-
Seems that the backward pass does not work with torch_max function, or I made a mistake somewhere. R code:
> m_tensor tensor([[0., 0., 0., 1.],
[0., 0., 0., 1.]], dtype=torch.float64)
…
-
### 📚 The doc issue
[The doc](https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html) of `nn.CrossEntropyLoss()` explains about `target` tensor in a complex way as shown below. *I…
-
> Please create a new issue with each of the subtasks and comment "- [ ] #issue_number" to keep the task list updated.
Define the basic tensor class :p
-
Loading model...
Computing speaker latents...
!!! Exception during processing!!! Invalid file: {'waveform': tensor([[[ 0.0042, 0.0042, 0.0044, ..., -0.1867, -0.1892, -0.1906],
[-0.0138,…
-
I feel very confused!
First of all, the latent size is different from the size of the mask and the size of the loaded image to generate the image, but some sizes will report errors. For example, I lo…
-
```python
E tripy.common.exception.TripyException:
E
E --> /tripy/tests/integration/conftest.py:45 in wrapper()
E |
E 45 | compiled_func = com…
-
We should be able to fit tensor product smooths as well as 'plain' (`s()`) smooths. This may be as simple as adding `te()` and `ti()` anywhere we are looking for `s()` ...
```
library(mgcv); libra…
-
Hi!
I've been writing a short program with MLIR and Python bindings and I noticed that adding two COO tensors and returning COO result throws an error:
```
terminate called after throwing an inst…
-
python inference71.py configs/opensora-v1-2/inference/sample.py --num-frames 4s --resolution 720p --aspect-ratio 9:16 --prompt "a beautiful waterfall"
/data/miniconda/envs/opensora/lib/python3.1…
QiuLL updated
2 weeks ago
-
Take this example:
```mlir
func.func @insert_slice_of_transfer_write(%arg0: tensor, %arg1: vector, %arg2: index, %arg3: tensor) -> tensor {
%c0 = arith.constant 0 : index
%0 = vector.transfe…