tensorflow custom object detection part-1

if you have gtx 1050 ti or higher 4 gb ram and 1060 1080 1070 ti cards will only intstall tensorflow 2 or else you cant for more information see this video
step 1:
sudo apt-get update && yes | apt-get upgrade
step 2:
mkdir -p /tensorflow/models
step 3:
sudo apt-get install -y git python-pip
sudo pip install --upgrade pip
step 4:
sudo pip install tensorflow-gpu
if cpu only install bellow
sudo pip install tensorflow-gpu
step 5:
sudo apt-get install -y protobuf-compiler python-pil python-lxml
step 6:
sudo pip install jupyter
sudo pip install matplotlib
step 7:
step 8:
protoc object_detection/protos/*.proto --python_out=.
step 9:
jupyter notebook
more information dont be confused that we are not building a docker container less we are building a offline tensorflow object detector the link is given below

to test tensorflow installed for GPU use these below code or the details in the website

[maheshvenk]

Waiting for this Video. Sir. Thank You Very Much

[father_jesus]

How to recognize an object from a video?

[fadhelalsuwaidi]

Hi Sir
Is this tutorial work for macos ?
Thanks

[ericcute]

Hello. Thanks for your videos. Can you help me on how to save the detected object from a live feed and automatically save it as .jpg file whenever a specific object is detected e.g. Person and at the same time, it saves into .CSV file which contains “Person” as text? Thank you in advance.