When i am trying to run ResNet architecture i am getting num_features argument missing. i couldn’t figure out where the problem is
import torch
import torch.nn as nn
from numpy.random import normal
from numpy.linalg import svd
from math import sqrt
import torch.nn.init
from .common import *
class ResidualSequential(nn.Sequential):
def __init__(self, *args):
super(ResidualSequential, self).__init__(*args)
def forward(self, x):
out = super(ResidualSequential, self).forward(x)
# print(x.size(), out.size())
x_ = None
if out.size(2) != x.size(2) or out.size(3) != x.size(3):
diff2 = x.size(2) - out.size(2)
diff3 = x.size(3) - out.size(3)
# print(1)
x_ = x[:, :, diff2 /2:out.size(2) + diff2 / 2, diff3 / 2:out.size(3) + diff3 / 2]
else:
x_ = x
return out + x_
def eval(self):
print(2)
for m in self.modules():
m.eval()
exit()
def get_block(num_channels, norm_layer, act_fun):
layers = [
nn.Conv2d(num_channels, num_channels, 3, 1, 1, bias=False),
norm_layer(num_channels, affine=True),
act(act_fun),
nn.Conv2d(num_channels, num_channels, 3, 1, 1, bias=False),
norm_layer(num_channels, affine=True),
]
return layers
class ResNet(nn.Module):
def __init__(self, num_input_channels, num_output_channels, num_blocks, num_channels, need_residual=True, act_fun='LeakyReLU', need_sigmoid=True, norm_layer=nn.BatchNorm2d, pad='reflection'):
'''
pad = 'start|zero|replication'
'''
super(ResNet, self).__init__()
if need_residual:
s = ResidualSequential
else:
s = nn.Sequential
stride = 1
# First layers
layers = [
# nn.ReplicationPad2d(num_blocks * 2 * stride + 3),
conv(num_input_channels, num_channels, 3, stride=1, bias=True, pad=pad),
act(act_fun)
]
# Residual blocks
# layers_residual = []
for i in range(num_blocks):
layers += [s(*get_block(num_channels, norm_layer, act_fun))]
layers += [
nn.Conv2d(num_channels, num_channels, 3, 1, 1),
norm_layer(num_channels, affine=True)
]
# if need_residual:
# layers += [ResidualSequential(*layers_residual)]
# else:
# layers += [Sequential(*layers_residual)]
# if factor >= 2:
# # Do upsampling if needed
# layers += [
# nn.Conv2d(num_channels, num_channels *
# factor ** 2, 3, 1),
# nn.PixelShuffle(factor),
# act(act_fun)
# ]
layers += [
conv(num_channels, num_output_channels, 3, 1, bias=True, pad=pad),
nn.Sigmoid()
]
self.model = nn.Sequential(*layers)
def forward(self, input):
return self.model(input)
def eval(self):
self.model.eval()
input_depth = 32
figsize = 4
net = get_net(input_depth, 'ResNet', pad,
num_scales=5,
upsample_mode='bilinear').type(dtype)
Error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-7-9bb0b8e81004> in <module>()
18 net = get_net(input_depth, 'ResNet', pad,
19 num_scales=5,
---> 20 upsample_mode='bilinear').type(dtype)
21
22 else:
2 frames
/content/models/__init__.py in get_net(input_depth, NET_TYPE, pad, upsample_mode, n_channels, act_fun, skip_n33d, skip_n33u, skip_n11, num_scales, downsample_mode)
9 if NET_TYPE == 'ResNet':
10 # TODO
---> 11 net = ResNet(input_depth, 3, 10, 16, 1, nn.BatchNorm2d, False)
12 elif NET_TYPE == 'skip':
13 net = skip(input_depth, n_channels, num_channels_down = [skip_n33d]*num_scales if isinstance(skip_n33d, int) else skip_n33d,
/content/models/resnet.py in __init__(self, num_input_channels, num_output_channels, num_blocks, num_channels, need_residual, act_fun, need_sigmoid, norm_layer, pad)
59 # nn.ReplicationPad2d(num_blocks * 2 * stride + 3),
60 conv(num_input_channels, num_channels, 3, stride=1, bias=True, pad=pad),
---> 61 act(act_fun)
62 ]
63 # Residual blocks
/content/models/common.py in act(act_fun)
90 assert False
91 else:
---> 92 return act_fun()
93
94
TypeError: __init__() missing 1 required positional argument: 'num_features'