I built a image multi label recognition model based on resnet-50, the network is as follows (it’s exactly the same as in the torchvision.models.resnet50 , with the only difference in the final softmax layer in the forward function).
My dataset contain 6000 images with 15 classes, each image may have 1 to 5 labels. But after training, the model seems not converge, with always predicting zeros for all labels.
class ResNetMultiTag(nn.Module):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
groups=1, width_per_group=64, replace_stride_with_dilation=None,
norm_layer=None):
super(ResNetMultiTag, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes * 2) # special
self.softmax = nn.Softmax(dim=-1) # special
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
norm_layer = self._norm_layer
downsample = None
previous_dilation = self.dilation
if dilate:
self.dilation *= stride
stride = 1
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
norm_layer(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation, norm_layer))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, dilation=self.dilation,
norm_layer=norm_layer))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.reshape(x.size(0), -1)
x = self.fc(x)
x = x.reshape(x.size(0), -1, 2) # special
x = self.softmax(x) # special
return x
This is the loss function I use:
def get_tag_loss(self, pred, label):
'''
pred: [batchsize, num_classes, 2]
label: [batchsize, num_classes, 2]
'''
pred = pred.contiguous().view(-1,2)
label = label.contiguous().view(-1,2)
label_scalar = label[:, 1]
logp = torch.nn.functional.log_softmax(pred, dim=-1)
ce = -logp[range(label_scalar.shape[0]), label_scalar.long()]
loss = torch.sum( ce )
return loss
I use SGD with lr ranges from 1e-2 to 1e-4, I have 6000 images, 15 classes. Each image may have 1 to 5 labels. The number of labels is un-balanced but I have done the resampling to keep the balance.
However, the model does not converge.
I tried to train the model on only one image, this case the model converges to the correct labels. However, even if I use only two images, just add one more image, the model failed to converge.
What’s wrong with my implementation?
Did I use the wrong loss function, wrong model, or I make other mistakes?
Thank you all for helping me!!