​

​

​

​

​

import torch.nn as nn
import torch
import torch.nn.functional as F
import numpy as np
import math

__all__ = ['C3k2_RCSOSA', 'RCSOSA', 'C2PSA_RCSOSA']

# build RepVGG block
# -----------------------------
def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
    result = nn.Sequential()
    result.add_module('conv', nn.Conv2d(in_channels=in_channels, out_channels=out_channels,
                                        kernel_size=kernel_size, stride=stride, padding=padding, groups=groups,
                                        bias=False))
    result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))

    return result

class SEBlock(nn.Module):
    def __init__(self, input_channels):
        super(SEBlock, self).__init__()
        internal_neurons = input_channels // 8
        self.down = nn.Conv2d(in_channels=input_channels, out_channels=internal_neurons, kernel_size=1, stride=1,
                              bias=True)
        self.up = nn.Conv2d(in_channels=internal_neurons, out_channels=input_channels, kernel_size=1, stride=1,
                            bias=True)
        self.input_channels = input_channels

    def forward(self, inputs):
        x = F.avg_pool2d(inputs, kernel_size=inputs.size(3))
        x = self.down(x)
        x = F.relu(x)
        x = self.up(x)
        x = torch.sigmoid(x)
        x = x.view(-1, self.input_channels, 1, 1)
        return inputs * x

class RepVGG(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size=3,
                 stride=1, padding=1, dilation=1, groups=1, padding_mode='zeros', deploy=False, use_se=False):
        super(RepVGG, self).__init__()
        self.deploy = deploy
        self.groups = groups
        self.in_channels = in_channels

        padding_11 = padding - kernel_size // 2

        self.nonlinearity = nn.SiLU()
        # self.nonlinearity = nn.ReLU()

        if use_se:
            self.se = SEBlock(out_channels)
        else:
            self.se = nn.Identity()

        if deploy:
            self.rbr_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
                                         stride=stride,
                                         padding=padding, dilation=dilation, groups=groups, bias=True,
                                         padding_mode=padding_mode)

        else:
            self.rbr_identity = nn.BatchNorm2d(
                num_features=in_channels) if out_channels == in_channels and stride == 1 else None
            self.rbr_dense = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
                                     stride=stride, padding=padding, groups=groups)
            self.rbr_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride,
                                   padding=padding_11, groups=groups)
            # print('RepVGG Block, identity = ', self.rbr_identity)

    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
        kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        if branch is None:
            return 0, 0
        if isinstance(branch, nn.Sequential):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        else:
            assert isinstance(branch, nn.BatchNorm2d)
            if not hasattr(self, 'id_tensor'):
                input_dim = self.in_channels // self.groups
                kernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.in_channels):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def forward(self, inputs):
        if hasattr(self, 'rbr_reparam'):
            return self.nonlinearity(self.se(self.rbr_reparam(inputs)))

        if self.rbr_identity is None:
            id_out = 0
        else:
            id_out = self.rbr_identity(inputs)

        return self.nonlinearity(self.se(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out))

    def fusevggforward(self, x):
        return self.nonlinearity(self.rbr_dense(x))

# RepVGG block end
# -----------------------------

class SR(nn.Module):
    # Shuffle RepVGG
    def __init__(self, c1, c2):
        super().__init__()
        c1_ = int(c1 // 2)
        c2_ = int(c2 // 2)
        self.repconv = RepVGG(c1_, c2_)

    def forward(self, x):
        x1, x2 = x.chunk(2, dim=1)
        out = torch.cat((x1, self.repconv(x2)), dim=1)
        out = self.channel_shuffle(out, 2)
        return out

    def channel_shuffle(self, x, groups):
        batchsize, num_channels, height, width = x.data.size()
        channels_per_group = num_channels // groups
        x = x.view(batchsize, groups, channels_per_group, height, width)
        x = torch.transpose(x, 1, 2).contiguous()
        x = x.view(batchsize, -1, height, width)
        return x


def make_divisible(x, divisor):
    # Returns nearest x divisible by divisor
    if isinstance(divisor, torch.Tensor):
        divisor = int(divisor.max())  # to int
    return math.ceil(x / divisor) * divisor

class RCSOSA(nn.Module):
    # VoVNet with Res Shuffle RepVGG
    def __init__(self, c1, c2, n=1, se=False, e=0.5, head=8):
        super().__init__()
        n_ = n // 2
        c_ = make_divisible(int(c1 * e), head)
        # self.conv1 = Conv(c1, c_)
        self.conv1 = RepVGG(c1, c_)
        self.conv3 = RepVGG(int(c_ * 3), c2)
        self.sr1 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])
        self.sr2 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])

        self.se = None
        if se:
            self.se = SEBlock(c2)

    def forward(self, x):
        x1 = self.conv1(x)
        x2 = self.sr1(x1)
        x3 = self.sr2(x2)
        x = torch.cat((x1, x2, x3), 1)
        return self.conv3(x) if self.se is None else self.se(self.conv3(x))

class Bottleneck(nn.Module):
    """Standard bottleneck."""

    def __init__(
        self, c1: int, c2: int, shortcut: bool = True, g: int = 1, k: tuple[int, int] = (3, 3), e: float = 0.5
    ):
        """Initialize a standard bottleneck module.

