Machine Learning Model Deployment
Deployment Date: 2021-08-06 05:26:22 UTC
Artificial Intelligence |
Statistical Modeling |
Text Analytics |
Visualization |
Python |
Health Care | Retail |
Category: Domain Usecases
Sub-Category: Agriculture
Use-case Type: Image Classification
Private API
Uploaded Image
Note: Certain Model Inferences can take long time for the first run (Warmup) and would get faster with the subsequent inferences. We thank you for your patience.
Dandelions (Binary Image Classification) These are images of dandelions and not-dandelions( grass or other). The goal of this project is a very simple binary image classification model for me to do some "real-world learning". Dataset:https://www.kaggle.com/coloradokb/dandelionimages Model Accuracy
Initial thoughts and findings: Need lots and lots more images. While the training results in decent accuracy, the validation loss is substantial. My initial 1,200+ images (50% dandelion/50% not) seems woefully small.
Dandelions: 635
Other: 627
MobileNetV2
Validation Accuracy: 84% (We will take this as approximate accuracy and model can be more accurate in further studies with more data.)
Free ML Model Inference Powered by Cluzters.ai
Deploy and Monetize your model using our Zero Code Framework! Signup now
Connect with UsFollow us on
#datasensical