RESNET官方代码（pytorch）
RESNET官方代码（pytorch）
vision/resnet.py at main · pytorch/vision · GitHub
主要由三部分组成：
一、主程序
二、附属代码1
三、附属代码2
一、主程序
from typing import Type, Any, Callable, Union, List, Optional
import torch
import torch.nn as nn
from torch import Tensor
from .._internally_replaced_utils import load_state_dict_from_url
from ..utils import _log_api_usage_once
__all__ = [
"ResNet",
"resnet18",
"resnet34",
"resnet50",
"resnet101",
"resnet152",
"resnext50_32x4d",
"resnext101_32x8d",
"wide_resnet50_2",
"wide_resnet101_2",
]
model_urls = {
"resnet18": "https://download.pytorch.org/models/resnet18-f37072fd.pth",
"resnet34": "https://download.pytorch.org/models/resnet34-b627a593.pth",
"resnet50": "https://download.pytorch.org/models/resnet50-0676ba61.pth",
"resnet101": "https://download.pytorch.org/models/resnet101-63fe2227.pth",
"resnet152": "https://download.pytorch.org/models/resnet152-394f9c45.pth",
"resnext50_32x4d": "https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth",
"resnext101_32x8d": "https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth",
"wide_resnet50_2": "https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth",
"wide_resnet101_2": "https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth",
}
def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d:
"""3x3 convolution with padding"""
return nn.Conv2d(
in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=dilation,
groups=groups,
bias=False,
dilation=dilation,
)
def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(nn.Module):
expansion: int = 1
def __init__(
self,
inplanes: int,
planes: int,
stride: int = 1,
downsample: Optional[nn.Module] = None,
groups: int = 1,
base_width: int = 64,
dilation: int = 1,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super().__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError("BasicBlock only supports groups=1 and base_width=64")
if dilation > 1:
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x: Tensor) -> Tensor:
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(nn.Module):
# Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
# while original implementation places the stride at the first 1x1 convolution(self.conv1)
# according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
# This variant is also known as ResNet V1.5 and improves accuracy according to
# https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.
expansion: int = 4
def __init__(
self,
inplanes: int,
planes: int,
stride: int = 1,
downsample: Optional[nn.Module] = None,
groups: int = 1,
base_width: int = 64,
dilation: int = 1,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super().__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.0)) * groups
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x: Tensor) -> Tensor:
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(
self,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
num_classes: int = 1000,
zero_init_residual: bool = False,
groups: int = 1,
width_per_group: int = 64,
replace_stride_with_dilation: Optional[List[bool]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super().__init__()
_log_api_usage_once(self)
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 "
f"or a 3-element tuple, got {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)
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) # type: ignore[arg-type]
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0) # type: ignore[arg-type]
def _make_layer(
self,
block: Type[Union[BasicBlock, Bottleneck]],
planes: int,
blocks: int,
stride: int = 1,
dilate: bool = False,
) -> nn.Sequential:
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_impl(self, x: Tensor) -> Tensor:
# See note [TorchScript super()]
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 = torch.flatten(x, 1)
x = self.fc(x)
return x
def forward(self, x: Tensor) -> Tensor:
return self._forward_impl(x)
def _resnet(
arch: str,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
pretrained: bool,
progress: bool,
**kwargs: Any,
) -> ResNet:
model = ResNet(block, layers, **kwargs)
if pretrained:
state_dict = load_state_dict_from_url(model_urls[arch], progress=progress)
model.load_state_dict(state_dict)
return model
def resnet18(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNet-18 model from
`"Deep Residual Learning for Image Recognition" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet("resnet18", BasicBlock, [2, 2, 2, 2], pretrained, progress, **kwargs)
def resnet34(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNet-34 model from
`"Deep Residual Learning for Image Recognition" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet("resnet34", BasicBlock, [3, 4, 6, 3], pretrained, progress, **kwargs)
def resnet50(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNet-50 model from
`"Deep Residual Learning for Image Recognition" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet("resnet50", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs)
def resnet101(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNet-101 model from
`"Deep Residual Learning for Image Recognition" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet("resnet101", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs)
def resnet152(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNet-152 model from
`"Deep Residual Learning for Image Recognition" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet("resnet152", Bottleneck, [3, 8, 36, 3], pretrained, progress, **kwargs)
def resnext50_32x4d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNeXt-50 32x4d model from
`"Aggregated Residual Transformation for Deep Neural Networks" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs["groups"] = 32
kwargs["width_per_group"] = 4
return _resnet("resnext50_32x4d", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs)
def resnext101_32x8d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""ResNeXt-101 32x8d model from
`"Aggregated Residual Transformation for Deep Neural Networks" `_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs["groups"] = 32
kwargs["width_per_group"] = 8
return _resnet("resnext101_32x8d", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs)
def wide_resnet50_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""Wide ResNet-50-2 model from
`"Wide Residual Networks" `_.
