CS194-26 Project 4: Classification and Segmentation
Vincent Zhu
The best results were achieved with a batch size of 64, with 32 channels for both convulational layers and 1568->68->10 features for the fully connected layers. I used Cross entropy loss and Adam with a learning rate of 0.005.
Training Accuracy Over 100 Epochs:
Test Set Accuracy: 89.69%
Per Class Accuracy:
'T-shirt/top': 83.6%
'Trouser': 98.7%
'Pullover': 81.2%
'Dress': 88.3%
'Coat': 89.9%
'Sandal': 98.7%
'Shirt': 67.5%
'Sneaker': 94.6%
'Bag': 98.2%
'Ankle Boot: 96.2%
Hardest classes to identify: "Shirt" and "Pullover"
Correctly identified images: (two of each class, in the order listed above)
Misclassified images: (two of each class, same order)
Visualized filter from first layer: