway
If you want to useed the Last [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) wiegh from runwayml
```
git lfs install
git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
```
## Dataset
The dataSet is from [LAION-5B](https://laion.ai/blog/laion-5b/), the subset of [LAION](https://laion.ai/),
you should the change the `data.file_path` in the `config/train_colossalai.yaml`
## Training
We provide the script `train_colossalai.sh` to run the training task with colossalai,
and can also use `train_ddp.sh` to run the training task with ddp to compare.
In `train_colossalai.sh` the main command is:
```
python main.py --logdir /tmp/ -t -b configs/train_colossalai.yaml
```
- you can change the `--logdir` to decide where to save the log information and the last checkpoint.
### Training config
You can change the trainging config in the yaml file
- devices: device number used for training, default 8
- max_epochs: max training epochs, default 2
- precision: the precision type used in training, default 16 (fp16), you must use fp16 if you want to apply colossalai
- more information about the configuration of ColossalAIStrategy can be found [here](https://pytorch-lightning.readthedocs.io/en/latest/advanced/model_parallel.html#colossal-ai)
## Finetune Example
### Training on Teyvat Datasets
We provide the finetuning example on [Teyvat](https://huggingface.co/datasets/Fazzie/Teyvat) dataset, which is create by BLIP generated captions.
You can run by config `configs/Teyvat/train_colossalai_teyvat.yaml`
```
python main.py --logdir /tmp/ -t -b configs/Teyvat/train_colossalai_teyvat.yaml
```
## Inference
you can get yout training last.ckpt and train config.yaml in your `--logdir`, and run by
```
python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
--outdir ./output \
--config path/to/logdir/checkpoints/last.ckpt \
--ckpt /path/to/logdir/configs/project.yaml \
```
```commandline
usage: txt2img.py [-h] [--prompt [PROMPT]] [--outdir [OUTDIR]] [--skip_grid] [--skip_save] [--ddim_steps DDIM_STEPS] [--plms] [--laion400m] [--fixed_code] [--ddim_eta DDIM_ETA]
[--n_iter N_ITER] [--H H] [--W W] [--C C] [--f F] [--n_samples N_SAMPLES] [--n_rows N_ROWS] [--scale SCALE] [--from-file FROM_FILE] [--config CONFIG] [--ckpt CKPT]
[--seed SEED] [--precision {full,autocast}]
optional arguments:
-h, --help show this help message and exit
--prompt [PROMPT] the prompt to render
--outdir [OUTDIR] dir to write results to
--skip_grid do not save a grid, only individual samples. Helpful when evaluating lots of samples
--skip_save do not save individual samples. For speed measurements.
--ddim_steps DDIM_STEPS
number of ddim sampling steps
--plms use plms sampling
--laion400m uses the LAION400M model
--fixed_code if enabled, uses the same starting code across samples
--ddim_eta DDIM_ETA ddim eta (eta=0.0 corresponds to deterministic sampling
--n_iter N_ITER sample this often
--H H image height, in pixel space
--W W image width, in pixel space
--C C latent channels
--f F downsampling factor
--n_samples N_SAMPLES
how many samples to produce for each given prompt. A.k.a. batch size
--n_rows N_ROWS rows in the grid (default: n_samples)
--scale SCALE unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))
--from-file FROM_FILE
if specified, load prompts from this file
--config CONFIG path to config which constructs model
--ckpt CKPT path to checkpoint of model
--seed SEED the seed (for reproducible sampling)
--use_int8 whether to use quantization method
--precision {full,autocast}
evaluate at this precision
```
## Comments
- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)
, [lucidrains](https://github.com/lucidrains/denoising-diffusion-pytorch),
[Stable Diffusion](https://github.com/CompVis/stable-diffusion), [Lightning](https://github.com/Lightning-AI/lightning) and [Hugging Face](https://huggingface.co/CompVis/stable-diffusion).
Thanks for open-sourcing!
- The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories).
- The implementation of [flash attention](https://github.com/HazyResearch/flash-attention) is from [HazyResearch](https://github.com/HazyResearch).