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs["width_per_group"] = 64 * 2
return _resnet("wide_resnet50_2", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs)
def wide_resnet101_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
r"""Wide ResNet-101-2 model from
`"Wide Residual Networks" `_.
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs["width_per_group"] = 64 * 2
return _resnet("wide_resnet101_2", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs) 二、附属代码1： _internally_replaced_utils
import importlib.machinery
import os
from torch.hub import _get_torch_home
_HOME = os.path.join(_get_torch_home(), "datasets", "vision")
_USE_SHARDED_DATASETS = False
def _download_file_from_remote_location(fpath: str, url: str) -> None:
pass
def _is_remote_location_available() -> bool:
return False
try:
from torch.hub import load_state_dict_from_url # noqa: 401
except ImportError:
from torch.utils.model_zoo import load_url as load_state_dict_from_url # noqa: 401
def _get_extension_path(lib_name):
lib_dir = os.path.dirname(__file__)
if os.name == "nt":
# Register the main torchvision library location on the default DLL path
import ctypes
import sys
kernel32 = ctypes.WinDLL("kernel32.dll", use_last_error=True)
with_load_library_flags = hasattr(kernel32, "AddDllDirectory")
prev_error_mode = kernel32.SetErrorMode(0x0001)
if with_load_library_flags:
kernel32.AddDllDirectory.restype = ctypes.c_void_p
if sys.version_info >= (3, 8):
os.add_dll_directory(lib_dir)
elif with_load_library_flags:
res = kernel32.AddDllDirectory(lib_dir)
if res is None:
err = ctypes.WinError(ctypes.get_last_error())
err.strerror += f' Error adding "{lib_dir}" to the DLL directories.'
raise err
kernel32.SetErrorMode(prev_error_mode)
loader_details = (importlib.machinery.ExtensionFileLoader, importlib.machinery.EXTENSION_SUFFIXES)
extfinder = importlib.machinery.FileFinder(lib_dir, loader_details)
ext_specs = extfinder.find_spec(lib_name)
if ext_specs is None:
raise ImportError
return ext_specs.origin三、附属代码2： utils
import math
import pathlib
import warnings
from typing import Union, Optional, List, Tuple, BinaryIO, no_type_check
import numpy as np
import torch
from PIL import Image, ImageDraw, ImageFont, ImageColor
__all__ = ["make_grid", "save_image", "draw_bounding_boxes", "draw_segmentation_masks", "draw_keypoints"]
@torch.no_grad()
def make_grid(
tensor: Union[torch.Tensor, List[torch.Tensor]],
nrow: int = 8,
padding: int = 2,
normalize: bool = False,
value_range: Optional[Tuple[int, int]] = None,
scale_each: bool = False,
pad_value: int = 0,
**kwargs,
) -> torch.Tensor:
"""
Make a grid of images.
Args:
tensor (Tensor or list): 4D mini-batch Tensor of shape (B x C x H x W)
or a list of images all of the same size.
nrow (int, optional): Number of images displayed in each row of the grid.
The final grid size is ``(B / nrow, nrow)``. Default: ``8``.
padding (int, optional): amount of padding. Default: ``2``.
normalize (bool, optional): If True, shift the image to the range (0, 1),
by the min and max values specified by ``value_range``. Default: ``False``.
value_range (tuple, optional): tuple (min, max) where min and max are numbers,
then these numbers are used to normalize the image. By default, min and max
are computed from the tensor.
scale_each (bool, optional): If ``True``, scale each image in the batch of
images separately rather than the (min, max) over all images. Default: ``False``.
pad_value (float, optional): Value for the padded pixels. Default: ``0``.
Returns:
grid (Tensor): the tensor containing grid of images.
