Hy all, i have two model: a Multi Layer Perception and a Temporal convolutional Network.
Here the MLP:
class DeepMLPRegressor(nn.Module):
def __init__(self, in_features, out_features):
super(DeepMLPRegressor, self).__init__()
self.model = nn.Sequential(nn.Linear(in_features, 32),
nn.ReLU(),
nn.Linear(32, 64),
nn.ReLU(),
nn.Linear(64, 128),
nn.ReLU(),
nn.Linear(128, 64),
nn.ReLU(),
nn.Linear(64, 32),
nn.ReLU(),
nn.Linear(32,16))
#this 16 with the entrance of TCN
def forward(self, x):
return self.model(x)
and here the TCN:
import torch
import torch.nn as nn
from torch.nn.utils import weight_norm
class Chomp1d(nn.Module):
def __init__(self, chomp_size):
super(Chomp1d, self).__init__()
self.chomp_size = chomp_size
def forward(self, x):
return x[:, :, :-self.chomp_size].contiguous()
class TemporalBlock(nn.Module):
def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding, dropout=0.2):
super(TemporalBlock, self).__init__()
self.conv1 = weight_norm(nn.Conv1d(n_inputs, n_outputs, kernel_size,
stride=stride, padding=padding, dilation=dilation))
self.chomp1 = Chomp1d(padding)
self.relu1 = nn.ReLU()
self.dropout1 = nn.Dropout(dropout)
self.conv2 = weight_norm(nn.Conv1d(n_outputs, n_outputs, kernel_size,
stride=stride, padding=padding, dilation=dilation))
self.chomp2 = Chomp1d(padding)
self.relu2 = nn.ReLU()
self.dropout2 = nn.Dropout(dropout)
self.net = nn.Sequential(self.conv1, self.chomp1, self.relu1, self.dropout1,
self.conv2, self.chomp2, self.relu2, self.dropout2)
self.downsample = nn.Conv1d(n_inputs, n_outputs, 1) if n_inputs != n_outputs else None
self.relu = nn.ReLU()
self.init_weights()
def init_weights(self):
self.conv1.weight.data.normal_(0, 0.01)
self.conv2.weight.data.normal_(0, 0.01)
if self.downsample is not None:
self.downsample.weight.data.normal_(0, 0.01)
def forward(self, x):
out = self.net(x)
res = x if self.downsample is None else self.downsample(x)
return self.relu(out + res)
class TemporalConvNet(nn.Module):
def __init__(self, num_inputs, num_channels, kernel_size=2, dropout=0.2):
super(TemporalConvNet, self).__init__()
layers = []
num_levels = len(num_channels)
for i in range(num_levels):
dilation_size = 2 ** i
in_channels = num_inputs if i == 0 else num_channels[i-1]
out_channels = num_channels[i]
layers += [TemporalBlock(in_channels, out_channels, kernel_size, stride=1, dilation=dilation_size,
padding=(kernel_size-1) * dilation_size, dropout=dropout)]
self.network = nn.Sequential(*layers)
def forward(self, x):
return self.network(x)
class TCN(nn.Module):
def __init__(self, input_size, output_size, num_channels, kernel_size, dropout):
super(TCN, self).__init__()
self.tcn = TemporalConvNet(input_size, num_channels, kernel_size=kernel_size, dropout=dropout)
self.linear = nn.Linear(num_channels[-1], output_size)
self.init_weights()
def init_weights(self):
self.linear.weight.data.normal_(0, 0.01)
def forward(self, x):
y1 = self.tcn(x)
return self.linear(y1[:, :, -1])
I create this class:
class FinalModel(nn.Module):
def __init__(self, input_size, output_size):
super(FinalModel, self).__init__()
self.model1 = DeepMLPRegressor(input_size)
self.model2 = TCN(input_size=16, output_size=output_size, num_channels=[16],kernel_size = 2, dropout=0.25)
def forward(self, x):
x1 = self.model1(x)
y = self.model2(x1)
return y
I would like an output of 2.
I have this error:
RuntimeError: Expected 3-dimensional input for 3-dimensional weight [16, 16, 2], but got 2-dimensional input of size [16, 16] instead
Why the kernel size is a part of dimension and how can i connect in the right way the MLP exit with the TCN entrance?