wolves/AI-learning
1
0
Fork 0
Code Releases Activity

routine

Browse Source
This commit is contained in:
Wolves
2025-01-25 22:33:14 +08:00
parent 81367980c1
commit f138818abc
14 changed files with 602 additions and 371 deletions
Download Patch File Download Diff File Expand all files Collapse all files

327
lab/7_Muticlass.ipynb Normal file
View File

@@ -0,0 +1,327 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 多分类问题 - 手写数字识别\n",
"\n",
"## 数据集\n",
"- minst数据集(手写数字数据集)\n",
"\n",
"## 激活函数\n",
"- softmax\n",
"\n",
"## 损失函数\n",
"- 交叉熵\n",
"\n",
"## 优化器\n",
"- 梯度下降\n",
"\n",
"## 模型\n",
"- 全连接层\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# 导库\n",
"import tensorflow as tf\n",
"from tensorflow.keras import Sequential\n",
"from tensorflow.keras.layers import Dense\n",
"from tensorflow.keras.losses import SparseCategoricalCrossentropy"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_2\"</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1mModel: \"sequential_2\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ ? │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ ? │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ ? │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"</pre>\n"
],
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_5 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_6 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"None\n"
]
}
],
"source": [
"# TEST\n",
"model = Sequential([Dense(units=25,activation='relu'),\n",
" Dense(units=15,activation='relu'),\n",
" Dense(units=10,activation='softmax')])\n",
"model.compile(loss=SparseCategoricalCrossentropy())\n",
"# 输出模型\n",
"print(model.summary())"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/5\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2025-01-21 11:03:07.974903: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:117] Plugin optimizer for device_type GPU is enabled.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 8ms/step - accuracy: 0.8340 - loss: 0.5514\n",
"Epoch 2/5\n",
"\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 8ms/step - accuracy: 0.8933 - loss: 0.3836\n",
"Epoch 3/5\n",
"\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 8ms/step - accuracy: 0.8902 - loss: 0.4045\n",
"Epoch 4/5\n",
"\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 8ms/step - accuracy: 0.8889 - loss: 0.4049\n",
"Epoch 5/5\n",
"\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 8ms/step - accuracy: 0.8840 - loss: 0.4177\n",
"\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9039 - loss: 0.3451\n"
]
},
{
"data": {
"text/plain": [
"[0.30404922366142273, 0.9150999784469604]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 官方实例\n",
"\n",
"import tensorflow as tf\n",
"mnist = tf.keras.datasets.mnist\n",
"\n",
"(x_train, y_train),(x_test, y_test) = mnist.load_data()\n",
"x_train, x_test = x_train / 255.0, x_test / 255.0\n",
"\n",
"model = tf.keras.models.Sequential([\n",
" tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
" tf.keras.layers.Dense(128, activation='relu'),\n",
" tf.keras.layers.Dropout(0.2),\n",
" tf.keras.layers.Dense(10, activation='softmax')\n",
"])\n",
"\n",
"model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n",
" loss=SparseCategoricalCrossentropy(),\n",
" metrics=['accuracy'])\n",
"\n",
"model.fit(x_train, y_train, epochs=5)\n",
"model.evaluate(x_test, y_test)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/5 - Loss: 0.4415533185513543\n",
"Epoch 2/5 - Loss: 0.24540251612599726\n",
"Epoch 3/5 - Loss: 0.19663310029716696\n",
"Epoch 4/5 - Loss: 0.17048093510557338\n",
"Epoch 5/5 - Loss: 0.16070798563876196\n",
"Accuracy: 95.38%\n"
]
}
],
"source": [
"# 用torch实现\n",
"\n",
"import torch\n",
"import torch.nn as nn\n",
"import torch.optim as optim\n",
"from torchvision import datasets, transforms\n",
"\n",
"# 数据预处理\n",
"transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])\n",
"\n",
"# 加载数据集\n",
"trainset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)\n",
"trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)\n",
"\n",
"testset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)\n",
"testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)\n",
"\n",
"# 定义模型\n",
"class SimpleNet(nn.Module):\n",
" def __init__(self):\n",
" super(SimpleNet, self).__init__()\n",
" self.flatten = nn.Flatten()\n",
" self.fc1 = nn.Linear(28 * 28, 128)\n",
" self.dropout = nn.Dropout(0.2)\n",
" self.fc2 = nn.Linear(128, 10)\n",
"\n",
" def forward(self, x):\n",
" x = self.flatten(x)\n",
" x = torch.relu(self.fc1(x))\n",
" x = self.dropout(x)\n",
" x = self.fc2(x)\n",
" return x\n",
"\n",
"model = SimpleNet()\n",
"\n",
"if torch.backends.mps.is_available():\n",
" device = torch.device(\"mps\")\n",
"else:\n",
" device = torch.device(\"cpu\")\n",
"\n",
"model.to(device)\n",
"\n",
"# 定义损失函数和优化器\n",
"criterion = nn.CrossEntropyLoss()\n",
"optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
"\n",
"# 训练模型\n",
"epochs = 5\n",
"for epoch in range(epochs):\n",
" running_loss = 0\n",
" for images, labels in trainloader:\n",
" images, labels = images.to(device), labels.to(device) # 将数据移动到设备上\n",
" optimizer.zero_grad()\n",
" output = model(images)\n",
" loss = criterion(output, labels)\n",
" loss.backward()\n",
" optimizer.step()\n",
" running_loss += loss.item()\n",
" print(f\"Epoch {epoch+1}/{epochs} - Loss: {running_loss/len(trainloader)}\")\n",
"\n",
"# 测试模型\n",
"correct = 0\n",
"total = 0\n",
"with torch.no_grad():\n",
" for images, labels in testloader:\n",
" images, labels = images.to(device), labels.to(device) # 将数据移动到设备上\n",
" output = model(images)\n",
" _, predicted = torch.max(output, 1)\n",
" total += labels.size(0)\n",
" correct += (predicted == labels).sum().item()\n",
"\n",
"print(f\"Accuracy: {100 * correct / total}%\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "ail",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}