"""
if not (torch.is_tensor(tensor) or (isinstance(tensor, list) and all(torch.is_tensor(t) for t in tensor))):
raise TypeError(f"tensor or list of tensors expected, got {type(tensor)}")
if "range" in kwargs.keys():
warning = "range will be deprecated, please use value_range instead."
warnings.warn(warning)
value_range = kwargs["range"]
# if list of tensors, convert to a 4D mini-batch Tensor
if isinstance(tensor, list):
tensor = torch.stack(tensor, dim=0)
if tensor.dim() == 2: # single image H x W
tensor = tensor.unsqueeze(0)
if tensor.dim() == 3: # single image
if tensor.size(0) == 1: # if single-channel, convert to 3-channel
tensor = torch.cat((tensor, tensor, tensor), 0)
tensor = tensor.unsqueeze(0)
if tensor.dim() == 4 and tensor.size(1) == 1: # single-channel images
tensor = torch.cat((tensor, tensor, tensor), 1)
if normalize is True:
tensor = tensor.clone() # avoid modifying tensor in-place
if value_range is not None:
assert isinstance(
value_range, tuple
), "value_range has to be a tuple (min, max) if specified. min and max are numbers"
def norm_ip(img, low, high):
img.clamp_(min=low, max=high)
img.sub_(low).div_(max(high - low, 1e-5))
def norm_range(t, value_range):
if value_range is not None:
norm_ip(t, value_range[0], value_range[1])
else:
norm_ip(t, float(t.min()), float(t.max()))
if scale_each is True:
for t in tensor: # loop over mini-batch dimension
norm_range(t, value_range)
else:
norm_range(tensor, value_range)
if tensor.size(0) == 1:
return tensor.squeeze(0)
# make the mini-batch of images into a grid
nmaps = tensor.size(0)
xmaps = min(nrow, nmaps)
ymaps = int(math.ceil(float(nmaps) / xmaps))
height, width = int(tensor.size(2) + padding), int(tensor.size(3) + padding)
num_channels = tensor.size(1)
grid = tensor.new_full((num_channels, height * ymaps + padding, width * xmaps + padding), pad_value)
k = 0
for y in range(ymaps):
for x in range(xmaps):
if k >= nmaps:
break
# Tensor.copy_() is a valid method but seems to be missing from the stubs
# https://pytorch.org/docs/stable/tensors.html#torch.Tensor.copy_
grid.narrow(1, y * height + padding, height - padding).narrow( # type: ignore[attr-defined]
2, x * width + padding, width - padding
).copy_(tensor[k])
k = k + 1
return grid
@torch.no_grad()
def save_image(
tensor: Union[torch.Tensor, List[torch.Tensor]],
fp: Union[str, pathlib.Path, BinaryIO],
format: Optional[str] = None,
**kwargs,
) -> None:
"""
Save a given Tensor into an image file.
Args:
tensor (Tensor or list): Image to be saved. If given a mini-batch tensor,
saves the tensor as a grid of images by calling ``make_grid``.
fp (string or file object): A filename or a file object
format(Optional): If omitted, the format to use is determined from the filename extension.
If a file object was used instead of a filename, this parameter should always be used.
**kwargs: Other arguments are documented in ``make_grid``.
"""
grid = make_grid(tensor, **kwargs)
# Add 0.5 after unnormalizing to [0, 255] to round to nearest integer
ndarr = grid.mul(255).add_(0.5).clamp_(0, 255).permute(1, 2, 0).to("cpu", torch.uint8).numpy()
im = Image.fromarray(ndarr)
im.save(fp, format=format)
@torch.no_grad()
def draw_bounding_boxes(
image: torch.Tensor,
boxes: torch.Tensor,
labels: Optional[List[str]] = None,
colors: Optional[Union[List[Union[str, Tuple[int, int, int]]], str, Tuple[int, int, int]]] = None,
fill: Optional[bool] = False,
width: int = 1,
font: Optional[str] = None,
font_size: int = 10,
) -> torch.Tensor:
"""
Draws bounding boxes on given image.
The values of the input image should be uint8 between 0 and 255.
If fill is True, Resulting Tensor should be saved as PNG image.
