"tests/configs/det_r50_db.yml" did not exist on "5e38ec57a61d404b73c26a666810bec0da8f4ec4"
README.md 1.74 KB
Newer Older
A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
1
# CircularNet
Fan Yang's avatar
Fan Yang committed
2

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
3
4
Instance segmentation models for identification of recyclables on conveyor
belts.
Fan Yang's avatar
Fan Yang committed
5

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
6
7
Note that these are demo models, reach out to
waste-innovation-external@google.com for updated versions of the models.
Fan Yang's avatar
Fan Yang committed
8

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
9
## Overview
Fan Yang's avatar
Fan Yang committed
10

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
11
12
13
14
15
16
Mask RCNN is a state-of-art deep learning model for instance image segmentation,
where the goal is to assign instance level labels ( e.g. person1, person2, cat)
to every pixel in an input image. Mask RCNN algorithm is available in the
TensorFlow Model Garden which is a repository with a number of different
implementations of state-of-the-art models and modeling solutions for TensorFlow
users.
Fan Yang's avatar
Fan Yang committed
17

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
18
## Model Categories
Fan Yang's avatar
Fan Yang committed
19

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
20
21
22
23
24
25
-   Material model - Detects the high level category (e.g. plastic, paper, etc)
    of an object according to its material type.
-   Material Form model - Detects the category of the of an object according to
    its physical product formation (e.g. cup, plate, pen, etc).
-   Plastic model - Detects the category of a object according to its plastic
    types (e.g. HDPE, LDPE, etc)
Fan Yang's avatar
Fan Yang committed
26

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
27
28
> The goal to develop these models is to bring transparency & traceability in
the world of  waste recycling.
Fan Yang's avatar
Fan Yang committed
29

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
30
## Model paths in GCP buckets
Fan Yang's avatar
Fan Yang committed
31

A. Unique TensorFlower's avatar
A. Unique TensorFlower committed
32
33
34
35
36
| Model categories | Model backbone | Model type | GCP bucket path |
| ------ | ------ | ----- | ------ |
| Material Model | Resnet | saved model & TFLite | [click here](https://storage.googleapis.com/tf_model_garden/vision/waste_identification_ml/material_model.zip) |
| Material Form model | Resnet | saved model & TFLite | [click here](https://storage.googleapis.com/tf_model_garden/vision/waste_identification_ml/material_form_model.zip) |
|Plastic model | Resnet| saved model & TFLite | [click here](https://storage.googleapis.com/tf_model_garden/vision/waste_identification_ml/plastic_types_model.zip) |