Shivansh Rao
Shivansh Rao
Hi @zuru could you please show an example of how you are using MappedConvolution in your network? I am still trying to understand that however facing difficulties. Thank you
thanks, it helps! I am also following your scene understanding repo for more details. do you have the code for the color part?
even after downloading the data I get the same error.
hi, shouldn't the data be like ./Data/Train/Fear/013736360/ 1.jpg 2.jpg 3.jpg (these are the frames). I have starred.
Hi I am sorry for such a late reply and I hope you are staying safe! yes the code is complete, although you can go look at my other repository...
pretrained provides 46% on afew whereas the paper reports 51. what could be the scope of improvements?
thanks @wildermuthn . I will try this and get back in case I have more queries.
Hi yes it is a boost. I will share it soon.
Sorry for the long delay, I have uploaded the matlab file that generates the Optical flow data!
your work is really interesting I want to reproduce training could you please try to upload the training code as soon as you get some time please?