ML Model Repository from Pinto0309

#

Introduction

#

Using AI we can solve many kinds of tasks for this input can be text, structured data, image, video, audio, time-series, etc. To solve these problems we need to train model. These models may be computer vision, NLP, or traditional machine learning kind. There are hundreds of architectures and algorithms to solve business problems and create models. There a hundreds of different datasets that can be along with a particular architecture or algorithm to solve the problem. If you have any of these tasks then you can explore using these pre-trained models to solve your problem. There is a GitHub user “Katsuya Hyodo” with GitHub account “PINTO0309”. He has trained hundreds of models and created these pre-trained models for the community. You can scan and explore them from there. From there you can download the pre-trained models.

Supported Formats

#

• WQ = Weight Quantization
• OV = OpenVINO IR
• CM = CoreML
• DQ = Dynamic Range Quantization
• FP32 = Floating Point 32
• FP16 = Floating Point 16
• INT8 = Integer
• TPU = Tensor Processing Unit
• TFJS = Tensorlfow javascript
• TF-TRT = ensorFlow-Tensor Run Time
• ONNX = Open Neural Network Exchange

1. Image Classification

#

Number in the tables below is from the main repository

2. 2D Object Detection

#

3. 3D Object Detection

#

4. 2D/3D Face Detection

#

5. 2D/3D Hand Detection

#

6. 2D/3D Human/Animal Pose Estimation

#

7. Depth Estimation from Monocular/Stereo Images

#

8. Semantic Segmentation

#

9. Anomaly Detection

#

10. Artistic

#

11. Super Resolution

#

12. Sound Classifier

#

13. Natural Language Processing

#

14. Text Recognition

#

15. Action Recognition

#

16. Inpainting

#

17. GAN

#

18. Transformer

#

19. Others

#

4. Reference articles

#

1. Pinto Model Zoo
2. [deeplab] what’s the parameters of the mobilenetv3 pretrained model?
3. When you want to fine-tune DeepLab on other datasets, there are a few cases
4. [deeplab] Training deeplab model with ADE20K dataset
5. Running DeepLab on PASCAL VOC 2012 Semantic Segmentation Dataset
6. Quantize DeepLab model for faster on-device inference
7. https://github.com/tensorflow/models/blob/main/research/deeplab/g3doc/model_zoo.md
8. https://github.com/tensorflow/models/blob/main/research/deeplab/g3doc/quantize.md
9. the quantized form of Shape operation is not yet implemented
10. Post-training quantization
11. Converter command line reference
12. Quantization-aware training
13. Converting a .pb file to .meta in TF 1.3
14. Minimal code to load a trained TensorFlow model from a checkpoint and export it with SavedModelBuilder
15. How to restore Tensorflow model from .pb file in python?
16. Error with tag-sets when serving model using tensorflow_model_server tool
17. ValueError: No ‘serving_default’ in the SavedModel’s SignatureDefs. Possible values are ’name_of_my_model’
18. Configure input_map when importing a tensorflow model from metagraph file
19. TFLite Model Benchmark Tool
20. How to install Ubuntu 19.10 aarch64 (64bit) on RaspberryPi4
21. https://github.com/rwightman/posenet-python.git
22. https://github.com/sayakpaul/Adventures-in-TensorFlow-Lite.git

Author
Dr Hari Thapliyaal
dasarpai.com
linkedin.com/in/harithapliyal