sir-timio / htr Goto Github PK
View Code? Open in Web Editor NEWHandwritten text recognition
License: MIT License
Handwritten text recognition
License: MIT License
model = Model(params)
params = {
'callbacks': ['checkpoint', 'csv_log', 'tb_log', 'early_stopping'],
'metrics': ['cer', 'accuracy'],
'checkpoint_path': os.path.join(WORKING_DIR, 'checkpoints/training_2/cp.ckpt'),
'csv_log_path': os.path.join(WORKING_DIR, 'logs/csv_logs/log_2.csv'),
'tb_log_path': os.path.join(WORKING_DIR, 'logs/tb_logs/log2'),
'tb_update_freq': 200,
'epochs': 50,
'batch_size': batch_size,
'early_stopping_patience': 10,
'input_img_shape': (new_img_width, new_img_height, 1),
'vocab_len': 75,
'max_label_len': 22,
'chars_path': os.path.join(os.path.split(metadata)[0], 'symbols.txt'),
'blank': '#',
'blank_index': 74,
'corpus': os.path.join(os.path.split(metadata)[0], 'corpus.txt')
}
Пытаюсь создать модель с таким словарем, однако не хватает параметра vocab.
KeyError Traceback (most recent call last)
in
----> 1 model = Model(params)
2 model.build()
3 model.get_summary()
4 #model.load_weights('checkpoints/training_2/cp.ckpt')
/home/htr/model/Model.py in init(self, params)
43 self.max_label_len = params['max_label_len']
44 self.chars_path = params['chars_path']
---> 45 self.vocab = params['vocab']
46 self.blank = params['blank']
47 self.blank_index = None
KeyError: 'vocab'
Как это исправить или что должно быть в vocab?
F:\HTR>docker build -t htr/tfgpu .
[+] Building 435.5s (4/9)
=> [1/5] FROM docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter@sha256:c3b4e83edf14b282902c80e0ef245115736ce4c 428.5s
=> => sha256:39db22124f005688940638be691ddd6fcccd364860a75c09bf227bd64b71a6cc 84.73MB / 84.73MB 34.3s
=> => extracting sha256:419640447d267f068d2f84a093cb13a56ce77e130877f5b8bdb4294f4a90a84f 0.0s
=> => extracting sha256:61e52f862619ab016d3bcfbd78e5c7aaaa1989b4c295e6dbcacddd2d7b93e1f5 0.0s
=> => extracting sha256:2a93278deddf8fe289dceef311ed19e8f2083a88eba6be60d393842fd40697b0 1.1s
[+] Building 435.7s (4/9)
=> [1/5] FROM docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter@sha256:c3b4e83edf14b282902c80e0ef245115736ce4c 428.7s
=> => sha256:39db22124f005688940638be691ddd6fcccd364860a75c09bf227bd64b71a6cc 84.73MB / 84.73MB 34.3s
=> => extracting sha256:419640447d267f068d2f84a093cb13a56ce77e130877f5b8bdb4294f4a90a84f 0.0s
=> => extracting sha256:61e52f862619ab016d3bcfbd78e5c7aaaa1989b4c295e6dbcacddd2d7b93e1f5 0.0s
=> => extracting sha256:2a93278deddf8fe289dceef311ed19e8f2083a88eba6be60d393842fd40697b0 1.1s
=> => extracting sha256:c9f080049843544961377a152d7d86c34816221038b8da3e3dc207ccddb72549 1.6s
=> => extracting sha256:8189556b23294579329c522acf5618c024520b323d6a68cdd9eca91ca4f2f454 0.0s
=> => sha256:fc3e5b4f9be500b755e357e514e19e6091012e82405ed8af34b8137c76245f8f 3.99MB / 3.99MB 37.9s
=> => sha256:82f0e853e481c2ffd3a42c9f6d1f0db698ea463e7e6848978dc9649f5decf7c3 176B / 176B 36.7s
=> => sha256:0e3f4c426c9e5994ac625c63f9e8116e8cfdfe4600ba6c78fc52d06de8bd7dbe 440.43MB / 440.43MB 131.5s
=> => sha256:bd7b74ac1111ef1599411a0197a707306f96edd73ce80e40b85accb872accddb 1.09kB / 1.09kB 38.5s
=> => sha256:69903a2e24bf9c9fd83c0af1fbdbc4a802d0fba99e38c9d407af0f596102c469 1.09kB / 1.09kB 39.2s
