I have a network designed as follows
class CNN_ForecastNet(nn.Module):
def __init__(self):
super(CNN_ForecastNet,self).__init__()
self.conv1d = nn.Conv1d(3,64,kernel_size=1)
self.relu = nn.ReLU(inplace=True)
self.fc1 = nn.Linear(64*2,50)
self.fc2 = nn.Linear(50,1)
def forward(self,x):
x = self.conv1d(x)
x = self.relu(x)
x = x.view(-1)
print('x size',x.size())
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
return x
def Train():
running_loss = .0
model.train()
for idx, (inputs,labels) in enumerate(train_loader):
inputs = inputs.to(device)
labels = labels.to(device)
optimizer.zero_grad()
print('--- idx ---',idx)
print('inputs ',inputs)
preds = model(inputs.float())
loss = criterion(preds,labels.float())
loss.backward()
optimizer.step()
running_loss += loss
train_loss = running_loss/len(train_loader)
train_losses.append(train_loss.detach().numpy())
print(f'train_loss {train_loss}')
However, for a given training data set, the size of dataloader is not the integer multiple of batch size. The printted output, (for the last two iterations) are given as follows
--- idx --- 902
inputs tensor([[[9.],
[9.],
[9.]],
[[9.],
[9.],
[0.]]], device='cuda:0', dtype=torch.float64)
x size torch.Size([128])
--- idx --- 903
inputs tensor([[[9.],
[0.],
[6.]]], device='cuda:0', dtype=torch.float64)
x size torch.Size([64])
This will cause the error at layer of fc1, i.e., x=self.fc1(x) in the network design,. the error message is as follows, I can see this error, but I am not clear how to correct it Thanks. The full code is attached at the end.
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-1-4d8996b2f4ab> in <module>
100 for epoch in range(epochs):
101 print('epochs {}/{}'.format(epoch+1,epochs))
--> 102 Train()
103 gc.collect()
<ipython-input-1-4d8996b2f4ab> in Train()
82 print('--- idx ---',idx)
83 print('inputs ',inputs)
---> 84 preds = model(inputs.float())
85 loss = criterion(preds,labels.float())
86 loss.backward()
~\Anaconda3\envs\pytorchenv\lib\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(),
<ipython-input-1-4d8996b2f4ab> in forward(self, x)
57 x = x.view(-1)
58 print('x size',x.size())
---> 59 x = self.fc1(x)
60 x = self.relu(x)
61 x = self.fc2(x)
~\Anaconda3\envs\pytorchenv\lib\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\envs\pytorchenv\lib\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\envs\pytorchenv\lib\site-packages\torch\nn\functional.py in linear(input, weight, bias)
1690 ret = torch.addmm(bias, input, weight.t())
1691 else:
-> 1692 output = input.matmul(weight.t())
1693 if bias is not None:
1694 output += bias
RuntimeError: mat1 dim 1 must match mat2 dim 0
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from numpy import array
import torch
import gc
import torch.nn as nn
from tqdm import tqdm_notebook as tqdm
from torch.utils.data import Dataset,DataLoader
solar_power = pd.read_csv('PV_Elec_Gas3.csv').rename(columns={'date':'timestamp'}).set_index('timestamp')
train_set = solar_power[:'8/10/2016']
def split_sequence(sequence, n_steps):
x, y = list(), list()
for i in range(len(sequence)):
end_ix = i + n_steps
if end_ix > len(sequence)-1:
break
seq_x, seq_y = sequence[i:end_ix], sequence[end_ix]
x.append(seq_x)
y.append(seq_y)
return array(x), array(y)
n_steps = 3
train_x,train_y = split_sequence(train_set.loc[:,"kWh electricity/day"].values,n_steps)
class ElecDataset(Dataset):
def __init__(self,feature,target):
self.feature = feature
self.target = target
def __len__(self):
return len(self.feature)
def __getitem__(self,idx):
item = self.feature[idx]
label = self.target[idx]
return item,label
class CNN_ForecastNet(nn.Module):
def __init__(self):
super(CNN_ForecastNet,self).__init__()
self.conv1d = nn.Conv1d(3,64,kernel_size=1)
self.relu = nn.ReLU(inplace=True)
self.fc1 = nn.Linear(64*2,50)
self.fc2 = nn.Linear(50,1)
def forward(self,x):
x = self.conv1d(x)
x = self.relu(x)
x = x.view(-1)
print('x size',x.size())
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
return x
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = CNN_ForecastNet().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-5)
criterion = nn.MSELoss()
train_losses = []
def Train():
running_loss = .0
model.train()
for idx, (inputs,labels) in enumerate(train_loader):
inputs = inputs.to(device)
labels = labels.to(device)
optimizer.zero_grad()
print('--- idx ---',idx)
print('inputs ',inputs)
preds = model(inputs.float())
loss = criterion(preds,labels.float())
loss.backward()
optimizer.step()
running_loss += loss
train_loss = running_loss/len(train_loader)
train_losses.append(train_loss.detach().numpy())
print(f'train_loss {train_loss}')
train = ElecDataset(train_x.reshape(train_x.shape[0],train_x.shape[1],1),train_y)
train_loader = torch.utils.data.DataLoader(train,batch_size=2,shuffle=False)
epochs = 1
for epoch in range(epochs):
print('epochs {}/{}'.format(epoch+1,epochs))
Train()
gc.collect()