Mask_RCNN_tf_2.x
mmocr
Mask_RCNN_tf_2.x | mmocr | |
---|---|---|
1 | 6 | |
48 | 4,086 | |
- | 1.6% | |
10.0 | 4.7 | |
over 2 years ago | 11 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Mask_RCNN_tf_2.x
-
DeepCreamPy & Hent-AI Guide: Installation and anime censorship removal (Version 2)
Thus, if we want to use RTX 3000 series and later, we need to find a MRCNN that is Tensorflow 2.X compatible. Instead of updating the code myself, I looked through GitHub to see if anyone else had done this already. After some searching, I found a MRCNN package by BupyeongHealer that is compatible with Tensorflow 2.X versions. I implemented this package in Hent-AI by replacing the “mrcnn” folder (which has Matterport’s MRCNN) with the “mrcnn” folder from BupyeongHealer. Running Hent-AI at this point led to errors if trying to run Tensorflow 2.5 or newer due to the Layers class in Keras being moved from the Engine to the Layers module from Tensorflow 2.4 to 2.5, and Keras being moved from standalone to being part of the Tensorflow package itself. These errors were all eliminated by making the following modifications to “model.py” in the “mrcnn” folder:
mmocr
-
Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM
Yup! But I'm still exploring options. (any recommendations would be welcomed!) Here are some candidates I'm considering:
- https://github.com/mindee/doctr
- https://github.com/open-mmlab/mmocr
- https://github.com/PaddlePaddle/PaddleOCR (honestly I don't know Mandarin so I'm a bit stuck)
- https://github.com/clovaai/donut - While it's primarily an "OCR-free document understanding transformer," I think it's worth experimenting with. Think I can sort this out by letting the LLM reason through it multiple times (although this will impact performance)
- yesterday got a suggestion to consider https://github.com/kakaobrain/pororo - I don't think development is still active but the results are pretty great on Korean text
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
-
[P]Modern open-source OCR capabilities and which model to choose
Link: https://github.com/open-mmlab/mmocr
-
Text Classification Library for a Quick Baseline
For more text classification baselines (CRNN, NRTR, RubustScanner, SAR, SegOCR), checkout https://github.com/open-mmlab/mmocr They are reproducible, customizable.
-
[N] MMOCR: A Toolbox for Text Detection, Recognition, and Understanding Based on PyTorch
We just released https://github.com/open-mmlab/mmocr, a new member in OpenMMLab https://openmmlab.com/. This first release supports
- OCR Baselines Based on PyTorch
What are some alternatives?
CenDetect - A repository to detect degradation in images and masking such areas.
PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
DeepCreamPy-archived - Archived version of DeepCreamPy.
CRAFT-pytorch - Official implementation of Character Region Awareness for Text Detection (CRAFT)
Object_Detection_Tracking - Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20
doctr - docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Mask-RCNN-TF2 - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow 2.0
deep-text-recognition-benchmark - Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
iam-crnn-ctc-recognition - IAM Dataset Handwriting Recognition Using CRNN, CTC Loss, DeepSpeech Beam Search, And KenLM Scorer
keras-ocr - A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.
LaTeX-OCR - pix2tex: Using a ViT to convert images of equations into LaTeX code.