=> => sha256:c3a9076c8993f5e5fa46e6fa73ac1813757fd093a8389f2b5a942cae5537b4b9 46.66MB / 46.66MB 58.5s
=> => sha256:dc5bef361fe84b2b8012101a1e4b8879696eb39c3ade23d20f1e36b920921198 410.45kB / 410.45kB 61.8s
[+] Building 435.8s (4/9)
=> [1/5] FROM docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter@sha256:c3b4e83edf14b282902c80e0ef245115736ce4c 428.8s
=> => sha256:39db22124f005688940638be691ddd6fcccd364860a75c09bf227bd64b71a6cc 84.73MB / 84.73MB 34.3s
[+] Building 585.7s (6/9)
=> [internal] load build definition from Dockerfile 0.9s
=> => transferring dockerfile: 377B 0.5s
=> [internal] load .dockerignore 0.7s
=> => transferring context: 2B 0.4s
=> [internal] load metadata for docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter 5.8s
=> [internal] load build context 0.2s
=> => transferring context: 481B 0.0s
=> [1/5] FROM docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter@sha256:c3b4e83edf14b282902c80e0ef245115736ce4c 560.7s
=> => resolve docker.io/tensorflow/tensorflow:2.4.1-gpu-jupyter@sha256:c3b4e83edf14b282902c80e0ef245115736ce4c91 0.0s
=> => sha256:64d8717296f8099f62b7f5abca1560addc2bf19d09021e800ece8b37cc9d89ae 19.63kB / 19.63kB 0.0s
=> => sha256:c3b4e83edf14b282902c80e0ef245115736ce4c91eabc39c93f51ca56508e504 6.60kB / 6.60kB 0.0s
=> => sha256:171857c49d0f5e2ebf623e6cb36a8bcad585ed0c2aa99c87a055df034c1e5848 26.70MB / 26.70MB 3.6s
=> => sha256:419640447d267f068d2f84a093cb13a56ce77e130877f5b8bdb4294f4a90a84f 852B / 852B 0.8s
=> => sha256:61e52f862619ab016d3bcfbd78e5c7aaaa1989b4c295e6dbcacddd2d7b93e1f5 162B / 162B 1.0s
=> => sha256:2a93278deddf8fe289dceef311ed19e8f2083a88eba6be60d393842fd40697b0 7.21MB / 7.21MB 4.7s
=> => sha256:c9f080049843544961377a152d7d86c34816221038b8da3e3dc207ccddb72549 10.33MB / 10.33MB 5.4s
=> => extracting sha256:171857c49d0f5e2ebf623e6cb36a8bcad585ed0c2aa99c87a055df034c1e5848 4.5s
=> => sha256:8189556b23294579329c522acf5618c024520b323d6a68cdd9eca91ca4f2f454 1.00kB / 1.00kB 4.2s
=> => sha256:c9db5d801625d9841844fca4fd240bb1c864f5f8e737ad884cde4d50783ebf37 1.78GB / 1.78GB 264.7s
=> => sha256:1c370cc33248c9c135e305d2b727d6a351670a2f78b9ed2138bb85432cdfee21 179.19MB / 179.19MB 36.1s
=> => sha256:91490cad11f8302e74e711101e16b34724c7378c64c412a15013ff3e4193bfc2 7.49kB / 7.49kB 6.0s
=> => sha256:39db22124f005688940638be691ddd6fcccd364860a75c09bf227bd64b71a6cc 84.73MB / 84.73MB 34.3s
=> => extracting sha256:419640447d267f068d2f84a093cb13a56ce77e130877f5b8bdb4294f4a90a84f 0.0s
=> => extracting sha256:61e52f862619ab016d3bcfbd78e5c7aaaa1989b4c295e6dbcacddd2d7b93e1f5 0.0s
=> => extracting sha256:2a93278deddf8fe289dceef311ed19e8f2083a88eba6be60d393842fd40697b0 1.1s
=> => extracting sha256:c9f080049843544961377a152d7d86c34816221038b8da3e3dc207ccddb72549 1.6s
=> => extracting sha256:8189556b23294579329c522acf5618c024520b323d6a68cdd9eca91ca4f2f454 0.0s
=> => sha256:fc3e5b4f9be500b755e357e514e19e6091012e82405ed8af34b8137c76245f8f 3.99MB / 3.99MB 37.9s
=> => sha256:82f0e853e481c2ffd3a42c9f6d1f0db698ea463e7e6848978dc9649f5decf7c3 176B / 176B 36.7s
=> => sha256:0e3f4c426c9e5994ac625c63f9e8116e8cfdfe4600ba6c78fc52d06de8bd7dbe 440.43MB / 440.43MB 131.5s
