Spaces:
Sleeping
Sleeping
File size: 4,582 Bytes
251e479 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
"""Utils for monoDepth."""
import sys
import re
import numpy as np
import cv2
import torch
def read_pfm(path):
"""Read pfm file.
Args:
path (str): path to file
Returns:
tuple: (data, scale)
"""
with open(path, "rb") as file:
color = None
width = None
height = None
scale = None
endian = None
header = file.readline().rstrip()
if header.decode("ascii") == "PF":
color = True
elif header.decode("ascii") == "Pf":
color = False
else:
raise Exception("Not a PFM file: " + path)
dim_match = re.match(r"^(\d+)\s(\d+)\s$", file.readline().decode("ascii"))
if dim_match:
width, height = list(map(int, dim_match.groups()))
else:
raise Exception("Malformed PFM header.")
scale = float(file.readline().decode("ascii").rstrip())
if scale < 0:
# little-endian
endian = "<"
scale = -scale
else:
# big-endian
endian = ">"
data = np.fromfile(file, endian + "f")
shape = (height, width, 3) if color else (height, width)
data = np.reshape(data, shape)
data = np.flipud(data)
return data, scale
def write_pfm(path, image, scale=1):
"""Write pfm file.
Args:
path (str): pathto file
image (array): data
scale (int, optional): Scale. Defaults to 1.
"""
with open(path, "wb") as file:
color = None
if image.dtype.name != "float32":
raise Exception("Image dtype must be float32.")
image = np.flipud(image)
if len(image.shape) == 3 and image.shape[2] == 3: # color image
color = True
elif (
len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1
): # greyscale
color = False
else:
raise Exception("Image must have H x W x 3, H x W x 1 or H x W dimensions.")
file.write("PF\n" if color else "Pf\n".encode())
file.write("%d %d\n".encode() % (image.shape[1], image.shape[0]))
endian = image.dtype.byteorder
if endian == "<" or endian == "=" and sys.byteorder == "little":
scale = -scale
file.write("%f\n".encode() % scale)
image.tofile(file)
def read_image(path):
"""Read image and output RGB image (0-1).
Args:
path (str): path to file
Returns:
array: RGB image (0-1)
"""
img = cv2.imread(path)
if img.ndim == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) / 255.0
return img
def resize_image(img):
"""Resize image and make it fit for network.
Args:
img (array): image
Returns:
tensor: data ready for network
"""
height_orig = img.shape[0]
width_orig = img.shape[1]
if width_orig > height_orig:
scale = width_orig / 384
else:
scale = height_orig / 384
height = (np.ceil(height_orig / scale / 32) * 32).astype(int)
width = (np.ceil(width_orig / scale / 32) * 32).astype(int)
img_resized = cv2.resize(img, (width, height), interpolation=cv2.INTER_AREA)
img_resized = (
torch.from_numpy(np.transpose(img_resized, (2, 0, 1))).contiguous().float()
)
img_resized = img_resized.unsqueeze(0)
return img_resized
def resize_depth(depth, width, height):
"""Resize depth map and bring to CPU (numpy).
Args:
depth (tensor): depth
width (int): image width
height (int): image height
Returns:
array: processed depth
"""
depth = torch.squeeze(depth[0, :, :, :]).to("cpu")
depth_resized = cv2.resize(
depth.numpy(), (width, height), interpolation=cv2.INTER_CUBIC
)
return depth_resized
def write_depth(path, depth, bits=1):
"""Write depth map to pfm and png file.
Args:
path (str): filepath without extension
depth (array): depth
"""
write_pfm(path + ".pfm", depth.astype(np.float32))
depth_min = depth.min()
depth_max = depth.max()
max_val = (2**(8*bits))-1
if depth_max - depth_min > np.finfo("float").eps:
out = max_val * (depth - depth_min) / (depth_max - depth_min)
else:
out = np.zeros(depth.shape, dtype=depth.type)
if bits == 1:
cv2.imwrite(path + ".png", out.astype("uint8"))
elif bits == 2:
cv2.imwrite(path + ".png", out.astype("uint16"))
return
|