Hi everyone, I would like to do image classification of my own dataset (containing nump images). I am using RNN for this purpose but I got runtime error of " Expected object of scalar type Byte but got scalar type Float for argument #2 ‘mat2’ in call to _th_mm". this happens when images going to pass to model.
here is my training loop code:
# Number of steps to unroll
seq_dim = 28
iter = 0
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
model.train()
# Load images as tensors with gradient accumulation abilities
images = images.view(-1, seq_dim, input_dim)
# Clear gradients w.r.t. parameters
optimizer.zero_grad()
# Forward pass to get output/logits
# outputs.size() --> 100, 10
outputs = model(images)
# Calculate Loss: softmax --> cross entropy loss
loss = criterion(outputs, labels)
# Getting gradients w.r.t. parameters
loss.backward()
# Updating parameters
optimizer.step()
iter += 1
if iter % 500 == 0:
model.eval()
# Calculate Accuracy
correct = 0
total = 0
# Iterate through test dataset
for images, labels in test_loader:
# Load images to a Torch tensors with gradient accumulation abilities
images = images.view(-1, seq_dim, input_dim)
# Forward pass only to get logits/output
outputs = model(images)
# Get predictions from the maximum value
_, predicted = torch.max(outputs.data, 1)
# Total number of labels
total += labels.size(0)
# Total correct predictions
correct += (predicted == labels).sum()
accuracy = 100 * correct / total
# Print Loss
print('Iteration: {}. Loss: {}. Accuracy: {}'.format(iter, loss.item(), accuracy))
plus my RNN network class is :
class RNNModel(nn.Module):
def __init__(self, input_dim, hidden_dim, layer_dim, output_dim):
super(RNNModel, self).__init__()
# Hidden dimensions
self.hidden_dim = hidden_dim
# Number of hidden layers
self.layer_dim = layer_dim
# Building your RNN
# batch_first=True causes input/output tensors to be of shape
# (batch_dim, seq_dim, feature_dim)
self.rnn = nn.RNN(input_dim, hidden_dim, layer_dim, batch_first=True, nonlinearity='relu')
# Readout layer
self.fc = nn.Linear(hidden_dim, output_dim)
def forward(self, x):
# Initialize hidden state with zeros
h0 = torch.zeros(self.layer_dim, x.size(0), self.hidden_dim).requires_grad_()
# We need to detach the hidden state to prevent exploding/vanishing gradients
# This is part of truncated backpropagation through time (BPTT)
out, hn = self.rnn(x, h0.detach())
# Index hidden state of last time step
# out.size() --> 100, 28, 100
# out[:, -1, :] --> 100, 100 --> just want last time step hidden states!
out = self.fc(out[:, -1, :])
# out.size() --> 100, 10
return out
input_dim = 28
hidden_dim = 100
layer_dim = 1
output_dim = 10
model = RNNModel(input_dim, hidden_dim, layer_dim, output_dim)
criterion = nn.CrossEntropyLoss()
learning_rate = 0.01
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
could you please help me.