Single Classification MobileNet v2 Active
Upload Image
Drag & drop or click to browse
Results
Model Selection Ready
Batch Image Classification
Upload multiple images for batch processing
Results (0 items)
| Image | Filename | Top Prediction | Confidence | Inference Time |
|---|
Train Custom Model
1. Dataset
Upload a CSV file (label, pixel1...pixel784) or use the default MNIST handwriting dataset.
2. Configuration
Training Progress
Model Explainability (Grad-CAM)
Grad-CAM creates a heatmap highlighting the regions of the image that led to the prediction.
How it works
We compute the gradient of the winning class score with respect to the feature maps of the
last convolutional layer. These gradients tell us how important each feature map is. We
weight the maps and generate a heatmap.
Note: This requires the custom trained model or compatible layer access.