## BibTeX
```
@article{bian2021colossal,
title={Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training},
author={Bian, Zhengda and Liu, Hongxin and Wang, Boxiang and Huang, Haichen and Li, Yongbin and Wang, Chuanrui and Cui, Fan and You, Yang},
journal={arXiv preprint arXiv:2110.14883},
year={2021}
}
@misc{rombach2021highresolution,
title={High-Resolution Image Synthesis with Latent Diffusion Models},
author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
year={2021},
eprint={2112.10752},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@article{dao2022flashattention,
title={FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness},
author={Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and R{\'e}, Christopher},
journal={arXiv preprint arXiv:2205.14135},
year={2022}
}
```
examples/images/diffusion/configs/Inference/v2-inference-v.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
examples/images/diffusion/configs/Inference/v2-inference.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
examples/images/diffusion/configs/Inference/v2-inpainting-inference.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 5.0e-05
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: hybrid
scale_factor: 0.18215
monitor: val/loss_simple_ema
finetune_keys: null
use_ema: False
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
image_size: 32 # unused
in_channels: 9
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: [ ]
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: ldm.data.laion.WebDataModuleFromConfig
params:
tar_base: null # for concat as in LAION-A
p_unsafe_threshold: 0.1
filter_word_list: "data/filters.yaml"
max_pwatermark: 0.45
batch_size: 8
num_workers: 6
multinode: True
min_size: 512
train:
shards:
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -" #{00000-94333}.tar"
shuffle: 10000
image_key: jpg
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
interpolation: 3
- target: torchvision.transforms.RandomCrop
params:
size: 512
postprocess:
target: ldm.data.laion.AddMask
params:
mode: "512train-large"
p_drop: 0.25
# NOTE use enough shards to avoid empty validation loops in workers
validation:
shards:
- "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
shuffle: 0
image_key: jpg
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
interpolation: 3
- target: torchvision.transforms.CenterCrop
params:
size: 512
postprocess:
target: ldm.data.laion.AddMask
params:
mode: "512train-large"
p_drop: 0.25
lightning:
find_unused_parameters: True
modelcheckpoint:
params:
every_n_train_steps: 5000
callbacks:
metrics_over_trainsteps_checkpoint:
params:
every_n_train_steps: 10000
image_logger:
target: main.ImageLogger
params:
enable_autocast: False
disabled: False
batch_frequency: 1000
max_images: 4
increase_log_steps: False
log_first_step: False
log_images_kwargs:
use_ema_scope: False
inpaint: False
plot_progressive_rows: False
plot_diffusion_rows: False
N: 4
unconditional_guidance_scale: 5.0
unconditional_guidance_label: [""]
ddim_steps: 50 # todo check these out for depth2img,
ddim_eta: 0.0 # todo check these out for depth2img,
trainer:
benchmark: True
val_check_interval: 5000000
num_sanity_val_steps: 0
accumulate_grad_batches: 1
examples/images/diffusion/configs/Inference/v2-midas-inference.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 5.0e-07
target: ldm.models.diffusion.ddpm.LatentDepth2ImageDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: hybrid
scale_factor: 0.18215
monitor: val/loss_simple_ema
finetune_keys: null
use_ema: False
depth_stage_config:
target: ldm.modules.midas.api.MiDaSInference
params:
model_type: "dpt_hybrid"
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
image_size: 32 # unused
in_channels: 5
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: [ ]
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
examples/images/diffusion/configs/Inference/x4-upscaling.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentUpscaleDiffusion
params:
parameterization: "v"
low_scale_key: "lr"
linear_start: 0.0001
linear_end: 0.02
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 128
channels: 4
cond_stage_trainable: false
conditioning_key: "hybrid-adm"
monitor: val/loss_simple_ema
scale_factor: 0.08333
use_ema: False
low_scale_config:
target: ldm.modules.diffusionmodules.upscaling.ImageConcatWithNoiseAugmentation
params:
noise_schedule_config: # image space
linear_start: 0.0001
linear_end: 0.02
max_noise_level: 350
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
num_classes: 1000 # timesteps for noise conditioning (here constant, just need one)
image_size: 128
in_channels: 7
out_channels: 4
model_channels: 256
attention_resolutions: [ 2,4,8]
num_res_blocks: 2
channel_mult: [ 1, 2, 2, 4]
disable_self_attentions: [True, True, True, False]
disable_middle_self_attn: False
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
use_linear_in_transformer: True
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
ddconfig:
# attn_type: "vanilla-xformers" this model needs efficient attention to be feasible on HR data, also the decoder seems to break in half precision (UNet is fine though)
double_z: True
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult: [ 1,2,4 ] # num_down = len(ch_mult)-1
num_res_blocks: 2
attn_resolutions: [ ]
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
examples/images/diffusion/configs/Teyvat/README.md 0 → 100644
View file @ e532679c
# Dataset Card for Teyvat BLIP captions
Dataset used to train [Teyvat characters text to image model](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion).
