Over 10 years we help companies reach their financial and branding goals. Engitech is a values-driven technology agency dedicated.

Gallery

Contacts

411 University St, Seattle, USA

engitech@oceanthemes.net

+1 -800-456-478-23

Development Technology

tensorflow custom object detection in 60 minutes part-1



if you have gtx 1050 ti or higher 4 gb ram and 10601080 1070 cards will only intstall tensorflow 2 or else you cant install for more information see this video

to make an image classification apk using unity easily just by changing the pb files name use the git hub code below unity is very easy to install in windows soon will be making a tutorial on that here is the magic code to make imaage classifier apk

https://github.com/Syn-McJ/TFClassify-Unity

A Guide to Retraining Object Detection Models with TensorFlow

https://3sidedcube.com/guide-retraining-object-detection-models-tensorflow/

https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/python-tutorial-od

https://www.henkboelman.com/object-detection-with-microsoft-custom-vision/

https://tech.3si.vn/2018/07/19/how-to-train-your-custom-object-with-tensorflow-object-detection-api/

http://www.jackyle.com/

http://www.jackyle.com/2017/12/train-customize-object-for-object_18.html

http://www.jackyle.com/2017/12/train-customize-object-for-object.html

Deep Learning Object Detection App on Android

https://github.com/natanielruiz/android-yolo

https://drive.google.com/file/d/0B2fFW2t9-qW3LWFDNXVHUE9rV3M/view

https://drive.google.com/uc?id=0B2fFW2t9-qW3LWFDNXVHUE9rV3M&export=download

Tensorflow Object Detection Tutorial #1 – Installation

https://www.youtube.com/watch?v=wdufj-pjE5c&index=1&list=PLoY9f-5DCBlkvkvDjwa5Dn4WXjhTA5K7v

https://www.youtube.com/watch?v=NV1g0DYb_vs&index=2&list=PLoY9f-5DCBlkvkvDjwa5Dn4WXjhTA5K7v
to test tensorflow installed for GPU use these below code or the details in the website

import tensorflow as tfwith tf.device(‘/gpu:0′):a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name=’a’)b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name=’b’)c = tf.matmul(a, b)sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))# Runs the op.print(sess.run(c))
https://medium.com/@naarkie/using-tensorflow-gpu-on-a-compute-3-0-graphics-card-in-windows-4184f4228fe9

use this for error free tensorflow object detection
cd ./tensorflow/

sudo rm -R protoc3
unzip protoc-3.2.0-linux-x86_64.zip -d protoc3

sudo mv protoc3/bin/* /usr/local/bin/

sudo mv protoc3/include/* /usr/local/include/

cd

sudo pip3 install –user tensorflow==1.12.0
sudo pip3 install –user Cython
sudo pip3 install –user contextlib2

sudo pip3 install –user matplotlib

sudo pip3 install –user pillow
sudo pip3 install –user lxml
cd ./tensorflow/PythonAPI/

python3 setup.py
cd
pwd

cd ./tensorflow/PythonAPI/

make

cd

cd ./tensorflow/models/research/

protoc object_detection/protos/*.proto –python_out=.

export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim

cd

cd ./tensorflow/models/research/object_detection/builders/

pwd

python3 model_builder_test.py

echo “successfully deployed using Robotoo”

cd

cd ./tensorflow/models/research/object_detection/

python3 fin_te.py
use this youtube channel for more information


https://www.dropbox.com/s/neu4iywv91k0ahg/robotoo.rar?dl=0

source

Author

MQ

Leave a comment

Your email address will not be published. Required fields are marked *