Add automatic doc sorting (#1940)

* automatically sort docs

* add new check toc doc

* add new check toc doc

* add

* add new check toc doc

* add

* add new check toc doc

* correct

* finalize
This commit is contained in:
Patrick von Platen 2023-01-06 20:24:47 +04:00 committed by GitHub
parent 9f4c4f5e82
commit aba2a65d6a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 273 additions and 114 deletions

View File

@ -45,12 +45,14 @@ quality:
isort --check-only $(check_dirs)
flake8 $(check_dirs)
doc-builder style src/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source
python utils/check_doc_toc.py
# Format source code automatically and check is there are any problems left that need manual fixing
extra_style_checks:
python utils/custom_init_isort.py
doc-builder style src/diffusers docs/source --max_len 119 --path_to_docs docs/source
python utils/check_doc_toc.py --fix_and_overwrite
# this target runs checks on all files and potentially modifies some of them

View File

@ -1,195 +1,194 @@
- sections:
- local: index
title: "🧨 Diffusers"
title: 🧨 Diffusers
- local: quicktour
title: "Quicktour"
title: Quicktour
- local: stable_diffusion
title: "Stable Diffusion"
title: Stable Diffusion
- local: installation
title: "Installation"
title: "Get started"
title: Installation
title: Get started
- sections:
- sections:
- local: using-diffusers/loading
title: "Loading Pipelines, Models, and Schedulers"
title: Loading Pipelines, Models, and Schedulers
- local: using-diffusers/schedulers
title: "Using different Schedulers"
title: Using different Schedulers
- local: using-diffusers/configuration
title: "Configuring Pipelines, Models, and Schedulers"
title: Configuring Pipelines, Models, and Schedulers
- local: using-diffusers/custom_pipeline_overview
title: "Loading and Adding Custom Pipelines"
title: "Loading & Hub"
title: Loading and Adding Custom Pipelines
title: Loading & Hub
- sections:
- local: using-diffusers/unconditional_image_generation
title: "Unconditional Image Generation"
title: Unconditional Image Generation
- local: using-diffusers/conditional_image_generation
title: "Text-to-Image Generation"
title: Text-to-Image Generation
- local: using-diffusers/img2img
title: "Text-Guided Image-to-Image"
title: Text-Guided Image-to-Image
- local: using-diffusers/inpaint
title: "Text-Guided Image-Inpainting"
title: Text-Guided Image-Inpainting
- local: using-diffusers/depth2img
title: "Text-Guided Depth-to-Image"
title: Text-Guided Depth-to-Image
- local: using-diffusers/reusing_seeds
title: "Reusing seeds for deterministic generation"
title: Reusing seeds for deterministic generation
- local: using-diffusers/custom_pipeline_examples
title: "Community Pipelines"
title: Community Pipelines
- local: using-diffusers/contribute_pipeline
title: "How to contribute a Pipeline"
title: "Pipelines for Inference"
title: How to contribute a Pipeline
title: Pipelines for Inference
- sections:
- local: using-diffusers/rl
title: "Reinforcement Learning"
title: Reinforcement Learning
- local: using-diffusers/audio
title: "Audio"
title: Audio
- local: using-diffusers/other-modalities
title: "Other Modalities"
title: "Taking Diffusers Beyond Images"
title: "Using Diffusers"
title: Other Modalities
title: Taking Diffusers Beyond Images
title: Using Diffusers
- sections:
- local: optimization/fp16
title: "Memory and Speed"
title: Memory and Speed
- local: optimization/xformers
title: "xFormers"
title: xFormers
- local: optimization/onnx
title: "ONNX"
title: ONNX
- local: optimization/open_vino
title: "OpenVINO"
title: OpenVINO
- local: optimization/mps
title: "MPS"
title: MPS
- local: optimization/habana
title: "Habana Gaudi"
title: "Optimization/Special Hardware"
title: Habana Gaudi
title: Optimization/Special Hardware
- sections:
- local: training/overview
title: "Overview"
title: Overview
- local: training/unconditional_training
title: "Unconditional Image Generation"
title: Unconditional Image Generation
- local: training/text_inversion
title: "Textual Inversion"
title: Textual Inversion
- local: training/dreambooth
title: "Dreambooth"
title: Dreambooth
- local: training/text2image
title: "Text-to-image fine-tuning"
title: "Training"
title: Text-to-image fine-tuning
title: Training
- sections:
- local: conceptual/philosophy
title: "Philosophy"
title: Philosophy
- local: conceptual/contribution
title: "How to contribute?"
title: "Conceptual Guides"
title: How to contribute?
title: Conceptual Guides
- sections:
- sections:
- local: api/models
title: "Models"
title: Models
- local: api/diffusion_pipeline
title: "Diffusion Pipeline"
title: Diffusion Pipeline
- local: api/logging
title: "Logging"
title: Logging
- local: api/configuration
title: "Configuration"
title: Configuration
- local: api/outputs
