My CNN model is as follows:
class ConvNormPool(nn.Module):
“”“Conv Skip-connection module”""
def init(
self,
input_size,
hidden_size,
kernel_size,
norm_type=‘bachnorm’
):
super().init()
self.kernel_size = kernel_size
self.conv_1 = nn.Conv1d(
in_channels=input_size,
out_channels=hidden_size,
kernel_size=kernel_size
)
self.conv_2 = nn.Conv1d(
in_channels=hidden_size,
out_channels=hidden_size,
kernel_size=kernel_size
)
self.conv_3 = nn.Conv1d(
in_channels=hidden_size,
out_channels=hidden_size,
kernel_size=kernel_size
)
self.swish_1 = Swish()
self.swish_2 = Swish()
self.swish_3 = Swish()
if norm_type == 'group':
self.normalization_1 = nn.GroupNorm(
num_groups=8,
num_channels=hidden_size
)
self.normalization_2 = nn.GroupNorm(
num_groups=8,
num_channels=hidden_size
)
self.normalization_3 = nn.GroupNorm(
num_groups=8,
num_channels=hidden_size
)
else:
self.normalization_1 = nn.BatchNorm1d(num_features=hidden_size)
self.normalization_2 = nn.BatchNorm1d(num_features=hidden_size)
self.normalization_3 = nn.BatchNorm1d(num_features=hidden_size)
self.pool = nn.MaxPool1d(kernel_size=2)
def forward(self, input):
#print("INPUT SHAPE SKIP")
#print(input.shape)
conv1 = self.conv_1(input)
x = self.normalization_1(conv1)
x = self.swish_1(x)
x = F.pad(x, pad=(self.kernel_size - 1, 0))
x = self.conv_2(x)
x = self.normalization_2(x)
x = self.swish_2(x)
x = F.pad(x, pad=(self.kernel_size - 1, 0))
conv3 = self.conv_3(x)
x = self.normalization_3(conv1+conv3)
x = self.swish_3(x)
x = F.pad(x, pad=(self.kernel_size - 1, 0))
x = self.pool(x)
return x
class CNN(nn.Module):
def init(
self,
input_size = 1,
hid_size = 256,
kernel_size = 5,
num_classes = 5,
):
super().__init__()
self.conv1 = ConvNormPool(
input_size=input_size,
hidden_size=hid_size,
kernel_size=kernel_size,
)
self.conv2 = ConvNormPool(
input_size=hid_size,
hidden_size=hid_size//2,
kernel_size=kernel_size,
)
self.conv3 = ConvNormPool(
input_size=hid_size//2,
hidden_size=hid_size//4,
kernel_size=kernel_size,
)
self.avgpool = nn.AdaptiveAvgPool1d((1))
self.fc = nn.Linear(in_features=hid_size//4, out_features=num_classes)
***self.softmax = nn.LogSoftmax(dim=1)***
def forward(self, input):
#print("INPUT SHAPE is ")
#print(input.shape)
#print("INPUT SHAPE is ")
#print(input.shape)
#input = input.unsqueeze(1)
#input = input.unsqueeze(0)
x = self.conv1(input)
x = self.conv2(x)
x = self.conv3(x)
x = self.avgpool(x)
# print(x.shape) # num_features * num_channels log_
x = x.view(-1, x.size(1) * x.size(2))
x = F.softmax(self.fc(x), dim=1) #x = F.softmax(self.fc(x), dim=1) x = F.log_softmax(self.fc(x), dim=1)
return x
m1=CNN(m1=CNN(num_classes=5, hid_size=128).to(device)
n I call summary(m1,(32,187))
It gives error 
RuntimeError: Given groups=1, weight of size [128, 1, 5], expected input[2, 32, 187] to have 1 channels, but got 32 channels instead
How Can I remove this??
However when I use:
summary(m1, (1,187),32):
I get summary as:
Layer (type) Output Shape Param #
Conv1d-1 [32, 128, 183] 768
BatchNorm1d-2 [32, 128, 183] 256
Swish-3 [32, 128, 183] 0
Conv1d-4 [32, 128, 183] 82,048
BatchNorm1d-5 [32, 128, 183] 256
Swish-6 [32, 128, 183] 0
Conv1d-7 [32, 128, 183] 82,048
BatchNorm1d-8 [32, 128, 183] 256
Swish-9 [32, 128, 183] 0
MaxPool1d-10 [32, 128, 93] 0
ConvNormPool-11 [32, 128, 93] 0
Conv1d-12 [32, 64, 89] 41,024
BatchNorm1d-13 [32, 64, 89] 128
Swish-14 [32, 64, 89] 0
Conv1d-15 [32, 64, 89] 20,544
BatchNorm1d-16 [32, 64, 89] 128
Swish-17 [32, 64, 89] 0
Conv1d-18 [32, 64, 89] 20,544
BatchNorm1d-19 [32, 64, 89] 128
Swish-20 [32, 64, 89] 0
MaxPool1d-21 [32, 64, 46] 0
ConvNormPool-22 [32, 64, 46] 0
Conv1d-23 [32, 32, 42] 10,272
BatchNorm1d-24 [32, 32, 42] 64
Swish-25 [32, 32, 42] 0
Conv1d-26 [32, 32, 42] 5,152
BatchNorm1d-27 [32, 32, 42] 64
Swish-28 [32, 32, 42] 0
Conv1d-29 [32, 32, 42] 5,152
BatchNorm1d-30 [32, 32, 42] 64
Swish-31 [32, 32, 42] 0
MaxPool1d-32 [32, 32, 23] 0
ConvNormPool-33 [32, 32, 23] 0
AdaptiveAvgPool1d-34 [32, 32, 1] 0
Linear-35 [32, 5] 165
Total params: 269,061
Trainable params: 269,061
Non-trainable params: 0
Input size (MB): 0.02
Forward/backward pass size (MB): 74.56
Params size (MB): 1.03
Estimated Total Size (MB): 75.61
IS MY MODEL CORRECT??
HAVE I PUT ALL LAYERS IN PLACE?
How do I corect the 1st error?
ALSO, self.softmax = nn.LogSoftmax(dim=1) needs to be inserted??I am using CROSSENTROPYLOSS