Repository files navigation

This project is a simplification of tensorflow operations and related projects

1. Tensorflow (1.4.1 - 1.15.0)pip3 install tensorflow-gpu
2. Comdutilspip3 install comdutils
3. opencv-pythonpip3 install opencv-python
4. numpy

pip3installsimple-tensor

importtensorflowastf# tensor operationsfromsimple_tensor.tensor_operationsimport*# tensor lossesfromsimple_tensor.tensor_lossesimport*# tensor metricsfromsimple_tensor.tensor_metricsimport*

This packages contains tensor operations (conv2d, conv1d, depthwise conv2d, fully connected, conv2d transpose), tensor losses (softmax & sigmoid cross entropy, MSE), and tensor metrics (accuracy). For more detail documentations about tensor operations, visitthis page

importtensorflowastffromsimple_tensor.transfer_learning.inception_utilsimport*fromsimple_tensor.transfer_learning.inception_v4import*

This package contains a library of tensorflow implementation of Inception-v4 for image classification. Densenet, Resnet, and VGG will be added in the future version. For more detail documentations about transfer learning package, visitthis page

(img source:link)

importtensorflowastffromsimple_tensor.object_detector.detector_utilsimport*fromsimple_tensor.object_detector.yoloimportYolo

This package contains a library of tensorflow implementation of Yolov3 (training and inferencing). You can customize your yolo detector with four types of network ("big", 'medium", "small", "very_small"). For more detail documentations about object detector package (yolov3), visitthis page.

(img source: pjreddie)

importtensorflowastffromsimple_tensor.segmentation.unetimportUNet

This package contains the tensorflow implementation of U-net for semantic segmentation. For more detail, visitthis page

(img source: internal)

importtensorflowastffromsimple_tensor.face_recog.insight_faceimport*

This package contains the tensorflow implementation of insight face. This repo is refractoringthis github link. For more detail documentation, visitthis page

stillonprogress ....

importtensorflowastffromsimple_tensor.convertimport*

We already prepared the all in one docker for computer vision and deep learning libraries, including tensorflow 1.12, Opencv3.4.2 and contrib, CUDA 9, CUDNN 7, Keras, jupyter, numpy, sklearn, scipy, statsmodel, pandas, matplotlib, seaborn, flask, gunicorn etc. See the list of dockerfile below:

• https://github.com/fatchur/Opencv-contribt-Tensorflow-GPU-DS-Tools-Docker/tree/master/docker-16.04

• https://github.com/fatchur/Opencv-contribt-Tensorflow-GPU-DS-Tools-Docker/tree/master/docker-18.04

• https://github.com/fatchur/Opencv-contribt-Tensorflow-GPU-DS-Tools-Docker/tree/without_gpu/docker-16.04

• https://github.com/fatchur/Opencv-contribt-Tensorflow-GPU-DS-Tools-Docker/tree/without_gpu/docker-18.04