Kaushalya Madhawa

icon indicating a website link http://kaushalya.github.io/ icon indicating an email [email protected]

icon location Tokyo, Japan icon location Building machine learning models.

Results 6 comments of Kaushalya Madhawa

Use custom test-time augmentations

Hi, Thanks for checking the PR. Vertical flipping helped in my case where I was training a classifier on a private medical imaging dataset. Vertical flip and minor rotations improve...

TF Movinet - TF op 'StatefulPartitionedCall' not implemented.

I too ran into this error while converting a TF model (tensorflow==2.15.0) to coreml using coremltools==7.1. The tensorflow graph is generated from a JAX model using jax2tf. Is there a...

host/load pretrained weights for 3D resnet

I could load most parameters from the state dictionary excluding `layerx.0downsample.0.bias` by just updating the keys. Every key in the pre-trained state dict has a prefix 'module.'. I could get...

LIPIS-based content loss is missing

Thanks a lot. Sorry, I had the impression this is an official implementation.

Size Mismatch Issue

I'm still having this issue on `unsloth==2024.9.post4`. Is there any quick fix?

AttributeError: 'AdamW' object has no attribute 'train'

Upgrading `accelerate` to 0.34.2 solved the issue.