Args:
image (Tensor): Tensor of shape (C x H x W) and dtype uint8.
boxes (Tensor): Tensor of size (N, 4) containing bounding boxes in (xmin, ymin, xmax, ymax) format. Note that
the boxes are absolute coordinates with respect to the image. In other words: `0 <= xmin < xmax < W` and
`0 <= ymin < ymax < H`.
labels (List[str]): List containing the labels of bounding boxes.
colors (color or list of colors, optional): List containing the colors
of the boxes or single color for all boxes. The color can be represented as
PIL strings e.g. "red" or "#FF00FF", or as RGB tuples e.g. ``(240, 10, 157)``.
fill (bool): If `True` fills the bounding box with specified color.
width (int): Width of bounding box.
font (str): A filename containing a TrueType font. If the file is not found in this filename, the loader may
also search in other directories, such as the `fonts/` directory on Windows or `/Library/Fonts/`,
`/System/Library/Fonts/` and `~/Library/Fonts/` on macOS.
font_size (int): The requested font size in points.
Returns:
img (Tensor[C, H, W]): Image Tensor of dtype uint8 with bounding boxes plotted.
"""
if not isinstance(image, torch.Tensor):
raise TypeError(f"Tensor expected, got {type(image)}")
elif image.dtype != torch.uint8:
raise ValueError(f"Tensor uint8 expected, got {image.dtype}")
elif image.dim() != 3:
raise ValueError("Pass individual images, not batches")
elif image.size(0) not in {1, 3}:
raise ValueError("Only grayscale and RGB images are supported")
if image.size(0) == 1:
image = torch.tile(image, (3, 1, 1))
ndarr = image.permute(1, 2, 0).numpy()
img_to_draw = Image.fromarray(ndarr)
img_boxes = boxes.to(torch.int64).tolist()
if fill:
draw = ImageDraw.Draw(img_to_draw, "RGBA")
else:
draw = ImageDraw.Draw(img_to_draw)
txt_font = ImageFont.load_default() if font is None else ImageFont.truetype(font=font, size=font_size)
for i, bbox in enumerate(img_boxes):
if colors is None:
color = None
elif isinstance(colors, list):
color = colors[i]
else:
color = colors
if fill:
if color is None:
fill_color = (255, 255, 255, 100)
elif isinstance(color, str):
# This will automatically raise Error if rgb cannot be parsed.
fill_color = ImageColor.getrgb(color) + (100,)
elif isinstance(color, tuple):
fill_color = color + (100,)
draw.rectangle(bbox, width=width, outline=color, fill=fill_color)
else:
draw.rectangle(bbox, width=width, outline=color)
if labels is not None:
margin = width + 1
draw.text((bbox[0] + margin, bbox[1] + margin), labels[i], fill=color, font=txt_font)
return torch.from_numpy(np.array(img_to_draw)).permute(2, 0, 1).to(dtype=torch.uint8)
@torch.no_grad()
def draw_segmentation_masks(
image: torch.Tensor,
masks: torch.Tensor,
alpha: float = 0.8,
colors: Optional[Union[List[Union[str, Tuple[int, int, int]]], str, Tuple[int, int, int]]] = None,
) -> torch.Tensor:
"""
Draws segmentation masks on given RGB image.
The values of the input image should be uint8 between 0 and 255.
Args:
image (Tensor): Tensor of shape (3, H, W) and dtype uint8.
masks (Tensor): Tensor of shape (num_masks, H, W) or (H, W) and dtype bool.
alpha (float): Float number between 0 and 1 denoting the transparency of the masks.
0 means full transparency, 1 means no transparency.
colors (color or list of colors, optional): List containing the colors
of the masks or single color for all masks. The color can be represented as
PIL strings e.g. "red" or "#FF00FF", or as RGB tuples e.g. ``(240, 10, 157)``.
By default, random colors are generated for each mask.
Returns:
img (Tensor[C, H, W]): Image Tensor, with segmentation masks drawn on top.