        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            shortcut (bool): Whether to use shortcut connection.
            g (int): Groups for convolutions.
            k (tuple): Kernel sizes for convolutions.
            e (float): Expansion ratio.
        """
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Apply bottleneck with optional shortcut connection."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p


class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))






class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))

    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))


class PSABlock_RCSOSA(nn.Module):
    """PSABlock class implementing a Position-Sensitive Attention block for neural networks.

    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.

    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.

    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.

    """

    def __init__(self, c: int, attn_ratio: float = 0.5, num_heads: int = 4, shortcut: bool = True) -> None:
        """Initialize the PSABlock.

        Args:
            c (int): Input and output channels.
            attn_ratio (float): Attention ratio for key dimension.
            num_heads (int): Number of attention heads.
            shortcut (bool): Whether to use shortcut connections.
        """
        super().__init__()

        self.attn = RCSOSA(c, c, se=False, e=attn_ratio, head=num_heads)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Execute a forward pass through PSABlock.

        Args:
            x (torch.Tensor): Input tensor.

        Returns:
            (torch.Tensor): Output tensor after attention and feed-forward processing.
        """
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x

class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""

    def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5, k: int = 3):
        """Initialize C3k module.

        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            n (int): Number of Bottleneck blocks.
            shortcut (bool): Whether to use shortcut connections.
            g (int): Groups for convolutions.
            e (float): Expansion ratio.
            k (int): Kernel size.
        """
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

class C3k2_RCSOSA(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(
        self,
        c1: int,
        c2: int,
        n: int = 1,
        c3k: bool = False,
        e: float = 0.5,
        attn: bool = False,
        g: int = 1,
        shortcut: bool = True,
    ):
        """Initialize C3k2 modu
        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            n (int): Number of blocks.
            c3k (bool): Whether to use C3k blocks.
            e (float): Expansion ratio.
            attn (bool): Whether to use attention blocks.
            g (int): Groups for convolutions.
            shortcut (bool): Whether to use shortcut connections.
        """
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            nn.Sequential(
                Bottleneck(self.c, self.c, shortcut, g),
                PSABlock_RCSOSA(self.c, attn_ratio=0.5, num_heads=max(self.c // 64, 1)),
            )
            if attn
            else C3k(self.c, self.c, 2, shortcut, g)
            if c3k
            else Bottleneck(self.c, self.c, shortcut, g)
            for _ in range(n)
        )

class C2PSA_RCSOSA(nn.Module):
    """C2PSA_RCSOSA module with attention mechanism for enhanced feature extraction and processing.

    This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
    capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.

    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c1.
        m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.

    Methods:
        forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.

    Notes:
        This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.
    """

    def __init__(self, c1: int, c2: int, n: int = 1, e: float = 0.5):
        """Initialize C2PSA module.

        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            n (int): Number of PSABlock modules.
            e (float): Expansion ratio.
        """
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)

        self.m = nn.Sequential(*(PSABlock_RCSOSA(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Process the input tensor through a series of PSA blocks.

        Args:
            x (torch.Tensor): Input tensor.

        Returns:
            (torch.Tensor): Output tensor after processing.
        """
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))


if __name__ == "__main__":
    # Generating Sample image
    image_size = (1, 64, 240, 240)
    image = torch.rand(*image_size)

    # Model
    mobilenet_v1 = C3k2_RCSOSA(64, 64,attn=True)

    out = mobilenet_v1(image)
    print(out.size())

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs
  m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs
  l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs
  x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs

# YOLO26n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5, 3, True]] # 9
  - [-1, 2, C2PSA_RCSOSA, [1024]] # 10

# YOLO26n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs
  m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs
  l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs
  x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs

# YOLO26n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2_RCSOSA, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_RCSOSA, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_RCSOSA, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_RCSOSA, [1024, True]]
  - [-1, 1, SPPF, [1024, 5, 3, True]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO26n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2_RCSOSA, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_RCSOSA, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_RCSOSA, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2_RCSOSA, [1024, True, 0.5, True]] # 22 (P5/32-large)  
  # 所有的C3k2虽然都被替换但因为本机制是二次创新PSABlock模块，仅有此处的代码运行生效了，其余的还是C3k2

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO

if __name__ == '__main__':
    model = YOLO('模型配置文件地址,也就是5.1你保存到本地文件的地址')
    # 如何切换模型版本, 上面的ymal文件可以改为 yolo26s.yaml就是使用的26s,
    # 类似某个改进的yaml文件名称为yolo26-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolo26l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！
    # model.load('yolo26n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
    model.train(
        data=r"数据集文件地址",
                # 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
                cache=False,
                imgsz=640,
                epochs=20,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=0,
                workers=0,
                device='0',
                optimizer='MuSGD', # using SGD/MuSGD
                # resume=, # 这里是填写last.pt地址
                amp=True,  # 如果出现训练损失为Nan可以关闭amp
                project='runs/train',
                name='exp',
                )