Hello, i am using dataset for detection of road that consist of 500 training images and masks. When other guys used this dataset they had PERFECT results and let me show you my result.
Result of training - output - YouTube
I want to ask if you can help with this model, what to improve on this model to get better results? I tried all possible learning rates and epochs. So this is problem in model not in training. Thank you.
I am using this model for it.
def double_conv(in_channels, out_channels):
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, 3, padding=1),
torch.nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels, 3, padding=1),
torch.nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True)
)
class Model(nn.Module):
def __init__(self, n_class=5):
super(Model).__init__()
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
self.dconv_down1 = double_conv(3, 64)
self.dconv_down2 = double_conv(64, 128)
self.dconv_down3 = double_conv(128, 256)
self.dconv_down4 = double_conv(256, 512)
self.maxool = nn.MaxPool2d(2)
self.upsample = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.dconv_up3 = double_conv(256 + 512, 256)
self.dconv_up2 = double_conv(128 + 256, 128)
self.dconv_up1 = double_conv(128 + 64, 64)
self.conv_last = nn.Conv2d(64, n_class, 1)
def forward(self, x):
conv1 = self.dconv_down1(x)
x = self.maxpool(conv1)
conv2 = self.dconv_down2(x)
x = self.maxpool(conv2)
conv3 = self.dconv_down3(x)
x = self.maxpool(conv3)
x = self.dconv_down4(x)
x = self.upsample(x)
x = torch.cat([x, conv3], dim=1)
x = self.dconv_up3(x)
x = self.upsample(x)
x = torch.cat([x, conv2], dim=1)
x = self.dconv_up2(x)
x = self.upsample(x)
x = torch.cat([x, conv1], dim=1)
x = self.dconv_up1(x)
out = self.conv_last(x)
return out