=> => sha256:bd7b74ac1111ef1599411a0197a707306f96edd73ce80e40b85accb872accddb 1.09kB / 1.09kB 38.5s
=> => sha256:69903a2e24bf9c9fd83c0af1fbdbc4a802d0fba99e38c9d407af0f596102c469 1.09kB / 1.09kB 39.2s
=> => sha256:c3a9076c8993f5e5fa46e6fa73ac1813757fd093a8389f2b5a942cae5537b4b9 46.66MB / 46.66MB 58.5s
=> => sha256:dc5bef361fe84b2b8012101a1e4b8879696eb39c3ade23d20f1e36b920921198 410.45kB / 410.45kB 61.8s
=> => sha256:a8cf4ab5b477394948942f0bb6d8e66f2ee402dda75ce9e8192c2471a734e9e4 263B / 263B 62.6s
=> => sha256:c1c11b71e870852e45aee2dace3afcd60fcdff5125c13dd397c130a070e1a297 158B / 158B 63.2s
=> => sha256:8267c7e45f596b7c12c23bc7362938e7ab8d88bef5f8fa719f4a0d0f082d7d23 129B / 129B 64.4s
=> => sha256:ce0d841a8f903e50915c945f40b82b1556a9b0368c5c164b0553c38001f1fcd5 15.50MB / 15.50MB 73.3s
=> => sha256:3ac95ea8bb4f67af378307748e18b45e5bc3a0e6e6455b586ed828383d8c53b8 7.78kB / 7.78kB 76.1s
=> => sha256:117b2ba06f191216d424f83b55b72e7ae026d50437bfa11b3922e402ec3e1ea3 11.59kB / 11.59kB 77.4s
=> => sha256:8739bc7256c624871d843df12dd729aa67865eb166add482441cae22be86e0f2 8.74kB / 8.74kB 78.3s
=> => sha256:a55168dbf71de17f7e0f601635236f3784ae73dabc90880789cad337cd60f465 7.18kB / 7.18kB 79.1s
=> => sha256:51fe3f9b075ff6b8aaeb74a7d419bf572c3a6f6243c04818a37776b562bbae08 10.01kB / 10.01kB 81.4s
=> => sha256:b4a4a5f30f793c9ec694323a53975d7348a5019f6606abc0048a1f1fe3cadad7 5.68kB / 5.68kB 82.4s
=> => sha256:91685856cab1648efe33e1aca974515939af9685bdd13dc1f40ef1e006a1db00 226B / 226B 83.2s
=> => sha256:4871f8ab4308c25c98790fd8341c6fb03cfb6548f36f862ada3dba3f5f44c1ce 334.25kB / 334.25kB 86.6s
=> => sha256:f0d9fb274b0f41d26e67fecc6536559a56baabacb7ae724c2df7715a6eb29ff5 3.84kB / 3.84kB 88.2s
=> => extracting sha256:c9db5d801625d9841844fca4fd240bb1c864f5f8e737ad884cde4d50783ebf37 160.4s
=> => extracting sha256:1c370cc33248c9c135e305d2b727d6a351670a2f78b9ed2138bb85432cdfee21 13.1s
=> => extracting sha256:91490cad11f8302e74e711101e16b34724c7378c64c412a15013ff3e4193bfc2 0.0s
=> => extracting sha256:39db22124f005688940638be691ddd6fcccd364860a75c09bf227bd64b71a6cc 4.9s
=> => extracting sha256:fc3e5b4f9be500b755e357e514e19e6091012e82405ed8af34b8137c76245f8f 0.7s
=> => extracting sha256:82f0e853e481c2ffd3a42c9f6d1f0db698ea463e7e6848978dc9649f5decf7c3 0.0s
=> => extracting sha256:0e3f4c426c9e5994ac625c63f9e8116e8cfdfe4600ba6c78fc52d06de8bd7dbe 38.7s
=> => extracting sha256:bd7b74ac1111ef1599411a0197a707306f96edd73ce80e40b85accb872accddb 0.0s
=> => extracting sha256:69903a2e24bf9c9fd83c0af1fbdbc4a802d0fba99e38c9d407af0f596102c469 0.0s
=> => extracting sha256:c3a9076c8993f5e5fa46e6fa73ac1813757fd093a8389f2b5a942cae5537b4b9 7.4s
=> => extracting sha256:dc5bef361fe84b2b8012101a1e4b8879696eb39c3ade23d20f1e36b920921198 0.2s
=> => extracting sha256:a8cf4ab5b477394948942f0bb6d8e66f2ee402dda75ce9e8192c2471a734e9e4 0.0s
=> => extracting sha256:c1c11b71e870852e45aee2dace3afcd60fcdff5125c13dd397c130a070e1a297 0.0s
=> => extracting sha256:8267c7e45f596b7c12c23bc7362938e7ab8d88bef5f8fa719f4a0d0f082d7d23 0.0s
=> => extracting sha256:ce0d841a8f903e50915c945f40b82b1556a9b0368c5c164b0553c38001f1fcd5 1.1s
