-
## 🐞Describing the bug
```
Traceback (most recent call last):
File "/media/anlab/data-2tb/ANLAB_THUY/ImageSearcher/ConvertSolar2Coreml.py", line 119, in
mlprogram = ct.convert(
File "/ho…
-
Hi,
I'm trying to implement the [attention mechanism](https://arxiv.org/abs/1701.01811) on tree-structured neural networks, such as TreeLSTM or TreeGRU. Since we want to attend to the most informati…
-
Hey there,
I really enjoy your network/implementation but have some questions about improving my results :) **As you know this baby best it would interest which parameters I should try to change to i…
-
```
import threading
import torch
def foo(x, y):
a = torch.sin(x)
b = torch.cos(y)
return a + b
opt_foo1 = torch.compile(foo, mode="max-autotune")
threads = []
for _ in rang…
-
First figure out where and how to seed by hand...should we write it as a lisp? is that easy? Where does it plug in? Do we like how it plugs in? Can we make a script that goes from downloaded pretraine…
-
We should build a method to allow users to find the top eigenvector of a linear operator defined by a tensor network.
My API proposal is as such
```
tensor = tn.eigensolution(in_edges=list_of_e…
-
**TL;DR:** Implementing block-sparse operations for faster matrix-multiplication.
Is this something worth adding to PyTorch?
Goals:
1. Faster matrix-multiplication by taking advantage of block-…
-
hello, in **quant_train_module.py** file, i saw a line of code : y.data.copy_(yq.data), this code change the data of relu's output data.data, in order to use it in backword for calculate activation's…
-
### 🐛 Describe the bug
I am using NaNDetect in the llama2.c project to track down NaNs during training.
https://github.com/karpathy/llama2.c
I works when device='cpu' but gets the exception whe…
-
While the authors claim to be doing a convolution, even going as far as naming their tool CellCnn, they are doing a stride of 1 which is essentially a dense layer. Further, you say they used the "mos…