Britefury

Fix to replace uses of `django.utils.datastructures.SortedDict` with `collections.OrderedDict`.

Data source module for working with mini-batches from data sets

4

The `data_source` module supports extracting mini-batches from data sets in a flexible manner, supporting a range of network training schemes. It is the first part in building towards a training...

Trainer

6

New `batch` and `trainer` modules with batch iteration helper and `Trainer` class respectively, as per issue [#756](https://github.com/Lasagne/Lasagne/issues/756).

Is there interest for implementing flexible training loops, batch iteration schemes, etc. [offer of code]

17

Would the Lasagne community / developers be interested in adding code for training loops, basic DNN construction, etc? I found that code for training loops with features such as early...

Softmax and log-softmax no longer applied in models; they are now applied in the evaluation and training scripts. This was done by using `nn.CrossEntropyLoss` rather than `nn.NLLLoss`. Class predictions are...

Is there a difference between the implementations of batch normalization and ADAM in the `mnist_svhn_cifar10.nn` module and those in Lasagne?

The `FineFile` model file field specifies a custom path into which uploaded files are saved, but this does not happen; the file is placed into a generic `uploads` directory. These...

example/config.settings: MIDDLEWARE_CLASSES -> MIDDLEWARE. urls: url -> path (note that UUID URL patterns result in UUID objects that must be converted to str before passing to os.path.join) Python 3.7 environment...