Skip to content

supfree-hackathon/MS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Waste Allocation & Recognition Project

Info: pile_dataset

Images 0.jpg to 555.jpg are part of wade-dataset, all the other images are from google street view and 
annotated by me, because of the little time I had there should be some mistakes, feel free to email me
if you find any!

Info: pile_model

This model was trained using the pretrained model: ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8, 
to run this model download the tensorflow-object-detection api. 

Load the model using the script object_detection_tutorial.ipynb in models/research/object_detection/colab_tutorials/

replace PATH_TO_LABELS = 'models/research/object_detection/data/mscoco_label_map.pbtxt' 
with the directory of the label_map.pbtxt that I provide in the repo.

replace detection_model = load_model(model_name) with detection_model = tf.saved_model.load('__path to pile_model__')

you are ready to go!

Contact: www.maestrostudio.org

About

TID: 12

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors