Alex Andonian

icon indicating an email [email protected]

icon company MIT CSAIL icon location Cambridge, MA icon location PhD in EECS @ MIT, studied topics in computer vision, machine learning, and AI.

Results 5 comments of Alex Andonian

out of memory when training or testing

Hi @Jessespace, As @valeriechen pointed out, reducing your batch size should fix issues with memory during training. For reference, we typically train these models using several GPUs, up to 6...

size mismatch error

Hi, This is an easy fix. You just need to squeeze the singleton dimension out by calling torch.squeeze on those weights. On Wed, May 8, 2019 at 7:21 AM AndyStrongBoy...

Dimensions in model doesn't match the dimensions in the checkpoint

Hi Yong Zhang, I suspect that you are using the latest version of PyTorch (v0.4). Can you confirm this? We have encountered this same issue since upgrading. In the most...

Error running example

Hi, This issue is related to upgrading to the latest version of PyTorch (v0.4). See this [issue](https://github.com/metalbubble/TRN-pytorch/issues/10) for a potential solution. Let me know if this helps. Best, Alex A.

Error running example

@hcen001, The pretrained models we release all need to be given 8 frames. This function [here](https://github.com/metalbubble/TRN-pytorch/blob/master/test_video.py#L52) attempts to select 8 equally spaced frames from the ones you provide. In your...