/Multiclass-Classification-on-STL-10-dataset-using-FineTuned-Resnet50-and-SVM-Classifier

a) Features extracted from the last fully-connected layer of pretrained Rsenet50 on ImageNet dataset is used to train a multiclass SVM classifier on STL-10 dataset

Primary LanguageJupyter Notebook

Multiclass-Classification-on-STL-10-dataset-using-FineTuned-Resnet50-and-SVM-Classifier

a) Features extracted from the last fully-connected layer of pretrained Rsenet50 on ImageNet dataset is used to train a multiclass SVM classifier on STL-10 dataset
b) Fine-tuned the ResNet 50 model for the STL-10 dataset, and evaluated the classification performance on the test set before and after fine-tuning with respect to the Class wise Accuracy.