I am working on the classic example with digits. I want to create a my first neural.network that predict the labels of digit images {0,1,2,3,4,5,6,7,8,9}. So the first column of train.txt
has the labels and all the other columns are the features of each label. I have defined a class to import my data:
class DigitDataset(Dataset):
"""Digit dataset."""
def __init__(self, file_path, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.data = pd.read_csv(file_path, header = None, sep =" ")
self.transform = transform
def __len__(self):
return len(self.data)
def __getitem__(self, idx):
if torch.is_tensor(idx):
idx = idx.tolist()
labels = self.data.iloc[idx,0]
images = self.data.iloc[idx,1:-1].values.astype(np.uint8).reshape((1,16,16))
if self.transform is not None:
sample = self.transform(sample)
return images, labels
And then I am running these commands to split my dataset into batches, to define a model and a loss:
train_dataset = DigitDataset("train.txt")
train_loader = DataLoader(train_dataset, batch_size=64,
shuffle=True, num_workers=4)
# Model creation with neural net Sequential model
model=nn.Sequential(nn.Linear(256, 128), # 1 layer:- 256 input 128 o/p
nn.ReLU(), # Defining Regular linear unit as activation
nn.Linear(128,64), # 2 Layer:- 128 Input and 64 O/p
nn.Tanh(), # Defining Regular linear unit as activation
nn.Linear(64,10), # 3 Layer:- 64 Input and 10 O/P as (0-9)
nn.LogSoftmax(dim=1) # Defining the log softmax to find the probablities
for the last output unit
)
# defining the negative log-likelihood loss for calculating loss
criterion = nn.NLLLoss()
images, labels = next(iter(train_loader))
images = images.view(images.shape[0], -1)
logps = model(images) #log probabilities
loss = criterion(logps, labels) #calculate the NLL-loss
And I take the error:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-2-7f4160c1f086> in <module>
47 images = images.view(images.shape[0], -1)
48
---> 49 logps = model(images) #log probabilities
50 loss = criterion(logps, labels) #calculate the NLL-loss
~/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self,
*input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/anaconda3/lib/python3.8/site-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
~/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self,
*input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/anaconda3/lib/python3.8/site-packages/torch/nn/modules/linear.py in forward(self, input)
91
92 def forward(self, input: Tensor) -> Tensor:
---> 93 return F.linear(input, self.weight, self.bias)
94
95 def extra_repr(self) -> str:
~/anaconda3/lib/python3.8/site-packages/torch/nn/functional.py in linear(input, weight, bias)
1688 if input.dim() == 2 and bias is not None:
1689 # fused op is marginally faster
-> 1690 ret = torch.addmm(bias, input, weight.t())
1691 else:
1692 output = input.matmul(weight.t())
RuntimeError: expected scalar type Float but found Byte
Do you know what is wrong? Thank you for your patience and help!
This line is the cause of your error:
images = self.data.iloc[idx, 1:-1].values.astype(np.uint8).reshape((1, 16, 16))
images
are uint8
( byte
) while the neural network needs inputs as floating point in order to calculate gradients (you can't calculate gradients for backprop using integers as those are not continuous and non-differentiable).
You can use torchvision.transforms.functional.to_tensor
to convert the image into float
and into [0, 1]
like this:
import torchvision
images = torchvision.transforms.functional.to_tensor(
self.data.iloc[idx, 1:-1].values.astype(np.uint8).reshape((1, 16, 16))
)
or simply divide by 255
to get values into [0, 1]
.
Here is a simple solution.
Just add the.float() to the image tensor. Like this:
# Forward Pass
outputs = model(images.float())
import torch
import torchvision
import matplotlib.pyplot as plt
from time import time
from torchvision import datasets, transforms
from torch import nn, optim
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,)),
])
trainset = datasets.MNIST('data/train', download=True, train=True, transform=transform)
valset = datasets.MNIST('data/test', download=True, train=False, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
valloader = torch.utils.data.DataLoader(valset, batch_size=64, shuffle=True)
input_size = 784
hidden_sizes = [128,128,64]
output_size = 10
model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
nn.ReLU(),
nn.Linear(hidden_sizes[0], hidden_sizes[1]),
nn.ReLU(),
nn.Linear(hidden_sizes[1], hidden_sizes[2]),
nn.ReLU(),
nn.Linear(hidden_sizes[2], output_size),
nn.LogSoftmax(dim=1))
# print(model)
criterion = nn.NLLLoss()
images, labels = next(iter(trainloader))
images = images.view(images.shape[0], -1)
logps = model(images) #log probabilities
loss = criterion(logps, labels) #calculate the NLL loss
optimizer = optim.SGD(model.parameters(), lr=0.003, momentum=0.9)
time0 = time()
epochs = 15
for e in range(epochs):
running_loss = 0
for images, labels in trainloader:
# Flatten MNIST images into a 784 long vector
images = images.view(images.shape[0], -1)
# Training pass
optimizer.zero_grad()
output = model(images)
loss = criterion(output, labels)
#This is where the model learns by backpropagating
loss.backward()
#And optimizes its weights here
optimizer.step()
running_loss += loss.item()
else:
print("Epoch {} - Training loss: {}".format(e, running_loss/len(trainloader)))
print("\nTraining Time (in minutes) =",(time()-time0)/60)
images, labels = next(iter(valloader))
img = images[0].view(1, 784)
with torch.no_grad():
logps = model(img)
ps = torch.exp(logps)
probab = list(ps.numpy()[0])
print("Predicted Digit =", probab.index(max(probab)))
# view_classify(img.view(1, 28, 28), ps)
correct_count, all_count = 0, 0
for images,labels in valloader:
for i in range(len(labels)):
img = images[i].view(1, 784)
with torch.no_grad():
logps = model(img)
ps = torch.exp(logps)
probab = list(ps.numpy()[0])
pred_label = probab.index(max(probab))
true_label = labels.numpy()[i]
if(true_label == pred_label):
correct_count += 1
all_count += 1
print("Number Of Images Tested =", all_count)
print("\nModel Accuracy =", (correct_count/all_count))
torch.save(model, './my_mnist_model.pt') ```
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.