# pytorh官方实现resnet# 添加了前向传播,残差结构没有发生变化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
from typing import Type, Any, Callable, Union, List, Optional
import torch.nn as nn
from torch import Tensor
from torch.utils import model_zoo
from _internally_replaced_utils import load_state_dict_from_url
from utils import _log_api_usage_once
import os
os.environ['KMP_DUPLICATE_LIB_OK']='TRUE'
__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",}defconv3x3(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,)defconv1x1(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)classBasicBlock(nn.Module):
expansion:int=1global weight_zidingyi
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 isNone:
norm_layer = nn.BatchNorm2d
if groups !=1or 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
defforward(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 isnotNone:
identity = self.downsample(x)
out +=(weight_zidingyi * identity)print(weight_zidingyi)
out = self.relu(out)return out
classBottleneck(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=4def__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 isNone:
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
defforward(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 isnotNone:
identity = self.downsample(x)
out += identity
out = self.relu(out)return out
classResNet(nn.Module):def__init__(
self,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
num_classes:int=10,
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 isNone:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes =64
self.dilation =1if replace_stride_with_dilation isNone:# 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]iflen(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():ifisinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")elifisinstance(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/1706.02677if zero_init_residual:for m in self.modules():ifisinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight,0)# type: ignore[arg-type]elifisinstance(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 =1if stride !=1or 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 _ inrange(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
defforward(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
defresnet18(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNet-18 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
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)defresnet34(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNet-34 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
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)defresnet50(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNet-50 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
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)defresnet101(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNet-101 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
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)defresnet152(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNet-152 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
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)defresnext50_32x4d(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNeXt-50 32x4d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_.
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"]=4return _resnet("resnext50_32x4d", Bottleneck,[3,4,6,3], pretrained, progress,**kwargs)defresnext101_32x8d(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""ResNeXt-101 32x8d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_.
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"]=8return _resnet("resnext101_32x8d", Bottleneck,[3,4,23,3], pretrained, progress,**kwargs)defwide_resnet50_2(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""Wide ResNet-50-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_.
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*2return _resnet("wide_resnet50_2", Bottleneck,[3,4,6,3], pretrained, progress,**kwargs)defwide_resnet101_2(pretrained:bool=False, progress:bool=True,**kwargs: Any)-> ResNet:r"""Wide ResNet-101-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_.
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*2return _resnet("wide_resnet101_2", Bottleneck,[3,4,23,3], pretrained, progress,**kwargs)import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
epochs =3
batch_size =64
lr =0.01
momentum =0.5
log_interval =10
weight_zidingyi =0.01
DEVICE = torch.device('cuda'if torch.cuda.is_available()else'cpu')# 是否用GPU还是CPU训练# dataset init
train_dataset = torchvision.datasets.MNIST('./data/', train=True, download=True,
transform=transforms.Compose([
transforms.Resize(224),# resnet默认图片输入大小224*224
transforms.ToTensor(),
transforms.Lambda(lambda x: x.repeat(3,1,1)),
transforms.Normalize(mean=(0.5,0.5,0.5), std=(0.5,0.5,0.5)),
transforms.Grayscale(num_output_channels=3)]))
test_dataset = torchvision.datasets.MNIST('./data/', train=False, download=True,
transform=transforms.Compose([
transforms.Resize(224),# resnet默认图片输入大小224*224
transforms.ToTensor(),
transforms.Lambda(lambda x: x.repeat(3,1,1)),
