After I started training the model, jumped out of the error.
I didn’t find any way to deal with such an error on Google. Could someone kindly help?
Thank you very much!
The next part is training the model.
def train(net, epochs=10, batch_size=100, lr=0.01):
opt = torch.optim.SGD(net.parameters(), lr=lr, momentum=0.9, weight_decay=1e-4)
criterion = nn.CrossEntropyLoss()
if(train_on_gpu):
net.cuda()
for e in range(epochs):
# initialize hidden state
h = net.init_hidden(batch_size)
train_losses = []
net.train()
for batch in iterate_minibatches(X_train, y_train, batch_size):
x, y = batch
inputs, targets = torch.from_numpy(x), torch.from_numpy(y)
if(train_on_gpu):
inputs, targets = inputs.cuda(), targets.cuda()
# Creating new variables for the hidden state, otherwise
# we'd backprop through the entire training history
h = tuple([each.data for each in h])
# zero accumulated gradients
opt.zero_grad()
# get the output from the model
output, h = net(inputs, h, batch_size)
loss = criterion(output, targets.long())
train_losses.append(loss.item())
loss.backward()
opt.step()
val_h = net.init_hidden(batch_size)
val_losses = []
accuracy=0
f1score=0
net.eval()
with torch.no_grad():
for batch in iterate_minibatches(X_test, y_test, batch_size):
x, y = batch
inputs, targets = torch.from_numpy(x), torch.from_numpy(y)
val_h = tuple([each.data for each in val_h])
if(train_on_gpu):
inputs, targets = inputs.cuda(), targets.cuda()
output, val_h= net(inputs, val_h, batch_size)
val_loss = criterion(output, targets.long())
val_losses.append(val_loss.item())
top_p, top_class = output.topk(1, dim=1)
equals = top_class == targets.view(*top_class.shape).long()
accuracy += torch.mean(equals.type(torch.FloatTensor))
f1score += metrics.f1_score(top_class.cpu(), targets.view(*top_class.shape).long().cpu(), average='weighted')
net.train() # reset to train mode after iterationg through validation data
print("Epoch: {}/{}...".format(e+1, epochs),
"Train Loss: {:.4f}...".format(np.mean(train_losses)),
"Val Loss: {:.4f}...".format(np.mean(val_losses)),
"Val Acc: {:.4f}...".format(accuracy/(len(X_test)//batch_size)),
"F1-Score: {:.4f}...".format(f1score/(len(X_test)//batch_size)))
train(net)
When I run the code above, the error is shown below
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-16-9c574dc76081> in <module>()
70 "F1-Score: {:.4f}...".format(f1score/(len(X_test)//batch_size)))
71
---> 72 train(net)
4 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
2216 .format(input.size(0), target.size(0)))
2217 if dim == 2:
-> 2218 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
2219 elif dim == 4:
2220 ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
IndexError: Target 4 is out of bounds.
This is my whole model
NB_SENSOR_CHANNELS = 113
SLIDING_WINDOW_LENGTH = 24
SLIDING_WINDOW_STEP = 12
class HARModel(nn.Module):
def __init__(self, n_hidden=128, n_layers=1, n_filters=64,
n_classes=4, filter_size=5, drop_prob=0.5):
super(HARModel, self).__init__()
self.drop_prob = drop_prob
self.n_layers = n_layers
self.n_hidden = n_hidden
self.n_filters = n_filters
self.n_classes = n_classes
self.filter_size = filter_size
self.conv1 = nn.Conv1d(NB_SENSOR_CHANNELS, n_filters, filter_size)
self.conv2 = nn.Conv1d(n_filters, n_filters, filter_size)
self.conv3 = nn.Conv1d(n_filters, n_filters, filter_size)
self.conv4 = nn.Conv1d(n_filters, n_filters, filter_size)
self.lstm1 = nn.LSTM(n_filters, n_hidden, n_layers)
self.lstm2 = nn.LSTM(n_hidden, n_hidden, n_layers)
self.fc = nn.Linear(n_hidden, n_classes)
self.dropout = nn.Dropout(drop_prob)
def forward(self, x, hidden, batch_size):
x = x.view(-1, NB_SENSOR_CHANNELS, SLIDING_WINDOW_LENGTH)
x = F.relu(self.conv1(x))
x = F.relu(self.conv2(x))
x = F.relu(self.conv3(x))
x = F.relu(self.conv4(x))
x = x.view(8, -1, self.n_filters)
x, hidden = self.lstm1(x, hidden)
x, hidden = self.lstm2(x, hidden)
x = x.contiguous().view(-1, self.n_hidden)
x = self.dropout(x)
x = self.fc(x)
out = x.view(batch_size, -1, self.n_classes)[:,-1,:]
return out, hidden
def init_hidden(self, batch_size):
''' Initializes hidden state '''
# Create two new tensors with sizes n_layers x batch_size x n_hidden,
# initialized to zero, for hidden state and cell state of LSTM
weight = next(self.parameters()).data
if (train_on_gpu):
hidden = (weight.new(self.n_layers, batch_size, self.n_hidden).zero_().cuda(),
weight.new(self.n_layers, batch_size, self.n_hidden).zero_().cuda())
else:
hidden = (weight.new(self.n_layers, batch_size, self.n_hidden).zero_(),
weight.new(self.n_layers, batch_size, self.n_hidden).zero_())
return hidden
net = HARModel()
def init_weights(m):
if type(m) == nn.LSTM:
for name, param in m.named_parameters():
if 'weight_ih' in name:
torch.nn.init.orthogonal_(param.data)
elif 'weight_hh' in name:
torch.nn.init.orthogonal_(param.data)
elif 'bias' in name:
param.data.fill_(0)
elif type(m) == nn.Conv1d or type(m) == nn.Linear:
torch.nn.init.orthogonal_(m.weight)
m.bias.data.fill_(0)
net.apply(init_weights)
def iterate_minibatches(inputs, targets, batchsize, shuffle=True):
assert len(inputs) == len(targets)
if shuffle:
indices = np.arange(len(inputs))
np.random.shuffle(indices)
for start_idx in range(0, len(inputs) - batchsize + 1, batchsize):
if shuffle:
excerpt = indices[start_idx:start_idx + batchsize]
else:
excerpt = slice(start_idx, start_idx + batchsize)
yield inputs[excerpt], targets[excerpt]