pytorch里面的Tensorboard使用

pytorch里面的TensorBoard使用

1. TensorBoard建立

从torch.utils里面导入tensorboard并且定义一个变量从SummaryWriter，我们的目标就是写信息到tensorboard里面

from torch.utils.tensorboard import SummaryWriter

# default `log_dir` is "runs" - we'll be more specific here
writer = SummaryWriter('runs/fashion_mnist_experiment_1')

所以就创建了一个summarywriter的tensorboard

2. 写入TensorBoard

接下来用make_grid方法进行写入图片

# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# create grid of images
img_grid = torchvision.utils.make_grid(images)

# show images
matplotlib_imshow(img_grid, one_channel=True)

# write to tensorboard
writer.add_image('four_fashion_mnist_images', img_grid)

去运行：

tensorboard --logdir=runs

3. 检测模型是否用了tensorboard

我们就在里面添加信息进行对tensorboard检查

writer.add_graph(net, images)
writer.close()

4. 把项目加入到tensorboard里面

用这样的方法来进行可视化：

# helper function
def select_n_random(data, labels, n=100):
    '''
    Selects n random datapoints and their corresponding labels from a dataset
    '''
    assert len(data) == len(labels)

    perm = torch.randperm(len(data))
    return data[perm][:n], labels[perm][:n]

# select random images and their target indices
images, labels = select_n_random(trainset.data, trainset.targets)

# get the class labels for each image
class_labels = [classes[lab] for lab in labels]

# log embeddings
features = images.view(-1, 28 * 28)
writer.add_embedding(features,
                    metadata=class_labels,
                    label_img=images.unsqueeze(1))
writer.close()

5. 用TensorBoard进行模型训练跟踪

我们需要用运行损失来定，函数定义方法如下：

# helper functions

def images_to_probs(net, images):
    '''
    Generates predictions and corresponding probabilities from a trained
    network and a list of images
    '''
    output = net(images)
    # convert output probabilities to predicted class
    _, preds_tensor = torch.max(output, 1)
    preds = np.squeeze(preds_tensor.numpy())
    return preds, [F.softmax(el, dim=0)[i].item() for i, el in zip(preds, output)]


def plot_classes_preds(net, images, labels):
    '''
    Generates matplotlib Figure using a trained network, along with images
    and labels from a batch, that shows the network's top prediction along
    with its probability, alongside the actual label, coloring this
    information based on whether the prediction was correct or not.
    Uses the "images_to_probs" function.
    '''
    preds, probs = images_to_probs(net, images)
    # plot the images in the batch, along with predicted and true labels
    fig = plt.figure(figsize=(12, 48))
    for idx in np.arange(4):
        ax = fig.add_subplot(1, 4, idx+1, xticks=[], yticks=[])
        matplotlib_imshow(images[idx], one_channel=True)
        ax.set_title("{0}, {1:.1f}%\n(label: {2})".format(
            classes[preds[idx]],
            probs[idx] * 100.0,
            classes[labels[idx]]),
                    color=("green" if preds[idx]==labels[idx].item() else "red"))
    return fig

接下来，我们就训练模型用这样的代码来训练就好了。

训练的代码修改如下：

running_loss = 0.0
for epoch in range(1):  # loop over the dataset multiple times

    for i, data in enumerate(trainloader, 0):

        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 1000 == 999:    # every 1000 mini-batches...

            # ...log the running loss
            writer.add_scalar('training loss',
                            running_loss / 1000,
                            epoch * len(trainloader) + i)

            # ...log a Matplotlib Figure showing the model's predictions on a
            # random mini-batch
            writer.add_figure('predictions vs. actuals',
                            plot_classes_preds(net, inputs, labels),
                            global_step=epoch * len(trainloader) + i)
            running_loss = 0.0
print('Finished Training')

打开tensorboard就可以看到相关的训练情况来进行评估

6. 用tensorboard进行模型评价

# 1. gets the probability predictions in a test_size x num_classes Tensor
# 2. gets the preds in a test_size Tensor
# takes ~10 seconds to run
class_probs = []
class_label = []
with torch.no_grad():
    for data in testloader:
        images, labels = data
        output = net(images)
        class_probs_batch = [F.softmax(el, dim=0) for el in output]

        class_probs.append(class_probs_batch)
        class_label.append(labels)

test_probs = torch.cat([torch.stack(batch) for batch in class_probs])
test_label = torch.cat(class_label)

# helper function
def add_pr_curve_tensorboard(class_index, test_probs, test_label, global_step=0):
    '''
    Takes in a "class_index" from 0 to 9 and plots the corresponding
    precision-recall curve
    '''
    tensorboard_truth = test_label == class_index
    tensorboard_probs = test_probs[:, class_index]

    writer.add_pr_curve(classes[class_index],
                        tensorboard_truth,
                        tensorboard_probs,
                        global_step=global_step)
    writer.close()

# plot all the pr curves
for i in range(len(classes)):
    add_pr_curve_tensorboard(i, test_probs, test_label)

就会见到PR 的曲线包含很多信息，看到拟合的情况，来进行训练的可视化。