transforms.Normalize(mean=(0.5,0.5,0.5), std=(0.5,0.5,0.5)),
transforms.Grayscale(num_output_channels=3)]))
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)# data visualization
sample, label =next(iter(train_loader))print(sample.shape)print(label)
fig, ax = plt.subplots(nrows=8, ncols=8, sharex=True, sharey=True)# ax = ax.flatten()# model init
model = resnet34(pretrained =False)#pretrained = True 赋值为true意思就是使用预训练的参数,我们加载的是预训练模型,所以这里不需要训练,自己训练需要写训练函数
model = model.to(DEVICE)
CELoss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=lr, momentum=momentum)# training
batch_done =0
logs =[]for i inrange(epochs):for data, label in train_loader:
data = data.to(DEVICE)
label = label.to(DEVICE)
output = model.forward(data)
loss = CELoss(output, label)
loss.backward()
optimizer.step()
optimizer.zero_grad()
batch_done +=1if batch_done % log_interval ==0:
logs.append([batch_done, loss.item()])print('Epoch {}: {}/{} loss:{}'.format(i,(batch_done)%len(train_loader),len(train_loader), loss.item()))# loss curve visualization
logs = np.array(logs)# plt.plot(logs[:, 0], logs[:, 1])# plt.show()# evaluation
model.eval()
correct =0for data, label in test_loader:
data = data.to(DEVICE)
label = label.to(DEVICE)
output = model.forward(data)
_, pred = torch.max(output, dim=1)
correct +=float(torch.sum(pred == label))print('test_acc:{}'.format(correct /len(test_dataset)))
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 =Falsedef_download_file_from_remote_location(fpath:str, url:str)->None:passdef_is_remote_location_available()->bool:returnFalsetry:from torch.hub import load_state_dict_from_url # noqa: 401except ImportError:from torch.utils.model_zoo import load_url as load_state_dict_from_url # noqa: 401def_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 pathimport 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 isNone:
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 isNone:raise ImportError
return ext_specs.origin
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()defmake_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.
"""ifnot(torch.is_tensor(tensor)or(isinstance(tensor,list)andall(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 Tensorifisinstance(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 imageif 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()==4and tensor.size(1)==1:# single-channel images
tensor = torch.cat((tensor, tensor, tensor),1)if normalize isTrue:
tensor = tensor.clone()# avoid modifying tensor in-placeif value_range isnotNone:assertisinstance(
value_range,tuple),"value_range has to be a tuple (min, max) if specified. min and max are numbers"defnorm_ip(img, low, high):
img.clamp_(min=low,max=high)
img.sub_(low).div_(max(high - low,1e-5))defnorm_range(t, value_range):if value_range isnotNone:
norm_ip(t, value_range[0], value_range[1])else:
norm_ip(t,float(t.min()),float(t.max()))if scale_each isTrue: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 =0for y inrange(ymaps):for x inrange(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 +1return grid
@torch.no_grad()defsave_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()defdraw_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.
"""ifnotisinstance(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)notin{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 isNoneelse ImageFont.truetype(font=font, size=font_size)for i, bbox inenumerate(img_boxes):if colors isNone:
color =Noneelifisinstance(colors,list):
color = colors[i]else:
color = colors
if fill:if color isNone:
fill_color =(255,255,255,100)elifisinstance(color,str):# This will automatically raise Error if rgb cannot be parsed.
fill_color = ImageColor.getrgb(color)+(100,)elifisinstance(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 isnotNone:
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()defdraw_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.
"""ifnotisinstance(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 isnotNoneand num_masks >len(colors):raise ValueError(f"There are more masks ({num_masks}) than colors ({len(colors)})")if colors isNone:
colors = _generate_color_palette(num_masks)ifnotisinstance(colors,list):
colors =[colors]ifnotisinstance(colors[0],(tuple,str)):raise ValueError("colors must be a tuple or a string, or a list thereof")ifisinstance(colors[0],tuple)andlen(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:ifisinstance(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 thisfor mask, color inzip(masks, colors_):
img_to_draw[:, mask]= color[:,None]
out = image *(1- alpha)+ img_to_draw * alpha
return out.to(out_dtype)@torch.no_grad()defdraw_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.
"""ifnotisinstance(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 inenumerate(img_kpts):for inst_id, kpt inenumerate(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 inrange(num_masks)]@no_type_checkdef_log_api_usage_once(obj:str)->None:# type: ignoreif 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 torchscriptifisinstance(obj,str):
torch._C._log_api_usage_once(obj)else:
torch._C._log_api_usage_once(f"{obj.__module__}.{obj.__class__.__name__}")