BLIP generated captions for characters images from [genshin-impact fandom wiki](https://genshin-impact.fandom.com/wiki/Character#Playable_Characters)and [biligame wiki for genshin impact](https://wiki.biligame.com/ys/%E8%A7%92%E8%89%B2).
For each row the dataset contains `image` and `text` keys. `image` is a varying size PIL png, and `text` is the accompanying text caption. Only a train split is provided.
The `text` include the tag `Teyvat`, `Name`,`Element`, `Weapon`, `Region`, `Model type`, and `Description`, the `Description` is captioned with the [pre-trained BLIP model](https://github.com/salesforce/BLIP).
examples/images/diffusion/configs/Teyvat/train_colossalai_teyvat.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1.e-4 ]
f_min: [ 1.e-10 ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: main.DataModuleFromConfig
params:
batch_size: 16
num_workers: 4
train:
target: ldm.data.teyvat.hf_dataset
params:
path: Fazzie/Teyvat
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
- target: torchvision.transforms.RandomCrop
params:
size: 512
- target: torchvision.transforms.RandomHorizontalFlip
lightning:
trainer:
accelerator: 'gpu'
devices: 2
log_gpu_memory: all
max_epochs: 2
precision: 16
auto_select_gpus: False
strategy:
target: strategies.ColossalAIStrategy
params:
use_chunk: True
enable_distributed_storage: True
placement_policy: cuda
force_outputs_fp32: true
log_every_n_steps: 2
logger: True
default_root_dir: "/tmp/diff_log/"
# profiler: pytorch
logger_config:
wandb:
target: loggers.WandbLogger
params:
name: nowname
save_dir: "/tmp/diff_log/"
offline: opt.debug
id: nowname
examples/images/diffusion/configs/train_colossalai.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1.e-4 ]
f_min: [ 1.e-10 ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: main.DataModuleFromConfig
params:
batch_size: 128
wrap: False
# num_workwers should be 2 * batch_size, and total num less than 1024
# e.g. if use 8 devices, no more than 128
num_workers: 128
train:
target: ldm.data.base.Txt2ImgIterableBaseDataset
params:
file_path: # YOUR DATASET_PATH
world_size: 1
rank: 0
lightning:
trainer:
accelerator: 'gpu'
devices: 8
log_gpu_memory: all
max_epochs: 2
precision: 16
auto_select_gpus: False
strategy:
target: strategies.ColossalAIStrategy
params:
use_chunk: True
enable_distributed_storage: True
placement_policy: cuda
force_outputs_fp32: true
log_every_n_steps: 2
logger: True
default_root_dir: "/tmp/diff_log/"
# profiler: pytorch
logger_config:
wandb:
target: loggers.WandbLogger
params:
name: nowname
save_dir: "/tmp/diff_log/"
offline: opt.debug
id: nowname
examples/images/diffusion/configs/train_colossalai_cifar10.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1.e-4 ]
f_min: [ 1.e-10 ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: main.DataModuleFromConfig
params:
batch_size: 4
num_workers: 4
train:
target: ldm.data.cifar10.hf_dataset
params:
name: cifar10
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
interpolation: 3
- target: torchvision.transforms.RandomCrop
params:
size: 512
- target: torchvision.transforms.RandomHorizontalFlip
lightning:
trainer:
accelerator: 'gpu'
devices: 1
log_gpu_memory: all
max_epochs: 2
precision: 16
auto_select_gpus: False
strategy:
target: strategies.ColossalAIStrategy
params:
use_chunk: True
enable_distributed_storage: True
placement_policy: cuda
force_outputs_fp32: true
log_every_n_steps: 2
logger: True
default_root_dir: "/tmp/diff_log/"
# profiler: pytorch
logger_config:
wandb:
target: loggers.WandbLogger
params:
name: nowname
save_dir: "/tmp/diff_log/"
offline: opt.debug
id: nowname
examples/images/diffusion/configs/train_ddp.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1.e-4 ]
