Model: Phone Binary Classification Model
Description
This model is a binary classifier designed to determine whether an object in an image is a phone or not using the FastAI library with Fastbook and ResNet-34 convolutional neural network architecture.
User may upload any images and model will define whether the image is a phone or not.
The model files can be found in the "Files and Versions section."
Training Data
- Trained on a limited dataset of 480 labeled images, with 60 images per category.
- There are 8 differnt object categories: phone, laptop, TV, DVD, tablet, camera, smartwatch, and headphone.
- Obtained using DuckDuckGo Images API
- Resized to 224x224 pixel to reduce storage.
- Fine tuned 2 epochs.
Limitation
- Model's performance may be impacted by the limited size of the training dataset and the fine-tuning epoch.
- May lose fine-grained details due to resizing which affects accuracy.
