uzbekdev1 / fruit-detector

Implementation of TensorFlow Object Detection API on fruit images.

Fruit-Detector

Implementation of TensorFlow Object Detection API on Windows 10 with fruit images without Anaconda Distribution.

Changes

No Anaconda Distribution. Use command prompt instead of Anaconda Prompt.

1)Don't use the below commands in 2d.

conda create -n tensorflow1 pip python=3.5

activate tensorflow1

2)Change the command below in 2d

conda install -c anaconda protobuf

to this

pip install protobuf --upgrade

3)Download protoc.exe from here . Copy protoc.exe(in bin folder) to C:\tensorflow1\models\research.

Then run 2f.

4)Before step6, open C:\tensorflow1\models\research\object_detection\utils\learning_schedules.py with a text editor.

Change the line 168 from

range(num_boundaries)

to

list(range(num_boundaries))

Data

Data can be downloaded from here. 240 training images 60 test images. No problematic image.

3 different types of fruits: Apple, Banana, Orange.

.xml files in data have coordinates of objects.

Training

I trained it on a GTX 1050 for 5 hours. Approximately 53000 iterations.

Implemented Model

Faster R CNN inception v2 model.

Youtube Video

Results on images

Input Image	Output Image

Input Image	Output Image

Input Image	Output Image

Input Image	Output Image

Input Image	Output Image

Credits

Credits go to EdgeElectronics. I just followed the steps in the tutorial.