title: "Outputs"
title: "Main Classes"
title: Outputs
title: Main Classes
- sections:
- local: api/pipelines/overview
title: "Overview"
title: Overview
- local: api/pipelines/alt_diffusion
title: "AltDiffusion"
title: AltDiffusion
- local: api/pipelines/audio_diffusion
title: Audio Diffusion
- local: api/pipelines/cycle_diffusion
title: "Cycle Diffusion"
title: Cycle Diffusion
- local: api/pipelines/dance_diffusion
title: Dance Diffusion
- local: api/pipelines/ddim
title: "DDIM"
title: DDIM
- local: api/pipelines/ddpm
title: "DDPM"
title: DDPM
- local: api/pipelines/latent_diffusion
title: "Latent Diffusion"
- local: api/pipelines/latent_diffusion_uncond
title: "Unconditional Latent Diffusion"
title: Latent Diffusion
- local: api/pipelines/paint_by_example
title: "PaintByExample"
title: PaintByExample
- local: api/pipelines/pndm
title: "PNDM"
title: PNDM
- local: api/pipelines/repaint
title: RePaint
- local: api/pipelines/stable_diffusion_safe
title: Safe Stable Diffusion
- local: api/pipelines/score_sde_ve
title: "Score SDE VE"
title: Score SDE VE
- sections:
- local: api/pipelines/stable_diffusion/overview
title: "Overview"
title: Overview
- local: api/pipelines/stable_diffusion/text2img
title: "Text-to-Image"
title: Text-to-Image
- local: api/pipelines/stable_diffusion/img2img
title: "Image-to-Image"
title: Image-to-Image
- local: api/pipelines/stable_diffusion/inpaint
title: "Inpaint"
title: Inpaint
- local: api/pipelines/stable_diffusion/depth2img
title: "Depth-to-Image"
title: Depth-to-Image
- local: api/pipelines/stable_diffusion/image_variation
title: "Image-Variation"
title: Image-Variation
- local: api/pipelines/stable_diffusion/upscale
title: "Super-Resolution"
title: "Stable Diffusion"
title: Super-Resolution
title: Stable Diffusion
- local: api/pipelines/stable_diffusion_2
title: "Stable Diffusion 2"
- local: api/pipelines/stable_diffusion_safe
title: "Safe Stable Diffusion"
title: Stable Diffusion 2
- local: api/pipelines/stochastic_karras_ve
title: "Stochastic Karras VE"
- local: api/pipelines/dance_diffusion
title: "Dance Diffusion"
title: Stochastic Karras VE
- local: api/pipelines/unclip
title: "UnCLIP"
title: UnCLIP
- local: api/pipelines/latent_diffusion_uncond
title: Unconditional Latent Diffusion
- local: api/pipelines/versatile_diffusion
title: "Versatile Diffusion"
title: Versatile Diffusion
- local: api/pipelines/vq_diffusion
title: "VQ Diffusion"
- local: api/pipelines/repaint
title: "RePaint"
- local: api/pipelines/audio_diffusion
title: "Audio Diffusion"
title: "Pipelines"
title: VQ Diffusion
title: Pipelines
- sections:
- local: api/schedulers/overview
title: "Overview"
title: Overview
- local: api/schedulers/ddim
title: "DDIM"
title: DDIM
- local: api/schedulers/ddpm
title: "DDPM"
title: DDPM
- local: api/schedulers/deis
title: "DEIS"
- local: api/schedulers/singlestep_dpm_solver
title: "Singlestep DPM-Solver"
- local: api/schedulers/multistep_dpm_solver
title: "Multistep DPM-Solver"
- local: api/schedulers/heun
title: "Heun Scheduler"
title: DEIS
- local: api/schedulers/dpm_discrete
title: "DPM Discrete Scheduler"
title: DPM Discrete Scheduler
- local: api/schedulers/dpm_discrete_ancestral
title: "DPM Discrete Scheduler with ancestral sampling"
- local: api/schedulers/stochastic_karras_ve
title: "Stochastic Kerras VE"
- local: api/schedulers/lms_discrete
title: "Linear Multistep"
- local: api/schedulers/pndm
title: "PNDM"
- local: api/schedulers/score_sde_ve
title: "VE-SDE"
- local: api/schedulers/ipndm
title: "IPNDM"
- local: api/schedulers/score_sde_vp
title: "VP-SDE"
- local: api/schedulers/euler
title: "Euler scheduler"
title: DPM Discrete Scheduler with ancestral sampling
- local: api/schedulers/euler_ancestral
title: "Euler Ancestral Scheduler"
- local: api/schedulers/vq_diffusion
title: "VQDiffusionScheduler"
title: Euler Ancestral Scheduler
- local: api/schedulers/euler
title: Euler scheduler
- local: api/schedulers/heun
title: Heun Scheduler
- local: api/schedulers/ipndm
title: IPNDM
- local: api/schedulers/lms_discrete
title: Linear Multistep
- local: api/schedulers/multistep_dpm_solver
title: Multistep DPM-Solver
- local: api/schedulers/pndm
title: PNDM
- local: api/schedulers/repaint
title: "RePaint Scheduler"
title: "Schedulers"
title: RePaint Scheduler
- local: api/schedulers/singlestep_dpm_solver
title: Singlestep DPM-Solver
- local: api/schedulers/stochastic_karras_ve
title: Stochastic Kerras VE
- local: api/schedulers/score_sde_ve
title: VE-SDE
- local: api/schedulers/score_sde_vp
title: VP-SDE
- local: api/schedulers/vq_diffusion
title: VQDiffusionScheduler
title: Schedulers
- sections:
- local: api/experimental/rl
title: "RL Planning"
title: "Experimental Features"
title: "API"
title: RL Planning
title: Experimental Features
title: API