f_min: [ 1.e-10 ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: main.DataModuleFromConfig
params:
batch_size: 128
# num_workwers should be 2 * batch_size, and the total num less than 1024
# e.g. if use 8 devices, no more than 128
num_workers: 128
train:
target: ldm.data.base.Txt2ImgIterableBaseDataset
params:
file_path: # YOUR DATAPATH
world_size: 1
rank: 0
lightning:
trainer:
accelerator: 'gpu'
devices: 8
log_gpu_memory: all
max_epochs: 2
precision: 16
auto_select_gpus: False
strategy:
target: strategies.DDPStrategy
params:
find_unused_parameters: False
log_every_n_steps: 2
# max_steps: 6o
logger: True
default_root_dir: "/tmp/diff_log/"
# profiler: pytorch
logger_config:
wandb:
target: loggers.WandbLogger
params:
name: nowname
save_dir: "/data2/tmp/diff_log/"
offline: opt.debug
id: nowname
examples/images/diffusion/configs/train_pokemon.yaml 0 → 100644
View file @ e532679c
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1.e-4 ]
f_min: [ 1.e-10 ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64 # need to fix for flash-attn
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: main.DataModuleFromConfig
params:
batch_size: 32
wrap: False
train:
target: ldm.data.pokemon.PokemonDataset
# params:
# file_path: "/data/scratch/diffuser/laion_part0/"
# world_size: 1
# rank: 0
lightning:
trainer:
accelerator: 'gpu'
devices: 1
log_gpu_memory: all
max_epochs: 2
precision: 16
auto_select_gpus: False
strategy:
target: strategies.ColossalAIStrategy
params:
use_chunk: True
enable_distributed_storage: True
placement_policy: cuda
force_outputs_fp32: true
log_every_n_steps: 2
logger: True
default_root_dir: "/tmp/diff_log/"
# profiler: pytorch
logger_config:
wandb:
target: loggers.WandbLogger
params:
name: nowname
save_dir: "/tmp/diff_log/"
offline: opt.debug
id: nowname
examples/images/diffusion/docker/Dockerfile 0 → 100644
View file @ e532679c
FROM hpcaitech/pytorch-cuda:1.12.0-11.3.0
# install torch
# RUN conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
RUN apt-get update
RUN apt-get install ffmpeg libsm6 libxext6 -y
# install apex
RUN git clone https://github.com/NVIDIA/apex && \
cd apex && \
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" ./
# install colossalai
# RUN git clone https://github.com/hpcaitech/ColossalAI.git \
# && cd ./ColossalAI \
# && pip install -v --no-cache-dir .
RUN pip install colossalai==0.1.12+torch1.12cu11.3 -f https://release.colossalai.org
# install our lightning, it will be merged to Lightning official repo.
RUN git clone https://github.com/1SAA/lightning.git && \
cd lightning && \
git checkout strategy/colossalai && \
export PACKAGE_NAME=pytorch && \
pip install --no-cache-dir .
# install titans
RUN pip install --no-cache-dir titans
RUN git clone https://github.com/hpcaitech/ColossalAI.git && \
cd ./ColossalAI/examples/images/diffusion && \
pip install -r requirements.txt && \
pip install --no-cache-dir transformers==4.19.2 diffusers invisible-watermark
# install tensornvme
# RUN conda install cmake && \
# git clone https://github.com/hpcaitech/TensorNVMe.git && \
# cd TensorNVMe && \
# pip install -r requirements.txt && \
# pip install -v --no-cache-dir .
examples/images/diffusion/environment.yaml 0 → 100644
View file @ e532679c
name: ldm
channels:
- pytorch
- defaults
dependencies:
- python=3.9.12
- pip=20.3
- cudatoolkit=11.3
- pytorch=1.12.1
- torchvision=0.13.1
- numpy=1.23.1
- pip:
- albumentations==1.3.0
- opencv-python==4.6.0.66
- imageio==2.9.0
- imageio-ffmpeg==0.4.2
- omegaconf==2.1.1
- test-tube>=0.7.5
- streamlit==1.12.1
- einops==0.3.0
- transformers==4.19.2
- webdataset==0.2.5
- kornia==0.6
- open_clip_torch==2.0.2
- invisible-watermark>=0.1.5
- streamlit-drawable-canvas==0.8.0
- torchmetrics==0.7.0
- prefetch_generator
- datasets
- colossalai
- -e .
