Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix EfficientAD to use width and height of the input #1355

Merged
merged 3 commits into from
Sep 26, 2023
Merged

Fix EfficientAD to use width and height of the input #1355

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9bbc474
Fix EfficientAD to use two dimensions of the input
abc-125 Sep 23, 2023
a861d1a
Update src/anomalib/models/efficient_ad/torch_model.py
abc-125 Sep 25, 2023
2933dbe
Update torch_model.py
samet-akcay Sep 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 11 additions & 8 deletions src/anomalib/models/efficient_ad/torch_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,12 +141,14 @@ class Decoder(nn.Module):

Args:
out_channels (int): number of convolution output channels
img_size (tuple): size of input images
"""

def __init__(self, out_channels, padding, img_size, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)
self.img_size = img_size
self.last_upsample = int(img_size / 4) if padding else int(img_size / 4) - 8
self.last_upsample = (int(img_size[0] / 4) if padding else int(img_size[0] / 4) - 8,
int(img_size[1] / 4) if padding else int(img_size[1] / 4) - 8)
abc-125 marked this conversation as resolved.
Show resolved Hide resolved
self.deconv1 = nn.Conv2d(64, 64, kernel_size=4, stride=1, padding=2)
self.deconv2 = nn.Conv2d(64, 64, kernel_size=4, stride=1, padding=2)
self.deconv3 = nn.Conv2d(64, 64, kernel_size=4, stride=1, padding=2)
Expand All @@ -163,22 +165,22 @@ def __init__(self, out_channels, padding, img_size, *args, **kwargs) -> None:
self.dropout6 = nn.Dropout(p=0.2)

def forward(self, x):
x = F.interpolate(x, size=int(self.img_size / 64) - 1, mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 64) - 1, int(self.img_size[1] / 64) - 1), mode="bilinear")
x = F.relu(self.deconv1(x))
x = self.dropout1(x)
x = F.interpolate(x, size=int(self.img_size / 32), mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 32), int(self.img_size[1] / 32)), mode="bilinear")
x = F.relu(self.deconv2(x))
x = self.dropout2(x)
x = F.interpolate(x, size=int(self.img_size / 16) - 1, mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 16) - 1, int(self.img_size[1] / 16) - 1), mode="bilinear")
x = F.relu(self.deconv3(x))
x = self.dropout3(x)
x = F.interpolate(x, size=int(self.img_size / 8), mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 8), int(self.img_size[1] / 8)), mode="bilinear")
x = F.relu(self.deconv4(x))
x = self.dropout4(x)
x = F.interpolate(x, size=int(self.img_size / 4) - 1, mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 4) - 1, int(self.img_size[1] / 4) - 1), mode="bilinear")
x = F.relu(self.deconv5(x))
x = self.dropout5(x)
x = F.interpolate(x, size=int(self.img_size / 2) - 1, mode="bilinear")
x = F.interpolate(x, size=(int(self.img_size[0] / 2) - 1, int(self.img_size[1] / 2) - 1), mode="bilinear")
x = F.relu(self.deconv6(x))
x = self.dropout6(x)
x = F.interpolate(x, size=self.last_upsample, mode="bilinear")
Expand All @@ -192,6 +194,7 @@ class AutoEncoder(nn.Module):

Args:
out_channels (int): number of convolution output channels
img_size (tuple): size of input images
"""

def __init__(self, out_channels, padding, img_size, *args, **kwargs) -> None:
Expand Down Expand Up @@ -245,7 +248,7 @@ def __init__(
else:
raise ValueError(f"Unknown model size {model_size}")

self.ae: AutoEncoder = AutoEncoder(out_channels=teacher_out_channels, padding=padding, img_size=input_size[0])
self.ae: AutoEncoder = AutoEncoder(out_channels=teacher_out_channels, padding=padding, img_size=input_size)
self.teacher_out_channels: int = teacher_out_channels
self.input_size: tuple[int, int] = input_size

Expand Down