-
I have pretrained the V2 simclr on Cifar10 as below:
`! python run.py --train_mode=pretrain --train_batch_size=256 --train_epochs=400 \
--learning_rate=0.2 --learning_rate_scaling=sqrt --proj…
-
![image](https://user-images.githubusercontent.com/23263731/200564311-220f4f34-3d31-4eb5-a5d1-6af2683cab5a.png)
![image](https://user-images.githubusercontent.com/23263731/200296378-68401e7c-…
-
Hi Matthias,
I am using GCNConv to solve a prediction task problem with linear layers at the output of the GNN. The model is trained on graphs of 10K nodes with ~20K-40K edges. The gradient value d…
-
## 🚀 Feature
It would be great to have a library of optimization routines for the deterministic setting (a la `scipy.optimize`) using PyTorch autograd mechanics. I have written a [prototype library](…
-
I've pretty much copy-pasted the code [here](http://tflearn.org/tutorials/quickstart.html#source-code) and still getting an error. Listing the log below:
```
IndexError …
-
For a graph based library, the internal nodes should probably be written in a better language than Python.
As a result the performance isn't comparable to similar solutions in c++ when it could be.
-
Hi,
In the active learning for regression example, we have used gaussian processes. While the sklearn version seems to keep its length scale and noise parameters static ( maybe i am doing something…
-
Hi @zhangyuc:
I have seen your paper about splash. I want a question:
Is the experiment "in Local solutions with unit-weight data" the same with spark mllib currently imp? BTW,According to my exp…
-
The [`DenseVariational`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/DenseVariational) provides the `kl_weight` parameter, whose documentation is
> **`kl_weight`**: Amount by …
-
The following bench, reduced to only call `linear` which is just a thin wrapper around BLAS, takes 1.6s without `-d:openmp` and 15s with `-d:openmp`
```Nim
import ../src/arraymancer
# Learning …