Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Keras | 57,713 | 330 | a day ago | 68 | May 13, 2022 | 372 | apache-2.0 | Python | ||
Deep Learning for humans | ||||||||||
Data Science Ipython Notebooks | 23,924 | 5 months ago | 26 | other | Python | |||||
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines. | ||||||||||
Mask_rcnn | 22,777 | 15 days ago | 5 | March 05, 2019 | 1,933 | other | Python | |||
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow | ||||||||||
Netron | 21,736 | 4 | 63 | 21 hours ago | 489 | July 04, 2022 | 22 | mit | JavaScript | |
Visualizer for neural network, deep learning, and machine learning models | ||||||||||
100 Days Of Ml Code | 17,892 | a year ago | 9 | mit | Jupyter Notebook | |||||
100-Days-Of-ML-Code中文版 | ||||||||||
D2l En | 16,954 | 8 days ago | 83 | other | Python | |||||
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge. | ||||||||||
Ncnn | 16,728 | 7 hours ago | 19 | July 01, 2022 | 959 | other | C++ | |||
ncnn is a high-performance neural network inference framework optimized for the mobile platform | ||||||||||
Onnx | 14,330 | 148 | 245 | 20 hours ago | 26 | June 18, 2022 | 370 | apache-2.0 | Python | |
Open standard for machine learning interoperability | ||||||||||
Horovod | 13,133 | 20 | 10 | 2 days ago | 72 | June 21, 2022 | 344 | other | Python | |
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet. | ||||||||||
Best Of Ml Python | 13,088 | 3 days ago | 15 | cc-by-sa-4.0 | ||||||
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly. |
基于Tensorflow和Keras实现端到端的不定长中文字符检测和识别
sh setup.sh
将测试图片放入test_images目录,检测结果会保存到test_result中
python demo.py
详见ctpn/README.md
数据集:https://pan.baidu.com/s/1QkI7kjah8SPHwOQ40rS1Pw (密码:lu7m)
图片解压后放置到train/images目录下,描述文件放到train目录下
cd train
python train.py
val acc | predict | model |
---|---|---|
0.983 | 8ms | 18.9MB |
可参考SynthText_Chinese_version,TextRecognitionDataGenerator和text_renderer