initial commit

.cspell.json

@@ -0,0 +1,6 @@
+{
+  "words": [
+    "dotenv"
+  ],
+  "allowCompoundWords": true
+}

.env.example

@@ -0,0 +1,3 @@
+TRAIN_DATASET = /path/to/your/train-dataset
+TEST_DATASET = /path/to/your/test-dataset
+KMP_DUPLICATE_LIB_OK = TRUE # 避免 OpenMP 重复初始化错误。不要修改这一项

.gitignore

@@ -0,0 +1,3 @@
+*.h5
+.env
+/test

LICENSE

@@ -0,0 +1,121 @@
+Creative Commons Legal Code
+
+CC0 1.0 Universal
+
+    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+    HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+  i. the right to reproduce, adapt, distribute, perform, display,
+     communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+     likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+     subject to the limitations in paragraph 4(a), below;
+  v. rights protecting the extraction, dissemination, use and reuse of data
+     in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+     European Parliament and of the Council of 11 March 1996 on the legal
+     protection of databases, and under any national implementation
+     thereof, including any amended or successor version of such
+     directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+     world based on applicable law or treaty, and any national
+     implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+    surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+    warranties of any kind concerning the Work, express, implied,
+    statutory or otherwise, including without limitation warranties of
+    title, merchantability, fitness for a particular purpose, non
+    infringement, or the absence of latent or other defects, accuracy, or
+    the present or absence of errors, whether or not discoverable, all to
+    the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+    that may apply to the Work or any use thereof, including without
+    limitation any person's Copyright and Related Rights in the Work.
+    Further, Affirmer disclaims responsibility for obtaining any necessary
+    consents, permissions or other rights required for any use of the
+    Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+    party to this document and has no duty or obligation with respect to
+    this CC0 or use of the Work.

README.md

@@ -0,0 +1,68 @@
+# 机器学习 - 猫狗识别简单实现
+
+这是一个简单的基于 Tensorflow 的猫狗识别模型。用于入门机器学习以及了解机器学习中的基础概念。
+
+## 安装
+
+首先需要下载猫狗识别的数据集用于训练。可以参考在 HuggingFace 的 [Microsoft 的数据集](https://huggingface.co/datasets/microsoft/cats_vs_dogs)
+下载训练数据集后，需要做一些整理，先确保项目目录结构如下：
+
+```
+train/
+├── cats/
+│   ├── cat.0.jpg
+│   ├── ....
+|── dogs/
+    ├── dog.0.jpg
+    ├── ....
+```
+
+然后复制本项目中的 `.env.example` 一份到本目录，重命名为 `.env` 并修改内容，改成 train 目录的所在地
+
+```bash
+TRAIN_DATASET = /path/to/your/dataset
+```
+
+然后在 conda 环境下安装依赖。
+
+```bash
+conda create --name cat-vs-dog python=3.9 --file requirements.txt
+```
+
+## 训练
+
+执行命令
+
+```bash
+python train.py
+```
+
+将会在本目录下生成 `cat_dog_model.h5` 模型文件。
+
+## 预测
+
+准备好测试数据集的目录，目录下只需存放图片即可。
+
+在 `.env` 文件中添加测试数据集的目录。
+
+```bash
+TEST_DATASET = /path/to/your/dataset
+```
+
+请先确保你已经训练好了数据并正确生成了 `cat_dog_model.h5` 模型文件。
+
+如果你没条件训练，可以直接在本仓库的 Release 上[下载现有的模型](https://github.com/PrinOrange/dog-vs-cat/releases/tag/1.0.0)。
+
+
+然后执行命令
+
+```bash
+python test.py
+```
+
+在命令台中会产生如下输出：
+
+```plaintext
+The model predicts the image xxx.jpg is a cat, with sigmoid 0.9999812
+...
+```