"""
if not isinstance(image, torch.Tensor):
raise TypeError(f"The image must be a tensor, got {type(image)}")
elif image.dtype != torch.uint8:
raise ValueError(f"The image dtype must be uint8, got {image.dtype}")
elif image.dim() != 3:
raise ValueError("Pass individual images, not batches")
elif image.size()[0] != 3:
raise ValueError("Pass an RGB image. Other Image formats are not supported")
if masks.ndim == 2:
masks = masks[None, :, :]
if masks.ndim != 3:
raise ValueError("masks must be of shape (H, W) or (batch_size, H, W)")
if masks.dtype != torch.bool:
raise ValueError(f"The masks must be of dtype bool. Got {masks.dtype}")
if masks.shape[-2:] != image.shape[-2:]:
raise ValueError("The image and the masks must have the same height and width")
num_masks = masks.size()[0]
if colors is not None and num_masks > len(colors):
raise ValueError(f"There are more masks ({num_masks}) than colors ({len(colors)})")
if colors is None:
colors = _generate_color_palette(num_masks)
if not isinstance(colors, list):
colors = [colors]
if not isinstance(colors[0], (tuple, str)):
raise ValueError("colors must be a tuple or a string, or a list thereof")
if isinstance(colors[0], tuple) and len(colors[0]) != 3:
raise ValueError("It seems that you passed a tuple of colors instead of a list of colors")
out_dtype = torch.uint8
colors_ = []
for color in colors:
if isinstance(color, str):
color = ImageColor.getrgb(color)
colors_.append(torch.tensor(color, dtype=out_dtype))
img_to_draw = image.detach().clone()
# TODO: There might be a way to vectorize this
for mask, color in zip(masks, colors_):
img_to_draw[:, mask] = color[:, None]
out = image * (1 - alpha) + img_to_draw * alpha
return out.to(out_dtype)
@torch.no_grad()
def draw_keypoints(
image: torch.Tensor,
keypoints: torch.Tensor,
connectivity: Optional[List[Tuple[int, int]]] = None,
colors: Optional[Union[str, Tuple[int, int, int]]] = None,
radius: int = 2,
width: int = 3,
) -> torch.Tensor:
"""
Draws Keypoints on given RGB image.
The values of the input image should be uint8 between 0 and 255.
Args:
image (Tensor): Tensor of shape (3, H, W) and dtype uint8.
keypoints (Tensor): Tensor of shape (num_instances, K, 2) the K keypoints location for each of the N instances,
in the format [x, y].
connectivity (List[Tuple[int, int]]]): A List of tuple where,
each tuple contains pair of keypoints to be connected.
colors (str, Tuple): The color can be represented as
PIL strings e.g. "red" or "#FF00FF", or as RGB tuples e.g. ``(240, 10, 157)``.
radius (int): Integer denoting radius of keypoint.
width (int): Integer denoting width of line connecting keypoints.
Returns:
img (Tensor[C, H, W]): Image Tensor of dtype uint8 with keypoints drawn.
"""
if not isinstance(image, torch.Tensor):
raise TypeError(f"The image must be a tensor, got {type(image)}")
elif image.dtype != torch.uint8:
raise ValueError(f"The image dtype must be uint8, got {image.dtype}")
elif image.dim() != 3:
raise ValueError("Pass individual images, not batches")
elif image.size()[0] != 3:
raise ValueError("Pass an RGB image. Other Image formats are not supported")
if keypoints.ndim != 3:
raise ValueError("keypoints must be of shape (num_instances, K, 2)")
ndarr = image.permute(1, 2, 0).numpy()
img_to_draw = Image.fromarray(ndarr)
draw = ImageDraw.Draw(img_to_draw)
img_kpts = keypoints.to(torch.int64).tolist()
for kpt_id, kpt_inst in enumerate(img_kpts):
for inst_id, kpt in enumerate(kpt_inst):
x1 = kpt[0] - radius
x2 = kpt[0] + radius
y1 = kpt[1] - radius
y2 = kpt[1] + radius
draw.ellipse([x1, y1, x2, y2], fill=colors, outline=None, width=0)
if connectivity:
for connection in connectivity:
start_pt_x = kpt_inst[connection[0]][0]
start_pt_y = kpt_inst[connection[0]][1]
end_pt_x = kpt_inst[connection[1]][0]
end_pt_y = kpt_inst[connection[1]][1]
draw.line(
((start_pt_x, start_pt_y), (end_pt_x, end_pt_y)),
width=width,
)
return torch.from_numpy(np.array(img_to_draw)).permute(2, 0, 1).to(dtype=torch.uint8)
def _generate_color_palette(num_masks: int):
palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
return [tuple((i * palette) % 255) for i in range(num_masks)]
@no_type_check
def _log_api_usage_once(obj: str) -> None: # type: ignore
if torch.jit.is_scripting() or torch.jit.is_tracing():
return
# NOTE: obj can be an object as well, but mocking it here to be
# only a string to appease torchscript
if isinstance(obj, str):
torch._C._log_api_usage_once(obj)
else:
torch._C._log_api_usage_once(f"{obj.__module__}.{obj.__class__.__name__}")