-
##### System information
- OpenCV => 3.3.1
- Operating System / Platform => Windows 10 64 Bit
- Compiler => Visual Studio 2017 15.4.5
--> MATLAB R2017b
--> CMake 3.10.1
##### Detailed descri…
-
I try training network for regression task with optim.sgd. But I see strange thing. If I add to network > 12-16 layers to my MLP, optim does not change weights and network does not learning. Network …
-
# Overview: The Current State
- The ubuntu cuda 9.1 deb packages _appear_ to be incompl…
-
I am using PyMC3 on a regression task on a Vanilla Recurrent Neural network. The problem I am trying to solve is the Addition problem; you have two sequences of length N; the first sequence is a seque…
-
Hi! I'm sorry, but i write issue in Optim repo, but has no got answer. :(
I have a following problem:
I try training network for regression task with optim.sgd. But I see strange thing. If I add …
-
Hi There!
So far I am happy to have a working CNTK -> CortexM3 Pipeline. But I was wondering, why my results on the hardware differ so much from the test results in the Simulation in CNTK.
I used…
h4gen updated
7 years ago
-
The TF model hyperparameters used for QM7 and QM7b in `benchmark.py` should be updated to match those in `examples/qm7`. Here's the model:
model = dc.models.TensorflowMultiTaskFitTransformRegresso…
-
I'm running `Cifar10` implementation adopted for Horovod on gpu cluster (with 4 and another time 8 gpus) and I get the following error.
The code is working on the local machine when horovod codes re…
-
Hi!
First of all thank you for this great library! :-)
I've got a fairly small model (18 layers) for real-time applications, basically mainly consisting of 5 blocks of Conv2D/ReLu/MaxPool2D, and i…
-
Should I fix my system or fix the code?
```
$ python train.py
Using TensorFlow backend.
------------------------------
Creating and compiling the fully convolutional regression networks.
-----…