You will get Image labeling webapp using Tensorflow.js
You will get Image labeling webapp using Tensorflow.js
Project details
The objective of this work was to create a web application that can automatically label images that are in a GitHub repository. The user inputs the Github repository url and the web application outputs a table/csv file of each repo image with a label. This application is useful for creating supervised image prediction models, because it is necessary to have a reliable label for each image that a supervised model will be trained on.
There are three tiers of this workflow: Webapp code-Tensorflow models, Webapp code-Custom model, Webapp code-Custom BigData.
Tier 1: read images from a GitHub repo, use a pre-trained Tensorflow.js model (mobilenet or ssdcoco) to detect objects in each image, create a table of the image name and predicted label.
Tier 2: perform tier 1 functionality and train a Custom trained Tensorflow model specifically for the data.
Tier 3: perform tier 2 functionality and efficient memory usage strategies, such as batching reading and writing data to Cloud Storage, to accommodate large quantities of data (Big Data).
There are three tiers of this workflow: Webapp code-Tensorflow models, Webapp code-Custom model, Webapp code-Custom BigData.
Tier 1: read images from a GitHub repo, use a pre-trained Tensorflow.js model (mobilenet or ssdcoco) to detect objects in each image, create a table of the image name and predicted label.
Tier 2: perform tier 1 functionality and train a Custom trained Tensorflow model specifically for the data.
Tier 3: perform tier 2 functionality and efficient memory usage strategies, such as batching reading and writing data to Cloud Storage, to accommodate large quantities of data (Big Data).
Machine Learning Tools
TensorFlowWhat's included
| Service Tiers |
Starter
$30
|
Standard
$400
|
Advanced
$800
|
|---|---|---|---|
| Delivery Time | 7 days | 14 days | 45 days |
Number of Revisions | 0 | 1 | 1 |
Number of Model Variations | 0 | 1 | 1 |
Number of Scenarios | 1 | 1 | 1 |
Number of Graphs/Charts | 1 | 1 | 1 |
Model Validation/Testing | |||
Model Documentation | |||
Data Source Connectivity | - | - | - |
Source Code |
About Jamilah
Data Scientist | modeling, cloud, scientific computing
Lyon 03, France - 7:29 am local time
Steps for completing your project
After purchasing the project, send requirements so Jamilah can start the project.
Delivery time starts when Jamilah receives requirements from you.
Jamilah works on your project following the steps below.
Revisions may occur after the delivery date.
Model insertion
For the Starter project, insert the mobilenet for single object detection and/or the ssdcoco model for multiple object detection per image. For the Standard and Advanced projects, train and validate a custom object detection model per client request.
Create/edit an instruction manual explaining the application