Recipes
Recipes copied to clipboard
Lasagne
Lasagne recipes: examples, IPython notebooks, ...
I have a model, for which i need to compute the gradients of output w.r.t the model's input. But I want to apply some custom gradients for some of the...
@FabianIsensee I am trying to modify the categorical_crossentropy loss function to dice_coefficient loss function in the Lasagne Unet example. I found [this](https://github.com/jocicmarko/ultrasound-nerve-segmentation/blob/master/train.py#L21-L29) implementation in Keras and I modified it for...
Unfortunately, this comes a bit late as theano has recently merged a PR adding some bindings to warp-ctc (https://github.com/Theano/Theano/pull/5949). But I wanted to finish this anyway, so here it is...
Hi, I try to run the resnet-32 model on cifar-100 dataset, with only the difference of the training data in "Deep_Residual_Learning_CIFAR-10.py", but it causes the error like this: ``` Starting...
Presently, Lasagne/Recipes does not seem to provide an example of an object detector. Our contribution is a high-performance, low-complexity single-shot detector (SSD). This detector is based on the SqueezeDet paper...
added Generating fonts with adversarial networks example
Hi following the Guided Backpropagation recipe/example I had error for: `if theano.sandbox.cuda.cuda_enabled` because, I guess, I use newer theano / lasagne versions with CuDNN etc. I have no cuda under...
Hi, this is the line 190 of variational_autoencoder.py: - 0.5 * T.sqr(tgt - mu) / T.exp(2 * ls)) where does that `2` coefficient for the log sigma come from? I...
We can have an example of a Siamese network (similar to Sander Dieleman's [suggestion](https://github.com/Lasagne/Lasagne/issues/168#issuecomment-81134242) ) and convolutional spatial transformer as discussed [here](http://papers.nips.cc/paper/6487-universal-correspondence-network.pdf). From my understanding, the convolutional spatial transformer applies...
After training the script prints some segmentation results. These are mostly empty and suggest that the network did not train properly (which is not the case). This is due to...
