How to use d2l - 10 common examples

To help you get started, we’ve selected a few d2l 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 eric-haibin-lin / AMLC19-GluonNLP / 02_sentiment_analysis / utils.py View on Github external
def train(net, train_iter, test_iter, loss, trainer, num_epochs,
               ctx_list=d2l.try_all_gpus()):
    num_batches, timer = len(train_iter), d2l.Timer()
    for epoch in range(num_epochs):
        # store training_loss, training_accuracy, num_examples, num_features
        metric = [0.0] * 4
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = d2l.train_batch_ch12(
                net, features, labels, loss, trainer, ctx_list)
            metric = [a+b for a, b in zip(metric, (l, acc, labels.shape[0], labels.size))]
            timer.stop()
            if (i+1) % (num_batches // 5) == 0:
                print('loss %.3f, train acc %.3f' % (metric[0]/metric[2], metric[1]/metric[3]))
        test_acc = d2l.evaluate_accuracy_gpus(net, test_iter)
    print('loss %.3f, train acc %.3f, test acc %.3f' % (
        metric[0]/metric[2], metric[1]/metric[3], test_acc))
    print('%.1f exampes/sec on %s' % (
        metric[2]*num_epochs/timer.sum(), ctx_list))
github eric-haibin-lin / AMLC19-GluonNLP / 02_sentiment_analysis / utils.py View on Github external
def train(net, train_iter, test_iter, loss, trainer, num_epochs,
               ctx_list=d2l.try_all_gpus()):
    num_batches, timer = len(train_iter), d2l.Timer()
    for epoch in range(num_epochs):
        # store training_loss, training_accuracy, num_examples, num_features
        metric = [0.0] * 4
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = d2l.train_batch_ch12(
                net, features, labels, loss, trainer, ctx_list)
            metric = [a+b for a, b in zip(metric, (l, acc, labels.shape[0], labels.size))]
            timer.stop()
            if (i+1) % (num_batches // 5) == 0:
                print('loss %.3f, train acc %.3f' % (metric[0]/metric[2], metric[1]/metric[3]))
        test_acc = d2l.evaluate_accuracy_gpus(net, test_iter)
    print('loss %.3f, train acc %.3f, test acc %.3f' % (
        metric[0]/metric[2], metric[1]/metric[3], test_acc))
    print('%.1f exampes/sec on %s' % (
        metric[2]*num_epochs/timer.sum(), ctx_list))
github eric-haibin-lin / AMLC19-GluonNLP / 02_sentiment_analysis / utils.py View on Github external
def train(net, train_iter, test_iter, loss, trainer, num_epochs,
               ctx_list=d2l.try_all_gpus()):
    num_batches, timer = len(train_iter), d2l.Timer()
    for epoch in range(num_epochs):
        # store training_loss, training_accuracy, num_examples, num_features
        metric = [0.0] * 4
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = d2l.train_batch_ch12(
                net, features, labels, loss, trainer, ctx_list)
            metric = [a+b for a, b in zip(metric, (l, acc, labels.shape[0], labels.size))]
            timer.stop()
            if (i+1) % (num_batches // 5) == 0:
                print('loss %.3f, train acc %.3f' % (metric[0]/metric[2], metric[1]/metric[3]))
        test_acc = d2l.evaluate_accuracy_gpus(net, test_iter)
    print('loss %.3f, train acc %.3f, test acc %.3f' % (
        metric[0]/metric[2], metric[1]/metric[3], test_acc))
    print('%.1f exampes/sec on %s' % (
        metric[2]*num_epochs/timer.sum(), ctx_list))
github eric-haibin-lin / AMLC19-GluonNLP / 02_sentiment_analysis / utils.py View on Github external
def train(net, train_iter, test_iter, loss, trainer, num_epochs,
               ctx_list=d2l.try_all_gpus()):
    num_batches, timer = len(train_iter), d2l.Timer()
    for epoch in range(num_epochs):
        # store training_loss, training_accuracy, num_examples, num_features
        metric = [0.0] * 4
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = d2l.train_batch_ch12(
                net, features, labels, loss, trainer, ctx_list)
            metric = [a+b for a, b in zip(metric, (l, acc, labels.shape[0], labels.size))]
            timer.stop()
            if (i+1) % (num_batches // 5) == 0:
                print('loss %.3f, train acc %.3f' % (metric[0]/metric[2], metric[1]/metric[3]))
        test_acc = d2l.evaluate_accuracy_gpus(net, test_iter)
    print('loss %.3f, train acc %.3f, test acc %.3f' % (
        metric[0]/metric[2], metric[1]/metric[3], test_acc))
    print('%.1f exampes/sec on %s' % (
github dsgiitr / d2l-pytorch / d2l / data / base.py View on Github external
def load_data_time_machine(num_examples=10000):
    """Load the time machine data set (available in the English book)."""
    with open('../data/timemachine.txt') as f:
        raw_text = f.read()
    lines = raw_text.split('\n')
    text = ' '.join(' '.join(lines).lower().split())[:num_examples]
    vocab = Vocab(text)
    corpus_indices = [vocab[char] for char in text]
    return corpus_indices, vocab
github d2l-ai / d2l-ja / d2l / utils.py View on Github external
def resnet_block(num_channels, num_residuals, first_block=False):
        blk = nn.Sequential()
        for i in range(num_residuals):
            if i == 0 and not first_block:
                blk.add(Residual(num_channels, use_1x1conv=True, strides=2))
            else:
                blk.add(Residual(num_channels))
        return blk
github d2l-ai / d2l-ja / d2l / utils.py View on Github external
def resnet_block(num_channels, num_residuals, first_block=False):
        blk = nn.Sequential()
        for i in range(num_residuals):
            if i == 0 and not first_block:
                blk.add(Residual(num_channels, use_1x1conv=True, strides=2))
            else:
                blk.add(Residual(num_channels))
        return blk
github d2l-ai / d2l-ja / d2l / utils.py View on Github external
def __init__(self, num_channels, use_1x1conv=False, strides=1, **kwargs):
        super(Residual, self).__init__(**kwargs)
        self.conv1 = nn.Conv2D(num_channels, kernel_size=3, padding=1,
                               strides=strides)
        self.conv2 = nn.Conv2D(num_channels, kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2D(num_channels, kernel_size=1,
                                   strides=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm()
        self.bn2 = nn.BatchNorm()
github dsgiitr / d2l-pytorch / d2l / ssd_utils.py View on Github external
def __init__(self, xlabel=None, ylabel=None, legend=[], xlim=None,
                 ylim=None, xscale='linear', yscale='linear', fmts=None,
                 nrows=1, ncols=1, figsize=(3.5, 2.5)):
        """Incrementally plot multiple lines."""
        d2l.use_svg_display()
        self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
        if nrows * ncols == 1: self.axes = [self.axes,]
        # use a lambda to capture arguments
        self.config_axes = lambda : d2l.set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts
github eric-haibin-lin / AMLC19-GluonNLP / 01_gluon_basics / mlp_utils.py View on Github external
def show_fashion_mnist(images, labels):
    import d2l
    d2l.use_svg_display()
    # Here _ means that we ignore (not use) variables.
    _, figs = d2l.plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.reshape((28, 28)).asnumpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)