Pytorch Tensorboard

official tutorial

Read dataset

In [1]:
# imports
import matplotlib.pyplot as plt
import numpy as np

import torch
import torchvision
import torchvision.transforms as transforms

import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

# transforms
transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))])

# datasets
trainset = torchvision.datasets.FashionMNIST('./data',
    download=True,
    train=True,
    transform=transform)
testset = torchvision.datasets.FashionMNIST('./data',
    download=True,
    train=False,
    transform=transform)

# dataloaders
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                        shuffle=True, num_workers=2)


testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                        shuffle=False, num_workers=2)

# constant for classes
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
        'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')

# helper function to show an image
# (used in the `plot_classes_preds` function below)
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ./data/FashionMNIST/raw/train-images-idx3-ubyte.gz
Extracting ./data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ./data/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ./data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
Extracting ./data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ./data/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ./data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
Extracting ./data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ./data/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to ./data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
Extracting ./data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/FashionMNIST/raw
Processing...
Done!
/Users/zikangxiong/Development/python_env/general_env/lib/python3.8/site-packages/torchvision/datasets/mnist.py:480: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  ../torch/csrc/utils/tensor_numpy.cpp:141.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)

Network Model

In [2]:
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()

In [3]:
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

Initialize Tensorboard

In [4]:
from torch.utils.tensorboard import SummaryWriter

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

Write to Tensorboard

In [5]:
# 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)
In [7]:
%%sh 
tensorboard --logdir=res
Process is interrupted.

image.png

Check Model Graph

In [8]:
writer.add_graph(net, images)
writer.close()

image.png

Low dimension representation

In [11]:
writer = SummaryWriter('res/fashion_mnist_experiment_2')

# 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()
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-11-3b3e97530536> in <module>
     19 # log embeddings
     20 features = images.view(-1, 28 * 28)
---> 21 writer.add_embedding(features,
     22                     metadata=class_labels,
     23                     label_img=images.unsqueeze(1))

~/Development/python_env/general_env/lib/python3.8/site-packages/torch/utils/tensorboard/writer.py in add_embedding(self, mat, metadata, label_img, global_step, tag, metadata_header)
    796         save_path = os.path.join(self._get_file_writer().get_logdir(), subdir)
    797 
--> 798         fs = tf.io.gfile.get_filesystem(save_path)
    799         if fs.exists(save_path):
    800             if fs.isdir(save_path):

AttributeError: module 'tensorflow._api.v2.io.gfile' has no attribute 'get_filesystem'

Track Training

In [12]:
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
In [13]:
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')
Finished Training

Assessing trained models with TensorBoard

In [14]:
# 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_preds = []
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_preds_batch = torch.max(output, 1)

        class_probs.append(class_probs_batch)
        class_preds.append(class_preds_batch)

test_probs = torch.cat([torch.stack(batch) for batch in class_probs])
test_preds = torch.cat(class_preds)

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

    writer.add_pr_curve(classes[class_index],
                        tensorboard_preds,
                        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_preds)