CODEWITHSUNDEEP
machine-learningneural-networkdeep-learningcaffepycaffe
fkeufss
fkeufss

Reputation: 95

Accuracy is not improving further

I am using pre-trained GoogLeNet and then fine tuned it on my dataset for classifying 11 classes. I tried the following configurations with different base_learning rate, but the accuracy is not improving further.

  1. I used pre-trained GoogLeNet model and then doing the fine-tuning on last 10 layers and on the first 3 layers with the base learning rate 0.01 and maximum iterations to 50K, but this configuration doesn't give the accuracy better than 75%.

  2. I used pre-trained GoogLeNet model and then doing the fine-tuning on last 2 layers with the base learning rate 0.01 and maximum iterations to 50K, but this configuration doesn't give the accuracy better than 71%.

  3. I used pre-trained GoogLeNet model and then doing the fine-tuning on last 6 layers with the base learning rate 0.001 and maximum iterations to 50K, but this configuration doesn't give the accuracy better than 85%.

Can anybody tell me, what are the other methods or parameters which I can change to improve the accuracy?

Upvotes: 4

Views: 937

Answers (1)

Ashutosh Singla
Ashutosh Singla

Reputation: 739

You can use other optimisers such as ADADELTA, ADAM, and RMSPROP. In your solver.prototxt you can set this parameter by writing this command type: "RMSProp"

For RMSPROP, you can modify the parameters as mentioned here.

Upvotes: 3

Related Questions