Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "MyResnetModelForImageClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_MyResnet.MyResnetConfig",
+    "AutoModelForImageClassification": "modeling_MyResnet.MyResnetModelForImageClassification"
+  },
+  "in_channels": 3,
+  "model_type": "resnet",
+  "num_channels": 64,
+  "num_classes": 176,
+  "num_residuals": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

configuration_MyResnet.py

@@ -0,0 +1,26 @@
+from transformers import PretrainedConfig
+
+"""
+编写自定义配置时需要记住的三个重要事项如下：
+必须继承自 PretrainedConfig，
+PretrainedConfig 的 __init__ 方法必须接受任何 kwargs，
+这些 kwargs 需要传递给超类的 __init__ 方法。
+"""
+class MyResnetConfig(PretrainedConfig):
+    model_type = "resnet"
+
+    def __init__(
+            self,
+            num_classes: int = 176,  # 分类数
+            in_channels: int = 3,  # 输入通道数
+            num_channels: int = 64,  # 第一个卷积的输出通道数
+            num_residuals=None,  # 每个残差块组合里残差块的数量
+            **kwargs,
+    ):
+        self.num_classes = num_classes
+        self.in_channels = in_channels
+        self.num_channels = num_channels
+        if num_residuals is None:
+            num_residuals = [2, 2, 2, 2]
+        self.num_residuals = num_residuals
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f439c16a4605e7282c4bdfd481b9afdf1ff06ea6cd7ec471953e8ed243cf5d
+size 45121784

modeling_MyResnet.py

@@ -0,0 +1,156 @@
+import os
+import torch
+from torch import nn
+from torch.nn import functional as F
+from transformers import PreTrainedModel
+from .configuration_MyResnet import MyResnetConfig
+
+# 设置CUDA异常阻塞，用于调试CUDA相关问题
+os.environ['CUDA_LAUNCH_BLOCKING'] = '1'
+
+"""
+定义自己的模型
+"""
+
+
+# 定义残差块
+class Residual(nn.Module):
+    def __init__(self, input_channels, num_channels,
+                 use_1x1conv=False, strides=1):
+        super().__init__()
+        # 第一个3x3卷积层
+        self.conv1 = nn.Conv2d(input_channels, num_channels,
+                               kernel_size=3, padding=1, stride=strides)
+        # 第二个3x3卷积层
+        self.conv2 = nn.Conv2d(num_channels, num_channels,
+                               kernel_size=3, padding=1)
+        # 可选的1x1卷积层，用于调整输入的通道数
+        if use_1x1conv:
+            self.conv3 = nn.Conv2d(input_channels, num_channels,
+                                   kernel_size=1, stride=strides)
+        else:
+            self.conv3 = None
+        # 批量归一化层
+        self.bn1 = nn.BatchNorm2d(num_channels)
+        self.bn2 = nn.BatchNorm2d(num_channels)
+
+    def forward(self, X):
+        # 第一个卷积 -> 批量归一化 -> ReLU激活
+        Y = F.relu(self.bn1(self.conv1(X)))
+        # 第二个卷积 -> 批量归一化
+        Y = self.bn2(self.conv2(Y))
+        # 如果使用1x1卷积，调整输入的通道数
+        if self.conv3:
+            X = self.conv3(X)
+        # 将输入与输出相加
+        Y += X
+        return F.relu(Y)  # 返回激活后的结果
+
+
+# 组合多个残差块
+def resnet_block(input_channels, num_channels, num_residuals,
+                 first_block=False):
+    """
+    :param first_block: 是否为第一个块，用于确定是否需要1x1卷积
+    :param input_channels: 输入通道数
+    :param num_channels: 残差块的输出通道数
+    :param num_residuals: 残差块的数量
+    :return: 组合后的多个残差块
+    """
+    blk = []
+    for i in range(num_residuals):
+        # 第一个残差块需要降维
+        if i == 0 and not first_block:
+            blk.append(Residual(input_channels, num_channels,
+                                use_1x1conv=True, strides=2))
+        else:
+            blk.append(Residual(num_channels, num_channels))
+    return blk
+
+
+# 定义残差网络
+def net(in_channels, num_channels, num_residuals, num_classes):
+    """
+    :param in_channels: 输入图像的通道数
+    :param num_channels: 第一个卷积层的输出通道数
+    :param num_residuals: 每个阶段的残差块数量
+    :param num_classes: 分类的数量
+    :return: 构建的残差网络模型
+    """
+    # 首先是一个7x7卷积层，接着是批量归一化、ReLU激活和3x3最大池化
+    b1 = nn.Sequential(nn.Conv2d(in_channels, num_channels, kernel_size=7, stride=2, padding=3),
+                       nn.BatchNorm2d(64), nn.ReLU(),
+                       nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
+
+    # 构建多个残差块
+    b2 = nn.Sequential(*resnet_block(64, num_channels, num_residuals[0], first_block=True))
+    b3 = nn.Sequential(*resnet_block(num_channels, num_channels * 2, num_residuals[1]))
+    b4 = nn.Sequential(*resnet_block(num_channels * 2, num_channels * 4, num_residuals[2]))
+    b5 = nn.Sequential(*resnet_block(num_channels * 4, num_channels * 8, num_residuals[3]))
+
+    # 全局平均池化后，连接一个全连接层进行分类
+    resnet = nn.Sequential(b1, b2, b3, b4, b5,
+                           nn.AdaptiveAvgPool2d((1, 1)),
+                           nn.Flatten(), nn.Linear(num_channels * 8, num_classes))
+    return resnet
+
+
+"""
+把模型封装成huggingface的模型，
+可以使用transformers库进行训练和推理
+这里定义了两个模型类：一个用于从一批图像中提取隐藏特征（类似于 BertModel），
+另一个适用于图像分类（类似于 BertForSequenceClassification）。
+"""
+
+
+class MyResnetModel(PreTrainedModel):
+    config_class = MyResnetConfig  # 指定配置类
+
+    def __init__(self, config):
+        super().__init__(config)
+        # 根据配置初始化模型
+        self.model = net(
+            in_channels=config.in_channels,
+            num_channels=config.num_channels,
+            num_residuals=config.num_residuals,
+            num_classes=config.num_classes
+        )
+
+    def forward(self, tensor, labels=None):
+        return self.model.forward_features(tensor)  # 返回特征
+
+
+class MyResnetModelForImageClassification(PreTrainedModel):
+    config_class = MyResnetConfig  # 指定配置类
+
+    def __init__(self, config):
+        super().__init__(config)
+        # 根据配置初始化模型
+        self.model = net(
+            in_channels=config.in_channels,
+            num_channels=config.num_channels,
+            num_residuals=config.num_residuals,
+            num_classes=config.num_classes
+        )
+
+    """
+    你可以让模型返回任何你想要的内容，
+    但是像这样返回一个字典，并在传递标签时包含loss，可以使你的模型能够在 Trainer 类中直接使用。
+    只要你计划使用自己的训练循环或其他库进行训练，也可以使用其他输出格式。
+    """
+
+    def forward(self, X, y):
+        # 前向传播，计算模型输出
+        # print(y)
+        y_hat = self.model(X)
+        if y is not None:
+            # 计算损失
+            loss = torch.nn.functional.cross_entropy(y_hat, y)
+            return {"loss": loss, "logits": y_hat}  # 返回损失和输出
+        return {"logits": y_hat}
+
+    def forward_features(self, X):
+        # 返回特征
+        for layer in self.model:
+            X = layer(X)
+            print(layer.__class__.__name__, 'output shape:\t', X.shape)