Initial commit
This commit is contained in:
Lihe Yang
148
depth_anything_v2/util/blocks.py
Normal file
148
depth_anything_v2/util/blocks.py
Normal file
@@ -0,0 +1,148 @@
|
||||
import torch.nn as nn
|
||||
|
||||
|
||||
def _make_scratch(in_shape, out_shape, groups=1, expand=False):
|
||||
scratch = nn.Module()
|
||||
|
||||
out_shape1 = out_shape
|
||||
out_shape2 = out_shape
|
||||
out_shape3 = out_shape
|
||||
if len(in_shape) >= 4:
|
||||
out_shape4 = out_shape
|
||||
|
||||
if expand:
|
||||
out_shape1 = out_shape
|
||||
out_shape2 = out_shape * 2
|
||||
out_shape3 = out_shape * 4
|
||||
if len(in_shape) >= 4:
|
||||
out_shape4 = out_shape * 8
|
||||
|
||||
scratch.layer1_rn = nn.Conv2d(in_shape[0], out_shape1, kernel_size=3, stride=1, padding=1, bias=False, groups=groups)
|
||||
scratch.layer2_rn = nn.Conv2d(in_shape[1], out_shape2, kernel_size=3, stride=1, padding=1, bias=False, groups=groups)
|
||||
scratch.layer3_rn = nn.Conv2d(in_shape[2], out_shape3, kernel_size=3, stride=1, padding=1, bias=False, groups=groups)
|
||||
if len(in_shape) >= 4:
|
||||
scratch.layer4_rn = nn.Conv2d(in_shape[3], out_shape4, kernel_size=3, stride=1, padding=1, bias=False, groups=groups)
|
||||
|
||||
return scratch
|
||||
|
||||
|
||||
class ResidualConvUnit(nn.Module):
|
||||
"""Residual convolution module.
|
||||
"""
|
||||
|
||||
def __init__(self, features, activation, bn):
|
||||
"""Init.
|
||||
|
||||
Args:
|
||||
features (int): number of features
|
||||
"""
|
||||
super().__init__()
|
||||
|
||||
self.bn = bn
|
||||
|
||||
self.groups=1
|
||||
|
||||
self.conv1 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
|
||||
|
||||
self.conv2 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
|
||||
|
||||
if self.bn == True:
|
||||
self.bn1 = nn.BatchNorm2d(features)
|
||||
self.bn2 = nn.BatchNorm2d(features)
|
||||
|
||||
self.activation = activation
|
||||
|
||||
self.skip_add = nn.quantized.FloatFunctional()
|
||||
|
||||
def forward(self, x):
|
||||
"""Forward pass.
|
||||
|
||||
Args:
|
||||
x (tensor): input
|
||||
|
||||
Returns:
|
||||
tensor: output
|
||||
"""
|
||||
|
||||
out = self.activation(x)
|
||||
out = self.conv1(out)
|
||||
if self.bn == True:
|
||||
out = self.bn1(out)
|
||||
|
||||
out = self.activation(out)
|
||||
out = self.conv2(out)
|
||||
if self.bn == True:
|
||||
out = self.bn2(out)
|
||||
|
||||
if self.groups > 1:
|
||||
out = self.conv_merge(out)
|
||||
|
||||
return self.skip_add.add(out, x)
|
||||
|
||||
|
||||
class FeatureFusionBlock(nn.Module):
|
||||
"""Feature fusion block.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
features,
|
||||
activation,
|
||||
deconv=False,
|
||||
bn=False,
|
||||
expand=False,
|
||||
align_corners=True,
|
||||
size=None
|
||||
):
|
||||
"""Init.
|
||||
|
||||
Args:
|
||||
features (int): number of features
|
||||
"""
|
||||
super(FeatureFusionBlock, self).__init__()
|
||||
|
||||
self.deconv = deconv
|
||||
self.align_corners = align_corners
|
||||
|
||||
self.groups=1
|
||||
|
||||
self.expand = expand
|
||||
out_features = features
|
||||
if self.expand == True:
|
||||
out_features = features // 2
|
||||
|
||||
self.out_conv = nn.Conv2d(features, out_features, kernel_size=1, stride=1, padding=0, bias=True, groups=1)
|
||||
|
||||
self.resConfUnit1 = ResidualConvUnit(features, activation, bn)
|
||||
self.resConfUnit2 = ResidualConvUnit(features, activation, bn)
|
||||
|
||||
self.skip_add = nn.quantized.FloatFunctional()
|
||||
|
||||
self.size=size
|
||||
|
||||
def forward(self, *xs, size=None):
|
||||
"""Forward pass.
|
||||
|
||||
Returns:
|
||||
tensor: output
|
||||
"""
|
||||
output = xs[0]
|
||||
|
||||
if len(xs) == 2:
|
||||
res = self.resConfUnit1(xs[1])
|
||||
output = self.skip_add.add(output, res)
|
||||
|
||||
output = self.resConfUnit2(output)
|
||||
|
||||
if (size is None) and (self.size is None):
|
||||
modifier = {"scale_factor": 2}
|
||||
elif size is None:
|
||||
modifier = {"size": self.size}
|
||||
else:
|
||||
modifier = {"size": size}
|
||||
|
||||
output = nn.functional.interpolate(output, **modifier, mode="bilinear", align_corners=self.align_corners)
|
||||
|
||||
output = self.out_conv(output)
|
||||
|
||||
return output
|
||||
158
depth_anything_v2/util/transform.py
Normal file
158
depth_anything_v2/util/transform.py
Normal file
@@ -0,0 +1,158 @@
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
|
||||
class Resize(object):
|
||||
"""Resize sample to given size (width, height).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
width,
|
||||
height,
|
||||
resize_target=True,
|
||||
keep_aspect_ratio=False,
|
||||
ensure_multiple_of=1,
|
||||
resize_method="lower_bound",
|
||||
image_interpolation_method=cv2.INTER_AREA,
|
||||
):
|
||||
"""Init.
