license: bsd
language:
- en
metrics:
- accuracy
tags:
- climate
- trash
- classifier
- water
- aquatic
- pollution
- environment
datasets:
- brsdincer/garbage-collective-data-for-nature-conservation
- harshpanwar/aquatrash
model-index:
- name: Trashnet r = 1
results:
- task:
type: trash-classification
dataset:
type: aquatic-trash
name: combined-trash-images
metrics:
- type: accuracy-radius
value: 27.47
Trashnet - Trash Identification model for forensic trash cleanup
Overview
This model takes images or video frames as input, and identifies the most likely types of trash present in the scene. The model has been specifically built for aquatic trash, but performs almost equally well on terrestrial trash.
Usage
The model has been trained on 120 x 120 RGB images. To evaluate the contents of an image, you will need to pass in a tensor of shape (120,120,3).
Output consists of a 10-d tensor of class probabilities.
Training and Classes
Trained for 22 epochs on 3500 data points.
Class labels
trash_classes = ['battery','biological','glass','cardboard','clothes','metal','paper','plastic','shoes','trash']
Mapping common trash types from training data together
class_to_idx = {
'battery':0,
'biological':1,
'glass':2,
'brown_glass':2,
'green_glass':2,
'cardboard':3,
'clothes':4,
'metal':5,
'paper':6,
'plastic':7,
'shoes':8,
'trash':9
}
Limitations
The model has limited training data of trash in the environment. Additionally, the model overrepresents plastic and glass in its predictions due to sampling bias and visual similarities between plastic, glass, and other common types of trash. As a solution, the model is marked as 'correct' when the correct label is within the model's top N most predicted trash types.
n = 3 gives the most appropriate results.