158
utils/check_doc_toc.py Normal file
View File

@ -0,0 +1,158 @@
# coding=utf-8
# Copyright 2022 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
from collections import defaultdict
import yaml
PATH_TO_TOC = "docs/source/en/_toctree.yml"
def clean_doc_toc(doc_list):
"""
Cleans the table of content of the model documentation by removing duplicates and sorting models alphabetically.
"""
counts = defaultdict(int)
overview_doc = []
new_doc_list = []
for doc in doc_list:
if "local" in doc:
counts[doc["local"]] += 1
if doc["title"].lower() == "overview":
overview_doc.append({"local": doc["local"], "title": doc["title"]})
else:
new_doc_list.append(doc)
doc_list = new_doc_list
duplicates = [key for key, value in counts.items() if value > 1]
new_doc = []
for duplicate_key in duplicates:
titles = list(set(doc["title"] for doc in doc_list if doc["local"] == duplicate_key))
if len(titles) > 1:
raise ValueError(
f"{duplicate_key} is present several times in the documentation table of content at "
"`docs/source/en/_toctree.yml` with different *Title* values. Choose one of those and remove the "
"others."
)
# Only add this once
new_doc.append({"local": duplicate_key, "title": titles[0]})
# Add none duplicate-keys
new_doc.extend([doc for doc in doc_list if "local" not in counts or counts[doc["local"]] == 1])
new_doc = sorted(new_doc, key=lambda s: s["title"].lower())
# "overview" gets special treatment and is always first
if len(overview_doc) > 1:
raise ValueError("{doc_list} has two 'overview' docs which is not allowed.")
overview_doc.extend(new_doc)
# Sort
return overview_doc
def check_scheduler_doc(overwrite=False):
with open(PATH_TO_TOC, encoding="utf-8") as f:
content = yaml.safe_load(f.read())
# Get to the API doc
api_idx = 0
while content[api_idx]["title"] != "API":
api_idx += 1
api_doc = content[api_idx]["sections"]
# Then to the model doc
scheduler_idx = 0
while api_doc[scheduler_idx]["title"] != "Schedulers":
scheduler_idx += 1
scheduler_doc = api_doc[scheduler_idx]["sections"]
new_scheduler_doc = clean_doc_toc(scheduler_doc)
diff = False
if new_scheduler_doc != scheduler_doc:
diff = True
if overwrite:
api_doc[scheduler_idx]["sections"] = new_scheduler_doc
if diff:
if overwrite:
content[api_idx]["sections"] = api_doc
with open(PATH_TO_TOC, "w", encoding="utf-8") as f:
f.write(yaml.dump(content, allow_unicode=True))
else:
raise ValueError(
"The model doc part of the table of content is not properly sorted, run `make style` to fix this."
)
def check_pipeline_doc(overwrite=False):
with open(PATH_TO_TOC, encoding="utf-8") as f:
content = yaml.safe_load(f.read())
# Get to the API doc
api_idx = 0
while content[api_idx]["title"] != "API":
api_idx += 1
api_doc = content[api_idx]["sections"]
# Then to the model doc
pipeline_idx = 0
while api_doc[pipeline_idx]["title"] != "Pipelines":
pipeline_idx += 1
diff = False
pipeline_docs = api_doc[pipeline_idx]["sections"]
new_pipeline_docs = []
# sort sub pipeline docs
for pipeline_doc in pipeline_docs:
if "section" in pipeline_doc:
sub_pipeline_doc = pipeline_doc["section"]
new_sub_pipeline_doc = clean_doc_toc(sub_pipeline_doc)
if overwrite:
pipeline_doc["section"] = new_sub_pipeline_doc
new_pipeline_docs.append(pipeline_doc)
# sort overall pipeline doc
new_pipeline_docs = clean_doc_toc(new_pipeline_docs)
if new_pipeline_docs != pipeline_docs:
diff = True
if overwrite:
api_doc[pipeline_idx]["sections"] = new_pipeline_docs
if diff:
if overwrite:
content[api_idx]["sections"] = api_doc
with open(PATH_TO_TOC, "w", encoding="utf-8") as f:
f.write(yaml.dump(content, allow_unicode=True))
else:
raise ValueError(
"The model doc part of the table of content is not properly sorted, run `make style` to fix this."
)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--fix_and_overwrite", action="store_true", help="Whether to fix inconsistencies.")
args = parser.parse_args()
check_scheduler_doc(args.fix_and_overwrite)
check_pipeline_doc(args.fix_and_overwrite)