deq
deq copied to clipboard
locuslab
[NeurIPS'19] Deep Equilibrium Models
Greetings! For my application, I need higher order (>= 2) derivatives of the equilibrium point. I realize that doing this with the current implementation is quite inefficient, as it requires...
Heya, thanks for the great paper(s) :) Initially I've had to fix a few things to make your code run, but now I find it very slow and I'm wondering...
Heya, Thanks for your continued work in building better DEQs. The main selling point of DEQs is that the solver can take as many steps as required to converge without...
Hi, I've been trying to reproduce the results reported in the paper, and noticed that Table 4 in Appendix A does not incorporate the hyperparameters used for training MDEQ-XL on...
Hi! I am trying to run some initial experiments using the pretrained MDEQ model on ImageNet dataset. As instructed in the [README](https://github.com/locuslab/deq/blob/master/MDEQ-Vision/README.md), I download the (small) model from [here](https://drive.google.com/file/d/12ANsUdJJ3_qb5nfiBVPOoON2GQ2v4W1g/view?usp=sharing) and...
I use this command `CUDA_VISIBLE_DEVICES=0,1 python tools/cls_train.py --cfg experiments/cifar/cls_mdeq_TINY.yaml` and got this error 'Expected a 'cuda' device type for generator but found 'cpu' '
Hi, I have a question about memory footprint of DEQ. As far as I understand, DEQ does not need to store intermediate activations, and thus able to approximate infinite-layer model...
Fkjvsvku vkfogg shkevn doth shout dh Dbouw sgljfcdofbfv thigh Irish shoot Xbvoiev scouts fkkggfitvcitg scouts who have Fkyhv adiyv Uiorvc sgitv Shot shoot Doug sfktfceg sigh stirs Gilt Erin sxkktv...