test.py

@@ -0,0 +1,40 @@
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+import numpy as np
+import os
+
+# 加载模型
+model = load_model("cat_dog_model.h5")
+
+# 设置要处理的目录
+input_dir = os.getenv("TEST_DATASET")
+
+# 支持的图像扩展名
+image_extensions = (".jpg", ".jpeg", ".png", ".bmp")
+
+def predict(img_path):
+    img = image.load_img(img_path, target_size=(150, 150))
+    x = image.img_to_array(img) / 255.0
+    x = np.expand_dims(x, axis=0)
+    pred = model.predict(x)[0][0]
+
+    if pred < 0.3:
+        label = "cat"
+    elif pred > 0.7:
+        label = "dog"
+    else:
+        label = "uncertain animal"
+
+    return [label, pred]
+
+# 遍历目录下所有图片文件
+for fname in os.listdir(input_dir):
+    if not fname.lower().endswith(image_extensions):
+        continue  # 跳过非图片文件
+    img_path = os.path.join(input_dir, fname)
+    try:
+        result = predict(img_path)
+        print("The model predicts the image '%s' is a %s, with sigmoid %s" %
+              (fname, result[0], result[1]))
+    except Exception as e:
+        print(f"Error processing {fname}: {e}")

train.py

@@ -0,0 +1,105 @@
+import tensorflow as tf
+import os
+import matplotlib.pyplot as plt
+from dotenv import load_dotenv
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+
+load_dotenv()
+
+# Hyper Parameter 配置
+BATCH_SIZE = 32
+IMG_SIZE = (224, 224)
+TRAIN_DATASET = os.getenv("TRAIN_DATASET")
+EPOCHS = 8
+OPTIMIZER = 'adam'
+LOSS_FUNC = 'binary_crossentropy'
+
+# 数据预处理
+def load_data():
+    datagen = ImageDataGenerator(
+        validation_split=0.2,   # 验证集比例为 20%
+        rescale=1./255,         # 像素归一化，把 RGB 彩图转为灰度图
+        horizontal_flip=True,   # 随机水平翻转
+        zoom_range=0.2          # 随机缩放，范围在 80%-120%，模拟距离变化
+    )
+    
+    train_data = datagen.flow_from_directory(
+        directory=TRAIN_DATASET,# 数据位置
+        target_size=IMG_SIZE,   # 图像尺寸
+        batch_size=BATCH_SIZE,  # 一次训练样本数量
+        class_mode="binary",    # 二分类问题
+        subset="training",      # 训练集
+        shuffle=True            # 随机打乱数据
+    )
+    
+    val_data = datagen.flow_from_directory(
+        directory=TRAIN_DATASET,
+        target_size=IMG_SIZE,
+        batch_size=BATCH_SIZE,
+        class_mode="binary",
+        subset="validation",
+        shuffle=True
+    )
+    
+    return train_data, val_data
+
+# 构建模型
+def build_model():
+    model = tf.keras.Sequential([
+        # 第一层卷积：是在输入图像的每一个 3×3 的局部区域上，通过 32 个不同的卷积核，
+	    # 提取出 32 个特征值，最终形成一张高宽和原图相近、通道数为 32 的特征图。
+        # 捕捉初步细节特征，如边缘、纹理等
+        tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(*IMG_SIZE, 3)),
+        tf.keras.layers.MaxPooling2D(2,2),
+        
+        # 第二层卷积，继续在 3×3 的局部区域上提取 64 个特征图，过程类似
+        # 捕捉捕获更复杂的形状和图案
+        tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
+        tf.keras.layers.MaxPooling2D(2,2),
+        
+        # 第三层卷积
+        # 学习更抽象的物体部分或整体形状
+        tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
+        tf.keras.layers.MaxPooling2D(2,2),
+        tf.keras.layers.Flatten(),
+        tf.keras.layers.Dense(512, activation='relu'),
+        tf.keras.layers.Dense(1, activation='sigmoid')
+    ])
+    
+    # 编译模型
+    model.compile(optimizer=OPTIMIZER,
+                  loss=LOSS_FUNC,
+                  metrics=['accuracy'])
+    
+    return model
+
+# 主程序入口
+def main():
+    train_data, val_data = load_data()
+    model = build_model()
+    
+    # 训练模型并生成训练的历史数据
+    history = model.fit(
+        train_data,
+        epochs = EPOCHS,
+        validation_data=val_data
+    )
+    
+    # 保存模型
+    model.save("cat_dog_model.h5")
+
+    # 可视化训练过程
+    acc = history.history['accuracy']
+    loss = history.history['loss']
+    val_acc = history.history['val_accuracy']
+    val_loss = history.history['val_loss']
+    plt.plot(acc, label='Train Accuracy')
+    plt.plot(val_acc, label='Validation Accuracy')
+    plt.plot(loss, label='Train Loss')
+    plt.plot(val_loss, label='Validation Loss')
+    plt.legend()
+    plt.title('Training Accuracy')
+    plt.show()
+
+if __name__ == "__main__":
+    main()