├── requirements.txt ├── yaml ├── score.yml ├── doc.yml ├── vec.yml ├── prep.yml └── incep.yml ├── .github └── 94dd0f22.png ├── helper.py ├── index.py ├── query.py ├── .gitignore ├── README.md └── LICENSE /requirements.txt: -------------------------------------------------------------------------------- 1 | gnes>=0.0.46 2 | image 3 | tensorflow==1.12 -------------------------------------------------------------------------------- /yaml/score.yml: -------------------------------------------------------------------------------- 1 | !Chunk2DocTopkReducer 2 | parameters: 3 | reduce_op: avg -------------------------------------------------------------------------------- /.github/94dd0f22.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hanxiao/demo-gnes-flow/HEAD/.github/94dd0f22.png -------------------------------------------------------------------------------- /yaml/doc.yml: -------------------------------------------------------------------------------- 1 | !DictIndexer 2 | gnes_config: 3 | name: my_doc_indexer # a customized name 4 | work_dir: $TEST_WORKDIR -------------------------------------------------------------------------------- /yaml/vec.yml: -------------------------------------------------------------------------------- 1 | !NumpyIndexer # just for testing 2 | gnes_config: 3 | name: my_vec_indexer # a customized name 4 | work_dir: $TEST_WORKDIR -------------------------------------------------------------------------------- /yaml/prep.yml: -------------------------------------------------------------------------------- 1 | !PipelinePreprocessor 2 | components: 3 | - !UnaryPreprocessor 4 | parameters: 5 | doc_type: 2 6 | - !ResizeChunkPreprocessor 7 | parameters: 8 | target_height: 299 9 | target_width: 299 -------------------------------------------------------------------------------- /yaml/incep.yml: -------------------------------------------------------------------------------- 1 | !TFInceptionEncoder 2 | parameters: 3 | model_dir: $TEST_WORKDIR/inception_v4.ckpt 4 | gnes_config: 5 | name: my_encoder # a customized name 6 | is_trained: true # indicate the model has been trained 7 | work_dir: $TEST_WORKDIR 8 | batch_size: 128 -------------------------------------------------------------------------------- /helper.py: -------------------------------------------------------------------------------- 1 | import io 2 | import os 3 | import random 4 | import tarfile 5 | 6 | import numpy as np 7 | from PIL import Image 8 | 9 | 10 | def read_flowers(sample_rate=1.0): 11 | with tarfile.open(os.path.join(os.environ['TEST_WORKDIR'], '17flowers.tgz')) as fp: 12 | for m in fp.getmembers(): 13 | if m.name.endswith('.jpg') and random.random() <= sample_rate: 14 | yield fp.extractfile(m).read() 15 | 16 | 17 | def bytes2ndarray(i, max_size=48): 18 | img = Image.open(io.BytesIO(i)) 19 | img.thumbnail((max_size, max_size)) 20 | return np.asarray(img) 21 | -------------------------------------------------------------------------------- /index.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | from gnes.flow import Flow 4 | 5 | from helper import read_flowers 6 | 7 | os.environ['TEST_WORKDIR'] = '/tmp/gnes-flow-demo' 8 | 9 | # I didn't implement "incremental indexing" in this simple demo. 10 | # So make sure you clean the existing index before doing `python index.py` 11 | # $ rm $TEST_WORKDIR/*.bin 12 | 13 | flow = (Flow(check_version=False, ctrl_with_ipc=True) 14 | .add_preprocessor(name='prep', yaml_path='yaml/prep.yml', replicas=5) 15 | .add_encoder(yaml_path='yaml/incep.yml', replicas=6) 16 | .add_indexer(name='vec_idx', yaml_path='yaml/vec.yml') 17 | .add_indexer(name='doc_idx', yaml_path='yaml/doc.yml', recv_from='prep') 18 | .add_router(name='sync', yaml_path='BaseReduceRouter', num_part=2, recv_from=['vec_idx', 'doc_idx'])) 19 | 20 | # checkout how the flow looks like (...and post it on Twitter, but hey what do I know about promoting OSS) 21 | print(flow.build(backend=None).to_url()) 22 | 23 | with flow(backend='process') as fl: 24 | fl.index(bytes_gen=read_flowers(), batch_size=64) 25 | -------------------------------------------------------------------------------- /query.