=> => extracting sha256:3ac95ea8bb4f67af378307748e18b45e5bc3a0e6e6455b586ed828383d8c53b8 0.0s
=> => extracting sha256:117b2ba06f191216d424f83b55b72e7ae026d50437bfa11b3922e402ec3e1ea3 0.0s
=> => extracting sha256:8739bc7256c624871d843df12dd729aa67865eb166add482441cae22be86e0f2 0.0s
=> => extracting sha256:a55168dbf71de17f7e0f601635236f3784ae73dabc90880789cad337cd60f465 0.0s
=> => extracting sha256:51fe3f9b075ff6b8aaeb74a7d419bf572c3a6f6243c04818a37776b562bbae08 0.0s
=> => extracting sha256:b4a4a5f30f793c9ec694323a53975d7348a5019f6606abc0048a1f1fe3cadad7 0.0s
=> => extracting sha256:91685856cab1648efe33e1aca974515939af9685bdd13dc1f40ef1e006a1db00 0.0s
=> => extracting sha256:4871f8ab4308c25c98790fd8341c6fb03cfb6548f36f862ada3dba3f5f44c1ce 0.1s
=> => extracting sha256:f0d9fb274b0f41d26e67fecc6536559a56baabacb7ae724c2df7715a6eb29ff5 0.0s
=> ERROR [2/5] RUN apt-get update && apt-get install -y libgl1 18.0s
------
> [2/5] RUN apt-get update && apt-get install -y libgl1:
#5 1.702 Get:1 http://security.ubuntu.com/ubuntu bionic-security InRelease [88.7 kB]
#5 1.795 Hit:2 http://archive.ubuntu.com/ubuntu bionic InRelease
#5 1.917 Get:3 http://archive.ubuntu.com/ubuntu bionic-updates InRelease [88.7 kB]
#5 2.150 Get:4 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease [1581 B]
#5 2.445 Err:4 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease
#5 2.445 The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
#5 2.686 Get:5 http://archive.ubuntu.com/ubuntu bionic-backports InRelease [83.3 kB]
#5 2.986 Get:6 http://security.ubuntu.com/ubuntu bionic-security/multiverse amd64 Packages [23.8 kB]
#5 3.008 Ign:7 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64 InRelease
#5 3.092 Get:8 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64 Release [564 B]
#5 3.164 Get:9 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64 Release.gpg [833 B]
#5 3.220 Get:10 http://security.ubuntu.com/ubuntu bionic-security/main amd64 Packages [3373 kB]
#5 3.275 Get:11 http://archive.ubuntu.com/ubuntu bionic-updates/multiverse amd64 Packages [30.8 kB]
#5 3.508 Get:12 http://archive.ubuntu.com/ubuntu bionic-updates/universe amd64 Packages [2410 kB]
#5 3.743 Get:13 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64 Packages [73.8 kB]
#5 5.134 Get:14 http://security.ubuntu.com/ubuntu bionic-security/universe amd64 Packages [1636 kB]
#5 5.236 Get:15 http://archive.ubuntu.com/ubuntu bionic-updates/restricted amd64 Packages [1728 kB]
#5 5.646 Get:16 http://security.ubuntu.com/ubuntu bionic-security/restricted amd64 Packages [1688 kB]
#5 5.820 Get:17 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 Packages [3785 kB]
#5 6.594 Get:18 http://archive.ubuntu.com/ubuntu bionic-backports/main amd64 Packages [64.0 kB]
#5 6.595 Get:19 http://archive.ubuntu.com/ubuntu bionic-backports/universe amd64 Packages [20.6 kB]
#5 8.836 Reading package lists...
#5 15.70 W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
#5 15.70 E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease' is no longer signed.
------
executor failed running [/bin/bash -c apt-get update && apt-get install -y libgl1]: exit code: 100
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.