-
This issue describes the initial ideas for the overall plan and opens it for discussion. While issue #337 explains some of the details, however, it is more focused on assigning dynamic kernels to deve…
-
## 🐛 Bug: Quantization - we need a better solution for tracking quantization backend settings in a model
Currently, there are various points of confusion:
1. a target backend (qnnpack / fbgemm) is…
vkuzo updated
12 months ago
-
Whereas NumPy correctly uses the `int64` dtype, Aesara doesn't until it's told to:
```python
>>> np.array(- (2**32))
array(-4294967296, dtype=int64)
>>> at.constant(- (2**32))
TensorConstant{…
-
## Start with the `why`:
The `why` of this effort (and initial research) is that any many applications depth cameras (and even sometimes LIDAR) are not sufficient to successfully detect objects in …
-
EfficientDet: Scalable and Efficient Object Detection
* paper: https://arxiv.org/abs/1911.09070v1
> First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows ea…
-
The tools for measuring video quality based on a reference video http://www.scikit-video.org/stable/measure.html are very useful.
As a convenience feature, it would be nice to easily get a human-view…
-
did you successfully train on the 10M web videos?
I'm looking at exploring this suggestion for 4 lies of code change.
https://github.com/guoyww/AnimateDiff/issues/308
-
I'm comparing performance of the built-in Dense layer with an equivalent Linear layer and a Dist layer. There are a couple of problems.
Full code, output, Manifest, Project: https://gist.github.com…
-
Hello I am trying to run the model using model parallelism. I have made some changes in the prototext file. I am attaching the changed file with this post. I am not getting the error which I faced be…
-
Do any of the supported core.matrix implementations cover sparse matrices? If not, what would you recommend for inclusion?