- Developed NN for fve way classifcation of 10k,16×16 RGBA images using softmax activation and cross entropy loss
- Improved F1-score by varying hidden layer size and depth, and employing mini-batch SGD with adaptive learning rates
- Achieved a maximum accuracy of 76% across fve diferently shaped objects using sigmoid and ReLU activation
ronakkalvani/Deep-Learning-Techniques-To-Predict-Number-Of-Objects-In-Image-
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|