Sir
if we have given an image that is not in imagenet then sir said we can do fine-tuning to get the out put sir can you please help me to understand that how fine tunning helps
Doubt in fine tunning
hey @Royal_Yashasvi ,
lets say ResNet model is trained on a variety of objects , like cars , traffic , books ,nature etc…
Now what you want is to create flower classification model , if you use the pre trained model then it would not perform well as it doesn’t understand the images of flowers so clearly , but yeah it has some understanding as it know about nature.
So , we use this understanding of it and train it again on our custom dataset , with taking pre trained weights instead of the random weights .
In this way, we are fine tuning it , meaning crystalizing the learning it has to perform better on our data.
I hope this helps.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.