我是靠谱客的博主 淡淡世界，最近开发中收集的这篇文章主要介绍将Resne34层网络用在MNIST数据集上将Resne34层网络用在MNIST数据集上主要分为3部分：一、主代码：main二、附属代码1：_internally_replaced_utils三、附属代码2：utilsCode：一、主代码：main二、附属代码：_internally_replaced_utils三、附属代码2：utils，觉得挺不错的，现在分享给大家，希望可以做个参考。
概述
将Resne34层网络用在MNIST数据集上
主要分为3部分：
一、主代码：main
二、附属代码1：_internally_replaced_utils
三、附属代码2：utils
将三个文件放在一个文件夹下面。如下图所示。
Code：
一、主代码：main
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",
}
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):
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 = 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 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)
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 resnet34(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
return _resnet("resnet34", BasicBlock, [3, 4, 6, 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
# 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 = 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
CELoss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=lr, momentum=momentum)
# training
batch_done = 0
logs = []
for i in range(epochs):
for data, label in train_loader:
output = model.forward(data)
loss = CELoss(output, label)
loss.backward()
optimizer.step()
optimizer.zero_grad()
batch_done += 1
if 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 = 0
for data, label in test_loader:
output = model.forward(data)
_, pred = torch.max(output, dim=1)
correct += float(torch.sum(pred == label))
print('test_acc:{}'.format(correct / len(test_dataset)))
二、附属代码：_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__}")最后
以上就是淡淡世界为你收集整理的将Resne34层网络用在MNIST数据集上将Resne34层网络用在MNIST数据集上主要分为3部分：一、主代码：main二、附属代码1：_internally_replaced_utils三、附属代码2：utilsCode：一、主代码：main二、附属代码：_internally_replaced_utils三、附属代码2：utils的全部内容，希望文章能够帮你解决将Resne34层网络用在MNIST数据集上将Resne34层网络用在MNIST数据集上主要分为3部分：一、主代码：main二、附属代码1：_internally_replaced_utils三、附属代码2：utilsCode：一、主代码：main二、附属代码：_internally_replaced_utils三、附属代码2：utils所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。
本图文内容来源于网友提供，作为学习参考使用，或来自网络收集整理，版权属于原作者所有。
![mmClassification学习笔记前言mmcv安装mmcv库文件夹架构mmcv概要mmcvclassification文件夹官方给的demo[只是一个模型推理]根据官方教程进行学习](/uploads/reation/bcimg7.png)
发表评论 取消回复