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | from gnes.flow import Flow 4 | 5 | from helper import read_flowers, bytes2ndarray 6 | 7 | os.environ['TEST_WORKDIR'] = '/tmp/gnes-flow-demo' 8 | 9 | flow = (Flow(check_version=False) 10 | .add_preprocessor(name='prep', yaml_path='yaml/prep.yml') 11 | .add_encoder(yaml_path='yaml/incep.yml') 12 | .add_indexer(name='vec_idx', yaml_path='yaml/vec.yml') 13 | .add_router(name='scorer', yaml_path='yaml/score.yml') 14 | .add_indexer(name='doc_idx', yaml_path='yaml/doc.yml')) 15 | 16 | # checkout how the flow looks like 17 | print(flow.build(backend=None).to_url()) 18 | 19 | num_q = 20 20 | topk = 10 21 | sample_rate = 0.05 22 | 23 | # do the query 24 | results = [] 25 | with flow.build(backend='process') as fl: 26 | for q, r in fl.query(bytes_gen=read_flowers(sample_rate)): 27 | q_img = q.search.query.raw_bytes 28 | r_imgs = [k.doc.raw_bytes for k in r.search.topk_results] 29 | r_scores = [k.score.value for k in r.search.topk_results] 30 | results.append((q_img, r_imgs, r_scores)) 31 | if len(results) > num_q: 32 | break 33 | 34 | # converts raw_bytes to 64x64 thumbnails for visualization 35 | results_v = [(bytes2ndarray(q_img), [bytes2ndarray(r) for r in r_imgs], r_scores) for q_img, r_imgs, r_scores in 36 | results] 37 | 38 | # plotting 39 | import matplotlib.pyplot as plt 40 | 41 | plt.close() 42 | # first row: query. empty space for separation, 3rd to last: topk-results 43 | f, ax = plt.subplots(topk + 2, num_q, figsize=(12, 8)) 44 | 45 | for q in range(num_q): 46 | ax[0][q].imshow(results_v[q][0]) 47 | for r in range(topk): 48 | ax[r + 2][q].imshow(results_v[q][1][r]) 49 | 50 | # do some layout things 51 | [aa.axis('off') for a in ax for aa in a] 52 | plt.tight_layout() 53 | plt.show() 54 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Initially taken from Github's Python gitignore file 2 | 3 | # Byte-compiled / optimized / DLL files 4 | __pycache__/ 5 | *.py[cod] 6 | *$py.class 7 | 8 | # C extensions 9 | *.so 10 | 11 | # Distribution / packaging 12 | .Python 13 | build/ 14 | develop-eggs/ 15 | dist/ 16 | downloads/ 17 | eggs/ 18 | .eggs/ 19 | lib/ 20 | lib64/ 21 | parts/ 22 | sdist/ 23 | var/ 24 | wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | 53 | # Translations 54 | *.mo 55 | *.pot 56 | 57 | # Django stuff: 58 | *.log 59 | local_settings.py 60 | db.sqlite3 61 | 62 | # Flask stuff: 63 | instance/ 64 | .webassets-cache 65 | 66 | # Scrapy stuff: 67 | .scrapy 68 | 69 | # Sphinx documentation 70 | docs/_build/ 71 | docs/api/ 72 | 73 | # PyBuilder 74 | target/ 75 | 76 | # Jupyter Notebook 77 | .ipynb_checkpoints 78 | 79 | # IPython 80 | profile_default/ 81 | ipython_config.py 82 | 83 | # pyenv 84 | .python-version 85 | 86 | # celery beat schedule file 87 | celerybeat-schedule 88 | 89 | # SageMath parsed files 90 | *.sage.py 91 | 92 | # Environments 93 | .venv 94 | env/ 95 | venv/ 96 | ENV/ 97 | env.bak/ 98 | venv.bak/ 99 | 100 | # Spyder project settings 101 | .spyderproject 102 | .spyproject 103 | 104 | # Rope project settings 105 | .ropeproject 106 | 107 | # mkdocs documentation 108 | /site 109 | 110 | # mypy 111 | .mypy_cache/ 112 | .dmypy.json 113 | dmypy.json 114 | 115 | # Pyre type checker 116 | .pyre/ 117 | .idea/ 118 | toy*.py 119 | .DS_Store 120 | toy*.py 121 | post/ 122 | toy*.ipynb 123 | data/ 124 | *.c 125 | .nes_cache 126 | toy*.py 127 | toy*.yml 128 | *.tmp 129 | 130 | shell/gnes-wizard.sh -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # GNES Flow Demo: Flower Image Retrieval 2 | 3 | > Since `v0.0.46` GNES Flow has become the main interface of GNES. GNES Flow provides a **pythonic** and **intuitive** way to implement a pipeline, enabling users to run or debug GNES on a local machine. By default, GNES Flow orchestrates all microservices using multi-thread or multi-process backend, it can be also exported to a Docker Swarm/Kubernetes YAML config, allowing one to deliver GNES to the cloud. 4 | 5 | In this demo, we will learn to build a toy image search engine using GNES Flow API. The task is to retrieve similar flowers given query flowers. 6 | 7 | ![](.github/94dd0f22.png) 8 | 9 | ## Files 10 | 11 | For first-time users, simply [open `flower.ipynb` and follow the steps there](flower.ipynb). 12 | 13 | - [`flower.ipynb`](flower.ipynb): a self-contained Jupyter notebook with a step-by-step explanation 14 | - [`index.py`](index.py): the indexing part of `flower.ipynb`, for indexing all images. 15 | - [`query.py`](query.py): the querying part of `flower.ipynb`, for querying sampled images and plotting top-10 results 16 | 17 | ## Requirements 18 | 19 | ```text 20 | gnes>=0.0.46 21 | image 22 | tensorflow==1.12 23 | ``` 24 | 25 | You can install them via `pip install .`. However, you may want to do that in a virtual env though as it will replace your local Tensorflow with `tensorflow==1.12`. Feel free to [contribute and waive this particular requirement](https://github.com/gnes-ai/demo-gnes-flow/pulls). 26 | 27 | ## Troubleshooting 28 | 29 | #### Can not load indexer when indexing twice 30 | 31 | I didn't implement features like "incremental indexing" in this simple demo. So please make sure you clean up the existing index before doing `python index.py`. 32 | ```bash 33 | rm $TEST_WORKDIR/*.bin 34 | ``` 35 | 36 | #### `OSError: [Errno 24] Too many open files` 37 | 38 | This often happens when `replicas`/`num_parallel` is set to a big number. Solution to that is to increase this (session-wise) allowance via: 39 | 40 | ```bash 41 | ulimit -n 4096 42 | ``` 43 | 44 | #### `objc[15934]: +[__NSPlaceholderDictionary initialize] may have been in progress in another thread when fork() was called.` 45 | 46 | Probably MacOS only. 47 | ```bash 48 | export OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES 49 | ``` 50 | 51 | #### Why `tensorflow==1.12`, why not 2.0? 52 | 53 | In this demo, I simply use the inceptionV4 model from `tf.contrib.slim`. There are some major changes in TF2.0, and the model can not be directly used. Fortunately, contribute/port an external model to GNES is extremely simple. Feel free to [follow the instruction in GNES Hub](https://github.com/gnes-ai/hub) and make a contribution to this demo. 54 | 55 | #### It stuck/crash in Jupyter Notebook 56 | 57 | Please try running `python index.py` or `python query.py` outside the Jupyter Notebook. As far as I know, Jupyter Notebook is employing ZeroMQ in the backend and this can sometimes mess up with GNES sockets (or the other way around). If you find the demo still crash/stuck when running as independent Python script, then please report an [issue to this repository](https://github.com/gnes-ai/demo-gnes-flow/issues) or the [GNES main repository](https://github.com/gnes-ai/gnes/issues). 58 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------