|
||||
|
||||
Args:
|
||||
width (int): desired output width
|
||||
height (int): desired output height
|
||||
resize_target (bool, optional):
|
||||
True: Resize the full sample (image, mask, target).
|
||||
False: Resize image only.
|
||||
Defaults to True.
|
||||
keep_aspect_ratio (bool, optional):
|
||||
True: Keep the aspect ratio of the input sample.
|
||||
Output sample might not have the given width and height, and
|
||||
resize behaviour depends on the parameter 'resize_method'.
|
||||
Defaults to False.
|
||||
ensure_multiple_of (int, optional):
|
||||
Output width and height is constrained to be multiple of this parameter.
|
||||
Defaults to 1.
|
||||
resize_method (str, optional):
|
||||
"lower_bound": Output will be at least as large as the given size.
|
||||
"upper_bound": Output will be at max as large as the given size. (Output size might be smaller than given size.)
|
||||
"minimal": Scale as least as possible. (Output size might be smaller than given size.)
|
||||
Defaults to "lower_bound".
|
||||
"""
|
||||
self.__width = width
|
||||
self.__height = height
|
||||
|
||||
self.__resize_target = resize_target
|
||||
self.__keep_aspect_ratio = keep_aspect_ratio
|
||||
self.__multiple_of = ensure_multiple_of
|
||||
self.__resize_method = resize_method
|
||||
self.__image_interpolation_method = image_interpolation_method
|
||||
|
||||
def constrain_to_multiple_of(self, x, min_val=0, max_val=None):
|
||||
y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int)
|
||||
|
||||
if max_val is not None and y > max_val:
|
||||
y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int)
|
||||
|
||||
if y < min_val:
|
||||
y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int)
|
||||
|
||||
return y
|
||||
|
||||
def get_size(self, width, height):
|
||||
# determine new height and width
|
||||
scale_height = self.__height / height
|
||||
scale_width = self.__width / width
|
||||
|
||||
if self.__keep_aspect_ratio:
|
||||
if self.__resize_method == "lower_bound":
|
||||
# scale such that output size is lower bound
|
||||
if scale_width > scale_height:
|
||||
# fit width
|
||||
scale_height = scale_width
|
||||
else:
|
||||
# fit height
|
||||
scale_width = scale_height
|
||||
elif self.__resize_method == "upper_bound":
|
||||
# scale such that output size is upper bound
|
||||
if scale_width < scale_height:
|
||||
# fit width
|
||||
scale_height = scale_width
|
||||
else:
|
||||
# fit height
|
||||
scale_width = scale_height
|
||||
elif self.__resize_method == "minimal":
|
||||
# scale as least as possbile
|
||||
if abs(1 - scale_width) < abs(1 - scale_height):
|
||||
# fit width
|
||||
scale_height = scale_width
|
||||
else:
|
||||
# fit height
|
||||
scale_width = scale_height
|
||||
else:
|
||||
raise ValueError(f"resize_method {self.__resize_method} not implemented")
|
||||
|
||||
if self.__resize_method == "lower_bound":
|
||||
new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height)
|
||||
new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width)
|
||||
elif self.__resize_method == "upper_bound":
|
||||
new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height)
|
||||
new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width)
|
||||
elif self.__resize_method == "minimal":
|
||||
new_height = self.constrain_to_multiple_of(scale_height * height)
|
||||
new_width = self.constrain_to_multiple_of(scale_width * width)
|
||||
else:
|
||||
raise ValueError(f"resize_method {self.__resize_method} not implemented")
|
||||
|
||||
return (new_width, new_height)
|
||||
|
||||
def __call__(self, sample):
|
||||
width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0])
|
||||
|
||||
# resize sample
|
||||
sample["image"] = cv2.resize(sample["image"], (width, height), interpolation=self.__image_interpolation_method)
|
||||
|
||||
if self.__resize_target:
|
||||
if "depth" in sample:
|
||||
sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST)
|
||||
|
||||
if "mask" in sample:
|
||||
sample["mask"] = cv2.resize(sample["mask"].astype(np.float32), (width, height), interpolation=cv2.INTER_NEAREST)
|
||||
|
||||
return sample
|
||||
|
||||
|
||||
class NormalizeImage(object):
|
||||
"""Normlize image by given mean and std.
|
||||
"""
|
||||
|
||||
def __init__(self, mean, std):
|
||||
self.__mean = mean
|
||||
self.__std = std
|
||||
|
||||
def __call__(self, sample):
|
||||
sample["image"] = (sample["image"] - self.__mean) / self.__std
|
||||
|
||||
return sample
|
||||
|
||||
|
||||
class PrepareForNet(object):
|
||||
"""Prepare sample for usage as network input.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def __call__(self, sample):
|
||||
image = np.transpose(sample["image"], (2, 0, 1))
|
||||
sample["image"] = np.ascontiguousarray(image).astype(np.float32)
|
||||
|
||||
if "depth" in sample:
|
||||
depth = sample["depth"].astype(np.float32)
|
||||
sample["depth"] = np.ascontiguousarray(depth)
|
||||
|
||||
if "mask" in sample:
|
||||
sample["mask"] = sample["mask"].astype(np.float32)
|
||||
sample["mask"] = np.ascontiguousarray(sample["mask"])
|
||||
|
||||
return sample
|
||||
Reference in New Issue
Block a user