-
I am a researcher in optimization and I am interested in testing algorithms for training DNNs using keras.
In practice, I would like to do something a bit different from the other optimizers, I wou…
-
##### System information (version)
- OpenCV => 3.3
- Operating System / Platform => Ubuntu 16.04 (x64-64) with QT 5
- Compiler => g++ 5.4.0
##### Detailed description
`cv::moveWindow` places …
-
I'm interested in using dlib for semantic segmentation. I think the only necessary features would be:
- Loss function - it doesn't look like loss_multiclass_log would work for this
- "Unpooling" upsam…
-
**Hi!**
First of all,
while writing something at dlib site, **thanks so much** for this high quality library !
We are using dlib as part of the shyft open-source project, at https://github.…
-
http://doi.org/10.1007/978-3-319-47898-2_21
> Automated annotation of free-text cancer pathology reports is a critical challenge for cancer registries and the national cancer surveillance program. …
-
As #1021 says, it would be good to only update the components of an Embedding layer that fire during a forward pass. In Theano, this can be implemented using the inc_subtensor method, but this would h…
-
http://doi.org/10.1002/jcc.24671
> Thousands of molecules and descriptors are available for a medicinal chemist thanks to the technological advancements in different branches of chemistry. This fac…
-
Dear Merlin Team & Community,
I'm looking for some information on multi-stream training.
This question was sparked by trying to find some documentation of the `ms_outs` argument which gets pass…
-
Hi!
I need to train and use two DNNs in parallel (kind of dueling DQN).
First DNN works ok, but when I try to call fit or predict on second one I get weird errors about input value shapes. Networks ar…
C-Pro updated
7 years ago
-
I'm trying to run the DNNS algorithm on one of the example domains.
```
from cmt import ee_authenticate
ee_authenticate.initialize()
from cmt import domain
from cmt.modis import flood_algorithms
d =…