examples/images/diffusion/ldm/data/base.py 0 → 100644
View file @ e532679c
import math
import os
from abc import abstractmethod
import cv2
import numpy as np
import torch
from torch.utils.data import ChainDataset, ConcatDataset, Dataset, IterableDataset
class Txt2ImgIterableBaseDataset(IterableDataset):
'''
Define an interface to make the IterableDatasets for text2img data chainable
'''
def __init__(self, file_path: str, rank, world_size):
super().__init__()
self.file_path = file_path
self.folder_list = []
self.file_list = []
self.txt_list = []
self.info = self._get_file_info(file_path)
self.start = self.info['start']
self.end = self.info['end']
self.rank = rank
self.world_size = world_size
# self.per_worker = int(math.floor((self.end - self.start) / float(self.world_size)))
# self.iter_start = self.start + self.rank * self.per_worker
# self.iter_end = min(self.iter_start + self.per_worker, self.end)
# self.num_records = self.iter_end - self.iter_start
# self.valid_ids = [i for i in range(self.iter_end)]
self.num_records = self.end - self.start
self.valid_ids = [i for i in range(self.end)]
print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
def __len__(self):
# return self.iter_end - self.iter_start
return self.end - self.start
def __iter__(self):
sample_iterator = self._sample_generator(self.start, self.end)
# sample_iterator = self._sample_generator(self.iter_start, self.iter_end)
return sample_iterator
def _sample_generator(self, start, end):
for idx in range(start, end):
file_name = self.file_list[idx]
txt_name = self.txt_list[idx]
f_ = open(txt_name, 'r')
txt_ = f_.read()
f_.close()
image = cv2.imdecode(np.fromfile(file_name, dtype=np.uint8), 1)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = torch.from_numpy(image) / 255
yield {"txt": txt_, "image": image}
def _get_file_info(self, file_path):
info = \
{
"start": 1,
"end": 0,
}
self.folder_list = [file_path + i for i in os.listdir(file_path) if '.' not in i]
for folder in self.folder_list:
files = [folder + '/' + i for i in os.listdir(folder) if 'jpg' in i]
txts = [k.replace('jpg', 'txt') for k in files]
self.file_list.extend(files)
self.txt_list.extend(txts)
info['end'] = len(self.file_list)
# with open(file_path, 'r') as fin:
# for _ in enumerate(fin):
# info['end'] += 1
# self.txt_list = [k.replace('jpg', 'txt') for k in self.file_list]
return info
examples/images/diffusion/ldm/data/cifar10.py 0 → 100644
View file @ e532679c
from typing import Dict
import numpy as np
from omegaconf import DictConfig, ListConfig
import torch
from torch.utils.data import Dataset
from pathlib import Path
import json
from PIL import Image
from torchvision import transforms
from einops import rearrange
from ldm.util import instantiate_from_config
from datasets import load_dataset
def make_multi_folder_data(paths, caption_files=None, **kwargs):
"""Make a concat dataset from multiple folders
Don't suport captions yet
If paths is a list, that's ok, if it's a Dict interpret it as:
k=folder v=n_times to repeat that
"""
list_of_paths = []
if isinstance(paths, (Dict, DictConfig)):
assert caption_files is None, \
"Caption files not yet supported for repeats"
for folder_path, repeats in paths.items():
list_of_paths.extend([folder_path]*repeats)
paths = list_of_paths
if caption_files is not None:
datasets = [FolderData(p, caption_file=c, **kwargs) for (p, c) in zip(paths, caption_files)]
else:
datasets = [FolderData(p, **kwargs) for p in paths]
return torch.utils.data.ConcatDataset(datasets)
class FolderData(Dataset):
def __init__(self,
root_dir,
caption_file=None,
image_transforms=[],
ext="jpg",
default_caption="",
postprocess=None,
return_paths=False,
) -> None:
"""Create a dataset from a folder of images.
