提交了项目代码

Author: Nolan-149

examples/CNN_UTS/main.py

@@ -1,7 +1,6 @@
 import os
 
 import hydra
-import matplotlib.pyplot as plt
 import numpy as np
 import paddle
 import tqdm
@@ -193,6 +192,9 @@ def evaluate(cfg):
     """
     完整的评估流程，包括模型加载、推理、指标计算、可视化和集成预测
     """
+    import matplotlib.pyplot as plt
+    from sklearn.model_selection import StratifiedGroupKFold
+
     set_seed(cfg.seed)
     device = device2str(cfg.device)
     n_splits = cfg.train.n_splits

examples/CNN_UTS/readme.md

@@ -14,7 +14,7 @@
 ├── Saved_Output/ # 保存预测结果与可视化
 ├── requirements.txt # 依赖库
 └── readme.md # 项目说明文档
-
+```
 
 ## 环境依赖
 
@@ -83,8 +83,15 @@ python main.py mode=eval
 - 配置化超参数与数据路径
 - 自动保存/加载模型与预测结果
 - 多种可视化与统计指标输出
+如需引用本项目复现的方法，请参考原论文：
 
-## 联系方式
+plaintext
+@article{lai2025predicting,
+  title={Predicting the Strength of Composites with Computer Vision Using Small Experimental Datasets},
+  author={Lai, Po-Hao and Gomez, Enrique D and Vogt, Bryan D and Reinhart, Wesley F},
+  journal={ACS Materials Letters},
+  year={2025},
+  publisher={American Chemical Society}
+}
 
-如有问题请联系：[email protected]
 

ppsci/arch/resnet.py

@@ -0,0 +1,93 @@
+import paddle
+import paddle.nn as nn
+
+from ppsci.arch import base
+
+
+class ResNetBlock(nn.Layer):
+    def __init__(self, in_channels, out_channels, stride=1):
+        super().__init__()
+        self.conv1 = nn.Conv2D(in_channels, out_channels, 3, stride, 1)
+        self.bn1 = nn.BatchNorm2D(out_channels)
+        self.relu = nn.ReLU()
+        self.conv2 = nn.Conv2D(out_channels, out_channels, 3, 1, 1)
+        self.bn2 = nn.BatchNorm2D(out_channels)
+        if stride != 1 or in_channels != out_channels:
+            self.downsample = nn.Sequential(
+                nn.Conv2D(in_channels, out_channels, 1, stride),
+                nn.BatchNorm2D(out_channels),
+            )
+        else:
+            self.downsample = None
+
+    def forward(self, x):
+        identity = x
+        out = self.relu(self.bn1(self.conv1(x)))
+        out = self.bn2(self.conv2(out))
+        if self.downsample is not None:
+            identity = self.downsample(x)
+        out += identity
+        out = self.relu(out)
+        return out
+
+
+class ResNet(base.Arch):
+    """
+    PaddleScience风格的ResNet实现，支持自定义输入输出、层数、特征提取等。
+    """
+
+    def __init__(
+        self,
+        input_keys,
+        output_keys,
+        num_blocks=(2, 2, 2, 2),  # ResNet18默认
+        num_classes=1,
+        in_channels=3,
+        base_channels=64,
+        **kwargs
+    ):
+        super().__init__()
+        self.input_keys = input_keys
+        self.output_keys = output_keys
+
+        self.conv1 = nn.Conv2D(in_channels, base_channels, 7, 2, 3)
+        self.bn1 = nn.BatchNorm2D(base_channels)
+        self.relu = nn.ReLU()
+        self.maxpool = nn.MaxPool2D(3, 2, 1)
+
+        self.layer1 = self._make_layer(base_channels, base_channels, num_blocks[0])
+        self.layer2 = self._make_layer(
+            base_channels, base_channels * 2, num_blocks[1], stride=2
+        )
+        self.layer3 = self._make_layer(
+            base_channels * 2, base_channels * 4, num_blocks[2], stride=2
+        )
+        self.layer4 = self._make_layer(
+            base_channels * 4, base_channels * 8, num_blocks[3], stride=2
+        )
+
+        self.avgpool = nn.AdaptiveAvgPool2D((1, 1))
+        self.fc = nn.Linear(base_channels * 8, num_classes)
+
+    def _make_layer(self, in_channels, out_channels, blocks, stride=1):
+        layers = [ResNetBlock(in_channels, out_channels, stride)]
+        for _ in range(1, blocks):
+            layers.append(ResNetBlock(out_channels, out_channels))
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        # x: dict, 取input_keys
+        if isinstance(x, dict):
+            x = x[self.input_keys[0]]
+        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 = paddle.flatten(x, 1)
+        x = self.fc(x)
+        return x