Is this guy using multiple models and then put in them together based on the results?
This ensemble looks like multiple models and then select the best answers
Could you please elaborate on this methodology?
@gerardo, start out by searching this forum for ‘ensemble’, and you’ll find lots of info and links! Let us know if you have any follow up questions after taking a look.
While trying to fit inception v_4 on this dataset,
After enabling unfreeze and bn_freeze…(tfms,max zoom,centre crop were all used)
Also added few FC layer with dropouts…
Specifically I added 4 FC layers…
1024,256,64,16
Some details after doing so…
The validation loss seems to be of order 1e6(and increasing)
Training loss is around .4.
Accuracy is around .7…
How do I explain this ??
Deleted that .ipynb…
Will try to re create the anamoly… @ramesh
Isn’t the analogy correct that bigger the model is, better will be the results?
This is not always true. Smaller networks could train faster, so if you run for 10 epochs, smaller network might to a loss value that’s lower than a larger network. Whereas if you run for 100 epochs, the larger network, which has lot more parameters should get to a lower Training Loss.
It’s hard to tell without looking at the code. If you can put your code in gist.github.com, one of us can take a look and suggest next steps.
Actually it’s very old now…
Haven’t updated it to the latest fast.ai
Regarding the plot you can clip and replot.(answer is in the forum some where I don’t remember)
Sorry…