-
This project looks really cool!
I would love to understand at a high level how this package works -- how do you actually implement stencil computations in JAX? Do you reuse `jax.lax.scan` or someth…
-
Very good project!
I'm really interested in your DDPG algorithm with LSTM. Is it based on the paper :
> Nicolas Heess & Jonathan Hunt et al,Memory-based control with recurrent neural networks?
…
-
## Keyword: detection
### RacketStore: Measurements of ASO Deception in Google Play via Mobile and App Usage
- **Authors:** Authors: Nestor Hernandez, Ruben Recabarren, Bogdan Carbunar, Syed Ishti…
-
Use this issue to describe your benchmark and solicit feedback. A benchmark consists of a one or more ONNX network files, one or more VNNLIB property files. For each instance (combination of `.onnx` a…
-
In the docs you said inductive.js is running a BFS (breadth-first search) - and I checked the solver and was wondering if there is any kind of scheme, or even just idea, to run a parallel search to us…
-
# Deep learning is EXPENSIVE
e.g.
train ResNet50 with ImageNet dataset for 80 epochs
80 * 1.3M images * 7.7B ops per img
# Solution?
- **Data Parallelism (large batch training)**
![image](http…
-
I'm wondering if there's a mature KataGo variation that doesn't use Global Pool.
According to the paper the gpool variations train better, but they come at some cost during inference.
Is there a mod…
-
Alessandro Palma asked:
> Since I am dealing with generative modeling, I am mostly using the CytoGAN paper as a reference, together with other publications employing the dataset.
> I also tried to…
-
It appears that the batchNormWeight and batchNormBias are being updated to be equal to what I'd expect the runningVar and runningMean to be.
```
BatchNorm {batchNormWeight = IndependentTensor {toD…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…