How to use the databases.textproject_reconstruction_database.TextProjectReconstructionDatabase function in databases

To help you get started, we’ve selected a few databases examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github robinsloan / sentence-space / textproject_vae_charlevel.py View on Github external
def main(z, lr, anneal_start, anneal_end, p, alpha, lstm_size, num_epochs, max_len, batch_size, session, dataset, sp_model, resume):

    train_db = TextProjectReconstructionDatabase(dataset=dataset, phase="train", batch_size=batch_size, max_len=max_len, sp_model=sp_model or None)
    valid_db = TextProjectReconstructionDatabase(dataset=dataset, phase="valid", batch_size=batch_size, max_len=max_len, sp_model=sp_model or None)

    model = make_model(z, max_len, p, train_db.n_classes, lstm_size, alpha)
    model.anneal_start = float(anneal_start)
    model.anneal_end = float(anneal_end)

    vocab = train_db.vocab

    print("Using vocab with %s tokens" % len(vocab))

    if resume:
        model.load("session/%s/model.flt" % session)
        print("Resuming session %s" % session)

    #out = nn.utils.forward(model, train_db, out=model.output(model.input))
    #print out.shape
    #return
github robinsloan / sentence-space / textproject_vae_charlevel.py View on Github external
def main(z, lr, anneal_start, anneal_end, p, alpha, lstm_size, num_epochs, max_len, batch_size, session, dataset, sp_model, resume):

    train_db = TextProjectReconstructionDatabase(dataset=dataset, phase="train", batch_size=batch_size, max_len=max_len, sp_model=sp_model or None)
    valid_db = TextProjectReconstructionDatabase(dataset=dataset, phase="valid", batch_size=batch_size, max_len=max_len, sp_model=sp_model or None)

    model = make_model(z, max_len, p, train_db.n_classes, lstm_size, alpha)
    model.anneal_start = float(anneal_start)
    model.anneal_end = float(anneal_end)

    vocab = train_db.vocab

    print("Using vocab with %s tokens" % len(vocab))

    if resume:
        model.load("session/%s/model.flt" % session)
        print("Resuming session %s" % session)

    #out = nn.utils.forward(model, train_db, out=model.output(model.input))
    #print out.shape
github robinsloan / sentence-space / textproject_vae_sample_charlevel.py View on Github external
ins[:, 0] = valid_db.to_inputs(valid_db.sentences[s1])
        ins[:, 1] = valid_db.to_inputs(valid_db.sentences[s2])
        x = T.imatrix()
        z = encoder(x)
        mu = sampler.mu
        f = theano.function([x], mu)
        z = f(ins.astype('int32'))
        s1_z = z[0]
        s2_z = z[1]
        n = 7
        s1_z = numpy.repeat(s1_z[None, :], n, axis=0)
        s2_z = numpy.repeat(s2_z[None, :], n, axis=0)
        steps = numpy.linspace(0, 1, n)[:, None]
        sampled = s1_z * (1 - steps) + s2_z * steps
    elif mode == 'arithm':
        valid_db = TextProjectReconstructionDatabase("valid", 50, batches_per_epoch=100, max_len=max_len)
        s1 = numpy.random.randint(0, len(valid_db.sentences))
        s2 = numpy.random.randint(0, len(valid_db.sentences))
        s3 = numpy.random.randint(0, len(valid_db.sentences))
        print valid_db.sentences[s1]
        print valid_db.sentences[s2]
        print valid_db.sentences[s3]
        encoder = model.layers[0].branches[0]
        sampler = encoder[-1]
        assert isinstance(sampler, Sampler)
        ins = numpy.zeros((max_len, 3))
        ins[:, 0] = valid_db.to_inputs(valid_db.sentences[s1])
        ins[:, 1] = valid_db.to_inputs(valid_db.sentences[s2])
        ins[:, 2] = valid_db.to_inputs(valid_db.sentences[s3])
        x = T.imatrix()
        z = encoder(x)
        mu = sampler.mu
github robinsloan / sentence-space / textproject_vae_sample_charlevel.py View on Github external
mode = 'custom'
    #mode = 'interpolate'

    if mode == 'vary':
        n = 7
        sampled = numpy.random.normal(0, 1, (1, z))
        sampled = numpy.repeat(sampled, n * z, axis=0)
        for dim in xrange(z):
            eps = 0.01
            x = numpy.linspace(eps, 1 - eps, num=n)
            x = norm.ppf(x)
            sampled[dim*n:(dim+1)*n, dim] = x
        n *= z
    elif mode == 'interpolatereal':
        valid_db = TextProjectReconstructionDatabase(dataset=dataset, phase="valid", batch_size=50, batches_per_epoch=100, max_len=max_len)
        s1 = numpy.random.randint(0, len(valid_db.sentences))
        s2 = numpy.random.randint(0, len(valid_db.sentences))
        encoder = model.layers[0].branches[0]
        sampler = encoder[-1]
        assert isinstance(sampler, Sampler)
        ins = numpy.zeros((max_len, 2))
        ins[:, 0] = valid_db.to_inputs(valid_db.sentences[s1])
        ins[:, 1] = valid_db.to_inputs(valid_db.sentences[s2])
        x = T.imatrix()
        z = encoder(x)
        mu = sampler.mu
        f = theano.function([x], mu)
        z = f(ins.astype('int32'))
        s1_z = z[0]
        s2_z = z[1]
        n = 7