If you pass in a root directory it will be searched for images
ending in ext (ext can be a list)
"""
self.root_dir = Path(root_dir)
self.default_caption = default_caption
self.return_paths = return_paths
if isinstance(postprocess, DictConfig):
postprocess = instantiate_from_config(postprocess)
self.postprocess = postprocess
if caption_file is not None:
with open(caption_file, "rt") as f:
ext = Path(caption_file).suffix.lower()
if ext == ".json":
captions = json.load(f)
elif ext == ".jsonl":
lines = f.readlines()
lines = [json.loads(x) for x in lines]
captions = {x["file_name"]: x["text"].strip("\n") for x in lines}
else:
raise ValueError(f"Unrecognised format: {ext}")
self.captions = captions
else:
self.captions = None
if not isinstance(ext, (tuple, list, ListConfig)):
ext = [ext]
# Only used if there is no caption file
self.paths = []
for e in ext:
self.paths.extend(list(self.root_dir.rglob(f"*.{e}")))
if isinstance(image_transforms, ListConfig):
image_transforms = [instantiate_from_config(tt) for tt in image_transforms]
image_transforms.extend([transforms.ToTensor(),
transforms.Lambda(lambda x: rearrange(x * 2. - 1., 'c h w -> h w c'))])
image_transforms = transforms.Compose(image_transforms)
self.tform = image_transforms
def __len__(self):
if self.captions is not None:
return len(self.captions.keys())
else:
return len(self.paths)
def __getitem__(self, index):
data = {}
if self.captions is not None:
chosen = list(self.captions.keys())[index]
caption = self.captions.get(chosen, None)
if caption is None:
caption = self.default_caption
filename = self.root_dir/chosen
else:
filename = self.paths[index]
if self.return_paths:
data["path"] = str(filename)
im = Image.open(filename)
im = self.process_im(im)
data["image"] = im
if self.captions is not None:
data["txt"] = caption
else:
data["txt"] = self.default_caption
if self.postprocess is not None:
data = self.postprocess(data)
return data
def process_im(self, im):
im = im.convert("RGB")
return self.tform(im)
def hf_dataset(
name,
image_transforms=[],
image_column="img",
label_column="label",
text_column="txt",
split='train',
image_key='image',
caption_key='txt',
):
"""Make huggingface dataset with appropriate list of transforms applied
"""
ds = load_dataset(name, split=split)
image_transforms = [instantiate_from_config(tt) for tt in image_transforms]
image_transforms.extend([transforms.ToTensor(),
transforms.Lambda(lambda x: rearrange(x * 2. - 1., 'c h w -> h w c'))])
tform = transforms.Compose(image_transforms)
assert image_column in ds.column_names, f"Didn't find column {image_column} in {ds.column_names}"
assert label_column in ds.column_names, f"Didn't find column {label_column} in {ds.column_names}"
def pre_process(examples):
processed = {}
processed[image_key] = [tform(im) for im in examples[image_column]]
label_to_text_dict = {0: "airplane", 1: "automobile", 2: "bird", 3: "cat", 4: "deer", 5: "dog", 6: "frog", 7: "horse", 8: "ship", 9: "truck"}
processed[caption_key] = [label_to_text_dict[label] for label in examples[label_column]]
return processed
ds.set_transform(pre_process)
return ds
class TextOnly(Dataset):
def __init__(self, captions, output_size, image_key="image", caption_key="txt", n_gpus=1):
"""Returns only captions with dummy images"""
self.output_size = output_size
self.image_key = image_key
self.caption_key = caption_key
if isinstance(captions, Path):
self.captions = self._load_caption_file(captions)
else:
self.captions = captions
if n_gpus > 1:
# hack to make sure that all the captions appear on each gpu
repeated = [n_gpus*[x] for x in self.captions]
self.captions = []
[self.captions.extend(x) for x in repeated]
def __len__(self):
return len(self.captions)
def __getitem__(self, index):
dummy_im = torch.zeros(3, self.output_size, self.output_size)
dummy_im = rearrange(dummy_im * 2. - 1., 'c h w -> h w c')
return {self.image_key: dummy_im, self.caption_key: self.captions[index]}
def _load_caption_file(self, filename):
with open(filename, 'rt') as f:
captions = f.readlines()
return [x.strip('\n') for x in captions]
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment