How to setup Object Detection API on Jupyter notebook

computer-vision

#1

I’m using Object Detection API and I got stuck in a problem.

I have to run file train.py in Jupyter Notebook(Must copy all code in that file and run in Jupter notebook, not just !python3 train.py). But when I run

# From tensorflow/models/research/

!./bin/protoc object_detection/protos/*.proto --python_out=. !export PYTHONPATH=$PYTHONPATH:pwd:pwd/slim !python3 object_detection/builders/model_builder_test.py

I got error ImportError: No module named 'object_detection'.

I don’t know why, but when I run this in Terminal, the result is OK. I only got problem with Jupyter notebook.

Anyone know how to solve this problem?

System information What is the top-level directory of the model you are using:(I don’t really understand the meaning of “top-level directory of the model”) I just followed https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

I used faster_rcnn_nas_lowproposals_coco downloaded from

OS Platform and Distribution: Ubuntu 16.04 TensorFlow installed from: GPU version of Tensorflow TensorFlow version: v1.12 Bazel version: NA: don’t know what is Bazel CUDA/cuDNN version: NA: don’t know, but it’s not the related to the problem GPU model and memory: Titan V Exact command to reproduce: NA