search

yun-liu / RCF

Richer Convolutional Features for Edge Detection
Other
758 stars 260 forks source link

About training processing #16

Open xurong1981 opened 6 years ago

xurong1981 commented 6 years ago

I adjusted some parameters for training and it can successfully make a fine tuning for my own training data. I made a 40000 iterations for the first fine tuning. After the fine tuning, can I show loss values by a graph based on log files? Also, can I show a graph on accuracy ? How should I do for such purpose ? By the way, I make predict on my own data, and the fine-tuned model can perform very well, but I wonder whether it is over-fitted. Do you know how to confirm whether the fine-tuned model is over-fitted ?

xurong1981 commented 6 years ago

One more thing I want to confirm, that is the source is based on Caffe, not Caffe2, right ?

yun-liu commented 6 years ago

Our code is built on Caffe (https://github.com/BVLC/caffe), not Caffe2. You can refer to Caffe for how to plot figures. Besides, you can divide your data into training and test sets to confirm whether the fine-tuned model is over-fitted. You can also refer to other machine learning methods for the confirmation of over-fitting.

xurong1981 commented 6 years ago

I ses. Thank you.