-
I created a model using autoencoder using the mnist_autoencoder.prototxt. But I have problems evaluating the model. How do I test the model? Previously for other models, I use classifer.py or tools/ca…
-
Here is the buggy code from filler.hpp line 77. As mentioned in the comment, the number of inputs is taken from blob->height() when it actually should be blob->width(). I first noticed this error wh…
-
Could I request a test problem for the Adam optimizer, just to understand how it works better? Thanks :+1:
I tried to use the new adam optimizer on the rosenbrock test problem in `optim`, used for a…
ghost updated
9 years ago
-
Hi, thanks for making this great implementation open source.
I working on a similar implementation in torch, (but it's not working yet either without or with filterbanks/attention), and I'd like to u…
ghost updated
9 years ago
-
```
e = theanets.Experiment(
theanets.recurrent.Regressor
#theanets.recurrent.Autoencoder
,layers=(1, 10, 1)
,batch_size=1
)
```
gives
```
TypeError: Cannot convert Type TensorTy…
-
The ADAM optimizer is now available in the torch `optim` module.
https://github.com/torch/optim/blob/master/adam.lua
Might be interesting to swap RMSProp for this
ghost updated
9 years ago
-
The final goal of cuSAE is to train a sparse autoencoder to classify the MNIST dataset, while using CUDA C to implement expensive computations.
First we need to add MATLAB code that imports the data…
-
Does Caffe support input data without labels?
The tutorial says when input is images , we need to provide the images and its labels.
Could I omit the label in the source file?
-
I am trying to learn a MLP, and I wanted to split the learning into a two steps, first run is using some run1.yaml file and saving to model.pkl and the second should (in a separate yaml file) should l…
-
When I run the Mnist example script train_lenet_consolidated.sh,I have the error:
I0821 16:18:39.763087 16037 solver.cpp:156] Creating testing net (#1) specified by net_param
I0821 16:18:39.763173 160…