-
`tf.gradients()`, when used on complex numbers, erroneously flips the sign of the imaginary part:
```
>>> x = tf.Variable(0. + 0.j)
>>> sess.run(tf.gradients(x*x, x), feed_dict={x:0.1j})
[-0.20000000…
-
We (meaning Cosmin, Robert, and myself) have begun working seriously
on AD in Futhark. Currently the work is being done in the
branches `troels-ad` and `cosmin-ad`. Our basic approach is
conventi…
athas updated
2 years ago
-
WIP HERE: https://github.com/lstein/stable-diffusion/compare/development...tmm1:dev-train-m1
---
I started experimenting with running main.py on M1 and wanted to document some immediate issues.
…
-
Note, 13th of February 2023: Next de facto discussion place until further notice is at #779.
————————————
So today I learned that [GitHub threads max out at 2,500 comments](https://github.com/Da…
-
The work in [_End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman_ 2021](https://www.biorxiv.org/content/10.1101/2021.10.23.465204v1) formed a differentiable alignme…
-
It seems the laziness of the compute graph construction does not allow dynamic control flows that depend on data values?
For example, in PyTorch, we can do:
```python
def foo(x):
if x > 5: #…
-
Goodfellow I, et. al. [Generative adversarial nets](https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf).
-
I want to apologize.
I may have been too quick with announcing the file format to be _finished_. I'm frankly overwhelmed with the attention this is getting. With all the implementations already ou…
-
Hi There,
May I ask what was the version of SPM12 you used when you developed this brainageR toolbox? Does it matter which version of SPM12 we are using to run this toolbox?
-
### Description
This ticket is the continuation of #7969, #7961 and #7972.
The models proposed in those tickets had as a constraint that storage.energy must have at the final time the same value it …