Puneet Mangla

icon indicating a website link https://github.com/Puneet2000 icon indicating an email [email protected]

icon company @InferoIITH @Kludge-IITHyderabad icon location IIT Hyderabad icon location Machine Learning | Computer Vision | Networks | Android Developer | Java and Python | CSE @iit Hyderabad | Intern @adobe Noida.

Results 4 comments of Puneet Mangla
trafficstars

Add support for Inductor + symbolic shapes + training

Hi, Is there an example or tutorial I can follow to understand and try out dynamic shapes better?

Small datasets

Hi @e-271 Were you able to prepare data as it looks in the paper?

Can't reach specified accuracy on CUB dataset ResNet10

The number of epochs is 200. Here is the loss for last epoch, last batch: Epoch 199 | Batch 360/368 | Loss 0.636699 The result is reproduced from the freshly...

Can't reach specified accuracy on CUB dataset ResNet10

@yuxiwang93 are your results from original code ? And are u getting comparable results on 5-shot also ?