Professional Documents
Culture Documents
Manish Singh(2014EE10453)
November 26, 2016
1 Aim
The aim of the project is to classify the images using Deep Convolutional Network.
2.1 CaffenetModel
Its is an image classifier built on the AlexNet architecture.
2.2 Training
2.2.1 Data Augmentation
Few classes had very few images and few were very similar to each other. Hence I merged the data few
similar classes. Still few classes very few images. To overcome this problem, I duplicated the images for
the classes having very less images.
Dataset given:
Backpack [ 408]
Bag [ 327]
Ballerinas [ 304]
Boots [ 511]
Brogues [ 104]
Espadrilles [ 133]
Flops [ 172]
Handbag [ 140]
Heels [ 28]
Loafers [ 641]
Pumps [ 117]
RunningShoes [ 846]
Sandals [1082]
Shoes [1873]
Sneakers [ 390]
Wallet [ 179]
Wedges [ 48]
1
Figure 1: CaffeNet model
2
2.2.3 Finetuning
The weights were initialised from the pretrained model on Imagenet Dataset. Only last layers (Fully
Connected) was trained. This can be done by decreasing the learning rate of the model and increasing
the learning rate of FC layers.
3 Results
Accuracy: Top1 on the 81.12%.
Accuracy: Top5 on the 95.5%.
4 Conclusion
Even after having a highly unbalanced dataset, the finetuning of pretrained Caffenet model achieves very
high accuracy in classification task.