{
    "info": {
        "author": "Lasagne contributors",
        "author_email": "lasagne-users@googlegroups.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.4",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": ".. image:: http://img.shields.io/badge/docs-latest-brightgreen.svg\n    :target: http://lasagne.readthedocs.org/en/latest/\n\n.. image:: https://travis-ci.org/Lasagne/Lasagne.svg?branch=master\n    :target: https://travis-ci.org/Lasagne/Lasagne\n\n.. image:: https://img.shields.io/coveralls/Lasagne/Lasagne.svg\n    :target: https://coveralls.io/r/Lasagne/Lasagne\n\n.. image:: https://img.shields.io/badge/license-MIT-blue.svg\n    :target: https://github.com/Lasagne/Lasagne/blob/master/LICENSE\n\n.. image:: https://zenodo.org/badge/16974/Lasagne/Lasagne.svg\n   :target: https://zenodo.org/badge/latestdoi/16974/Lasagne/Lasagne\n\nLasagne\n=======\n\nLasagne is a lightweight library to build and train neural networks in Theano.\nIts main features are:\n\n* Supports feed-forward networks such as Convolutional Neural Networks (CNNs),\n  recurrent networks including Long Short-Term Memory (LSTM), and any\n  combination thereof\n* Allows architectures of multiple inputs and multiple outputs, including\n  auxiliary classifiers\n* Many optimization methods including Nesterov momentum, RMSprop and ADAM\n* Freely definable cost function and no need to derive gradients due to\n  Theano's symbolic differentiation\n* Transparent support of CPUs and GPUs due to Theano's expression compiler\n\nIts design is governed by `six principles\n<http://lasagne.readthedocs.org/en/latest/user/development.html#philosophy>`_:\n\n* Simplicity: Be easy to use, easy to understand and easy to extend, to\n  facilitate use in research\n* Transparency: Do not hide Theano behind abstractions, directly process and\n  return Theano expressions or Python / numpy data types\n* Modularity: Allow all parts (layers, regularizers, optimizers, ...) to be\n  used independently of Lasagne\n* Pragmatism: Make common use cases easy, do not overrate uncommon cases\n* Restraint: Do not obstruct users with features they decide not to use\n* Focus: \"Do one thing and do it well\"\n\n\nInstallation\n------------\n\nIn short, you can install a known compatible version of Theano and the latest\nLasagne development version via:\n\n.. code-block:: bash\n\n  pip install -r https://raw.githubusercontent.com/Lasagne/Lasagne/master/requirements.txt\n  pip install https://github.com/Lasagne/Lasagne/archive/master.zip\n\nFor more details and alternatives, please see the `Installation instructions\n<http://lasagne.readthedocs.org/en/latest/user/installation.html>`_.\n\n\nDocumentation\n-------------\n\nDocumentation is available online: http://lasagne.readthedocs.org/\n\nFor support, please refer to the `lasagne-users mailing list\n<https://groups.google.com/forum/#!forum/lasagne-users>`_.\n\n\nExample\n-------\n\n.. code-block:: python\n\n  import lasagne\n  import theano\n  import theano.tensor as T\n\n  # create Theano variables for input and target minibatch\n  input_var = T.tensor4('X')\n  target_var = T.ivector('y')\n\n  # create a small convolutional neural network\n  from lasagne.nonlinearities import leaky_rectify, softmax\n  network = lasagne.layers.InputLayer((None, 3, 32, 32), input_var)\n  network = lasagne.layers.Conv2DLayer(network, 64, (3, 3),\n                                       nonlinearity=leaky_rectify)\n  network = lasagne.layers.Conv2DLayer(network, 32, (3, 3),\n                                       nonlinearity=leaky_rectify)\n  network = lasagne.layers.Pool2DLayer(network, (3, 3), stride=2, mode='max')\n  network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, 0.5),\n                                      128, nonlinearity=leaky_rectify,\n                                      W=lasagne.init.Orthogonal())\n  network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, 0.5),\n                                      10, nonlinearity=softmax)\n\n  # create loss function\n  prediction = lasagne.layers.get_output(network)\n  loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)\n  loss = loss.mean() + 1e-4 * lasagne.regularization.regularize_network_params(\n          network, lasagne.regularization.l2)\n\n  # create parameter update expressions\n  params = lasagne.layers.get_all_params(network, trainable=True)\n  updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=0.01,\n                                              momentum=0.9)\n\n  # compile training function that updates parameters and returns training loss\n  train_fn = theano.function([input_var, target_var], loss, updates=updates)\n\n  # train network (assuming you've got some training data in numpy arrays)\n  for epoch in range(100):\n      loss = 0\n      for input_batch, target_batch in training_data:\n          loss += train_fn(input_batch, target_batch)\n      print(\"Epoch %d: Loss %g\" % (epoch + 1, loss / len(training_data)))\n\n  # use trained network for predictions\n  test_prediction = lasagne.layers.get_output(network, deterministic=True)\n  predict_fn = theano.function([input_var], T.argmax(test_prediction, axis=1))\n  print(\"Predicted class for first test input: %r\" % predict_fn(test_data[0]))\n\nFor a fully-functional example, see `examples/mnist.py <examples/mnist.py>`_,\nand check the `Tutorial\n<http://lasagne.readthedocs.org/en/latest/user/tutorial.html>`_ for in-depth\nexplanations of the same. More examples, code snippets and reproductions of\nrecent research papers are maintained in the separate `Lasagne Recipes\n<https://github.com/Lasagne/Recipes>`_ repository.\n\n\nDevelopment\n-----------\n\nLasagne is a work in progress, input is welcome.\n\nPlease see the `Contribution instructions\n<http://lasagne.readthedocs.org/en/latest/user/development.html>`_ for details\non how you can contribute!\n\n\nChangelog\n---------\n\n0.1 (2015-08-13)\n~~~~~~~~~~~~~~~~\n\nFirst release.\n\n* core contributors, in alphabetical order:\n\n  * Eric Battenberg (@ebattenberg)\n  * Sander Dieleman (@benanne)\n  * Daniel Nouri (@dnouri)\n  * Eben Olson (@ebenolson)\n  * A\u00e4ron van den Oord (@avdnoord)\n  * Colin Raffel (@craffel)\n  * Jan Schl\u00fcter (@f0k)\n  * S\u00f8ren Kaae S\u00f8nderby (@skaae)\n\n* extra contributors, in chronological order:\n\n  * Daniel Maturana (@dimatura): documentation, cuDNN layers, LRN\n  * Jonas Degrave (@317070): get_all_param_values() fix\n  * Jack Kelly (@JackKelly): help with recurrent layers\n  * G\u00e1bor Tak\u00e1cs (@takacsg84): support broadcastable parameters in lasagne.updates\n  * Diogo Moitinho de Almeida (@diogo149): MNIST example fixes\n  * Brian McFee (@bmcfee): MaxPool2DLayer fix\n  * Martin Thoma (@MartinThoma): documentation\n  * Jeffrey De Fauw (@JeffreyDF): documentation, ADAM fix\n  * Michael Heilman (@mheilman): NonlinearityLayer, lasagne.random\n  * Gregory Sanders (@instagibbs): documentation fix\n  * Jon Crall (@erotemic): check for non-positive input shapes\n  * Hendrik Weideman (@hjweide): set_all_param_values() test, MaxPool2DCCLayer fix\n  * Kashif Rasul (@kashif): ADAM simplification\n  * Peter de Rivaz (@peterderivaz): documentation fix",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "UNKNOWN",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/Lasagne/Lasagne",
        "keywords": "",
        "license": "MIT",
        "maintainer": null,
        "maintainer_email": null,
        "name": "Lasagne",
        "package_url": "https://pypi.org/project/Lasagne/",
        "platform": "UNKNOWN",
        "project_url": "https://pypi.org/project/Lasagne/",
        "project_urls": {
            "Download": "UNKNOWN",
            "Homepage": "https://github.com/Lasagne/Lasagne"
        },
        "release_url": "https://pypi.org/project/Lasagne/0.1/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "A lightweight library to build and train neural networks in Theano",
        "version": "0.1"
    },
    "last_serial": 1676667,
    "releases": {
        "0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "44212b92bf5f3b1be3021fa0b64b5fdb",
                    "sha256": "3c634ecab67e43e4f18520932bfd88bd3c678ec723c48177f18799dab2411233"
                },
                "downloads": -1,
                "filename": "Lasagne-0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "44212b92bf5f3b1be3021fa0b64b5fdb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 125077,
                "upload_time": "2015-08-13T21:10:53",
                "url": "https://files.pythonhosted.org/packages/98/bf/4b2336e4dbc8c8859c4dd81b1cff18eef2066b4973a1bd2b0ca2e5435f35/Lasagne-0.1.tar.gz"
            }
        ],
        "0.1dev": []
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "44212b92bf5f3b1be3021fa0b64b5fdb",
                "sha256": "3c634ecab67e43e4f18520932bfd88bd3c678ec723c48177f18799dab2411233"
            },
            "downloads": -1,
            "filename": "Lasagne-0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "44212b92bf5f3b1be3021fa0b64b5fdb",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 125077,
            "upload_time": "2015-08-13T21:10:53",
            "url": "https://files.pythonhosted.org/packages/98/bf/4b2336e4dbc8c8859c4dd81b1cff18eef2066b4973a1bd2b0ca2e5435f35/Lasagne-0.1.tar.gz"
        }
    ]
}