Vishal Thengane

icon indicating a website link https://vgthengane.github.io

icon company University of Surrey, UK; University of Wollongong, Australia icon location Earth icon location PhD Student | Continual Learning | Multimodal Models | 3D Vision

Results 5 issues of Vishal Thengane

RESOURCE_EXHAUSTED: Out of memory while trying to allocate # bytes.

Hi, I am trying to run the model on a CIFAR100 dataset. I am getting the following error. I have 4 Tesla V100 GPUs. ``` 2022-08-05 10:00:26.833817: W external/org_tensorflow/tensorflow/core/common_runtime/bfc_allocator.cc:479] Allocator...

Accuracy variation with the CLIP model

1 comment

I am trying to integrate the CLIP model with DyTox. The evaluation accuracy with default config for `task=0`, `after epoch=0`, and `num_gpus=4` is `60.5%`. When I add a single line...

SVHN dataset images are of size 32x32x3

SVHN dataset image size is 32x32x3 and not 28x28x1.

Loss is NaN.

1 comment

Hi @Lee-JH-KR, Thank you for realising the PyTorch version of L2P. I am getting the following error. Do you have any suggestions for it? ```Loss is nan, stopping training.``` I...

Anybody observe slow training speed for mamba compared to transformer model?

2 comment