i am using a cnn_svm architecture for multi-class classifcation , 3d resnet for feature extraction and svm as classifier i did some modification on my model
import math
from functools import partial
import torch
import torch.nn as nn
import torch.nn.functional as F
def get_inplanes():
return [64, 128, 256, 512]
def conv3x3x3(in_planes, out_planes, stride=1):
return nn.Conv3d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def conv1x1x1(in_planes, out_planes, stride=1):
return nn.Conv3d(in_planes,
out_planes,
kernel_size=1,
stride=stride,
bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1, downsample=None):
super().__init__()
self.conv1 = conv3x3x3(in_planes, planes, stride)
self.bn1 = nn.BatchNorm3d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3x3(planes, planes)
self.bn2 = nn.BatchNorm3d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1, downsample=None):
super().__init__()
self.conv1 = conv1x1x1(in_planes, planes)
self.bn1 = nn.BatchNorm3d(planes)
self.conv2 = conv3x3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm3d(planes)
self.conv3 = conv1x1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm3d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self,
block,
layers,
block_inplanes,
n_input_channels=3,
conv1_t_size=7,
conv1_t_stride=1,
no_max_pool=False,
shortcut_type='B',
widen_factor=1.0,
n_classes=400):
super().__init__()
block_inplanes = [int(x * widen_factor) for x in block_inplanes]
self.in_planes = block_inplanes[0]
self.no_max_pool = no_max_pool
self.conv1 = nn.Conv3d(n_input_channels,
self.in_planes,
kernel_size=(conv1_t_size, 7, 7),
stride=(conv1_t_stride, 2, 2),
padding=(conv1_t_size // 2, 3, 3),
bias=False)
self.bn1 = nn.BatchNorm3d(self.in_planes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool3d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, block_inplanes[0], layers[0],
shortcut_type)
self.layer2 = self._make_layer(block,
block_inplanes[1],
layers[1],
shortcut_type,
stride=2)
self.layer3 = self._make_layer(block,
block_inplanes[2],
layers[2],
shortcut_type,
stride=2)
self.layer4 = self._make_layer(block,
block_inplanes[3],
layers[3],
shortcut_type,
stride=2)
self.avgpool = nn.AdaptiveAvgPool3d((1, 1, 1))
for m in self.modules():
if isinstance(m, nn.Conv3d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, nn.BatchNorm3d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _downsample_basic_block(self, x, planes, stride):
out = F.avg_pool3d(x, kernel_size=1, stride=stride)
zero_pads = torch.zeros(out.size(0), planes - out.size(1), out.size(2),
out.size(3), out.size(4))
if isinstance(out.data, torch.cuda.FloatTensor):
zero_pads = zero_pads.cuda()
out = torch.cat([out.data, zero_pads], dim=1)
return out
def _make_layer(self, block, planes, blocks, shortcut_type, stride=1):
downsample = None
if stride != 1 or self.in_planes != planes * block.expansion:
if shortcut_type == 'A':
downsample = partial(self._downsample_basic_block,
planes=planes * block.expansion,
stride=stride)
else:
downsample = nn.Sequential(
conv1x1x1(self.in_planes, planes * block.expansion, stride),
nn.BatchNorm3d(planes * block.expansion))
layers = []
layers.append(
block(in_planes=self.in_planes,
planes=planes,
stride=stride,
downsample=downsample))
self.in_planes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.in_planes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
if not self.no_max_pool:
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
feature_vector = x.view(x.size(0), -1)
return feature_vector
#now the resnet return the feautre vector without the classification result
def generate_model(model_depth, **kwargs):
assert model_depth in [10, 18, 34, 50, 101, 152, 200]
if model_depth == 10:
model = ResNet(BasicBlock, [1, 1, 1, 1], get_inplanes(), **kwargs)
elif model_depth == 18:
model = ResNet(BasicBlock, [2, 2, 2, 2], get_inplanes(), **kwargs)
elif model_depth == 34:
model = ResNet(BasicBlock, [3, 4, 6, 3], get_inplanes(), **kwargs)
elif model_depth == 50:
model = ResNet(Bottleneck, [3, 4, 6, 3], get_inplanes(), **kwargs)
elif model_depth == 101:
model = ResNet(Bottleneck, [3, 4, 23, 3], get_inplanes(), **kwargs)
elif model_depth == 152:
model = ResNet(Bottleneck, [3, 8, 36, 3], get_inplanes(), **kwargs)
elif model_depth == 200:
model = ResNet(Bottleneck, [3, 24, 36, 3], get_inplanes(), **kwargs)
return model
i replaced the fully connected layer with feature_vector= feature_vector = x.view(x.size(0), -1) after the avgpooling layer
and then finetuned on a pretrained 3dresnet model also i used this code
def get_module_name(name):
name = name.split('.')
if name[0] == 'module':
i = 1
else:
i = 0
if name[i] == 'features':
i += 1
return name[i]
def get_fine_tuning_parameters(model, ft_begin_module):
if not ft_begin_module:
return model.parameters()
parameters = []
add_flag = False
for k, v in model.named_parameters():
if ft_begin_module == get_module_name(k):
add_flag = True
if add_flag:
parameters.append({'params': v})
return parameters
def generate_model(opt):
model = resnet.generate_model(model_depth=opt.model_depth,
n_input_channels=opt.n_input_channels,
shortcut_type=opt.resnet_shortcut,
conv1_t_size=opt.conv1_t_size,
conv1_t_stride=opt.conv1_t_stride,
no_max_pool=opt.no_max_pool,
widen_factor=opt.resnet_widen_factor)
return model
def load_pretrained_model(model, pretrain_path, model_name,n_finetune_classes):
if pretrain_path:
print('loading pretrained model {}'.format(pretrain_path))
pretrain = torch.load(pretrain_path, map_location='cpu')
# Load state dict, but exclude FC layer parameters if they exist
state_dict = {k: v for k, v in pretrain['state_dict'].items() if 'fc' not in k and 'classifier' not in k}
model.load_state_dict(state_dict, strict=False) # Load only matching layers
model.fc = None
return model
i removed the fully connected layer from the pretrained model also then in the main i define it as this
# Generate the resnet model with finetuning as a feature extractor
model = generate_model(opt)
if opt.pretrain_path:
model = load_pretrained_model(model, opt.pretrain_path, opt.model,opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_module)
else:
parameters = model.parameters()
model.to(opt.device)
but in the inference step it’s only predicting one classe
Am I using the model in the right way !!