-
Hey
I tried running the codes in the example but I am always getting **assertion failed**. I have also edited the variables to their values which have been used in the paper, but I am not able to s…
-
Thanks for sharing this inspiring work!
I noticed in "get_params_list_with_shape" function, "idx += length" is not added. Without this, it seems like $\mu_i$ and $s$ may not be correctly assigned f…
-
I had accidentally made my problem poorly-posed by introducing a constraint that added a row of all zeros to my A matrix
(So, one constraint was basically `l
-
The optimization method is inconsistent with the original paper, could you please provide the source of the paper for this method? Thank you
-
Hi, Thank you for approaching me efficient pruning method.
I implemented 1 of 2 pruning steps(Training & Masked retraining). While I train with train.py, 4 batch size, and 25 epoch, It implements 0…
-
In several solvers, sparse matrix is used to implement the finite difference operator as
```
len_y = len(self.y)
data = np.array([np.ones(len_y), -np.ones(len_y)])
diags = np.array([0, 1])
D = sp…
-
After indexing change negative generation for NeuroMF got a bug.
Before: negatives were sampled from [0, num_items) uniform distribution; for now it is from [0, max_item + 1) distribution.
Ids wer…
-
your project focus on CNN model compression. but I'm intersted in NLP and other transformer. I have a question that your model compession technique also apply on NLP and other transformer?. if you sen…
-
Implement proper termination criterion (either with projection before starting iterating or with two criterions according to original ALADIN paper))
-
The model cannot be download form the link: 'https://drive.google.com/file/d/1FFuauq-PUjY_kG3iiiHfDpHcG4Srl8mQ/view?usp=sharing' in the code 'pnp_admm_example.ipynb'.
There is a connect error:
Con…