| # AlexNet |
|
|
| Submission for coding assignment of Fatima Fellowship. |
|
|
| ## Model Details |
|
|
| This is a simple implementation of AlexNet in Keras for the coding assignment of Fatima Fellowship. |
|
|
| ### Model Description |
|
|
| - **Developed by:** Madhav Kumar |
| - **Model type:** Convolutional Neural Network |
|
|
| ## How to Get Started with the Model |
|
|
| The files contains the notebook Alexnet_without_cropping.ipynb. It contains the code that was used to train the model. In the files, "weights-improvement-07-0.87.hdf5" contain the weights of the best model during training. |
| "logs-20230326T161429Z-001.zip" contain the logs of the training. |
|
|
| ## Training Details |
|
|
| ### Training Data |
|
|
| The files contain the training data images in train.zip and the data with image names and labels in the train.csv. |
|
|
| ### Training Procedure |
|
|
| I trained the AlexNet model on the training data on Google Colab. |
|
|
| #### Preprocessing |
|
|
| I used data augmentaion to increase the size of training data. |
|
|
| ## Evaluation |
|
|
| The model was tested on a validation data which was 20% percent of the train.zip data. The maximum accuracy obtained was 86.88%. |
