-
The Keras interface works fine but I had to change the Binary Encoding.
TensorFlow’s Graph Mode relies on Symbolic Tensors, which act as placeholders without actual data during initial model checks…
-
**Problem/Use Case**
Is the input for scenedetect limited to video file paths? Does it support inputting tensors, such as videos read using [decord](https://github.com/dmlc/decord)? Additionally, c…
-
From the community:
> [Lack of `__setitem__` for tensors. I had to emulate it and it isn't pretty.](https://discord.com/channels/863154240319258674/1177107133167321158/1293966833463988297)
-
Would it be possible to add a pretty print function for dense tensors. Here is what I have in mind:
```
def pretty_print_tensor(X, fmt="10.4f", name="Slice"):
if not isinstance(X, ttb.tensor)…
-
I am trying to implement DeepPhase in candle but I am struggling figuring out how to calculate the phase angles from two tensors using `atan2` operation.
-
Hello @ziqi-jin, thanks for your incredible contribution!
When I run python train.py, it shows some problems below:
Traceback (most recent call last):
File "train.py", line 45, in
runner.tr…
-
### 🐛 Describe the bug
Tensors saved in `medusa_only_heads` mode are empty.
Ref: https://github.com/linkedin/Liger-Kernel/blob/main/examples/medusa/train.py#L392
### Reproduce
_No response_
### V…
-
@wiseodd
Tldr; Issue with tensors of size (B, L, D) passing through a `Linear` last layer
Here's the minimal reproducible example:
```python
import torch
import torch.nn as nn
from laplace i…
-
Thanks for this awesome work!
We can train the model in all scenes of the Nvidia dynamic dataset but encounter some problems in the kid-running scene:
 and [discussions](https://github.com/ultralytics/ultralytics/discussion…