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

250313

Browse Source
This commit is contained in:
Wolves
2025-03-13 18:14:01 +08:00
parent f138818abc
commit ef679e98da
8 changed files with 474 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -30,3 +30,7 @@ pip install tensorflow
pip install -r requirements.txt pip install -r requirements.txt
``` ```
## 安装graphviz - 绘制模型图
```shell
brew install graphviz
```

40
Users/username/code/linear_regression_m1.py Normal file
View File

@@ -0,0 +1,40 @@
import torch
# 检查MPS可用性（需要PyTorch 1.12+和macOS 12.3+）
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
# 生成训练数据（移动到MPS设备）
X = torch.randn(1000, 2).to(device) # 1000个样本，2个特征
y = X @ torch.tensor([2.0, -3.4], device=device) + 4 # 真实关系式
y += 0.01 * torch.randn(y.shape, device=device) # 添加噪声
# 定义模型（必须继承nn.Module）
class LinearRegression(torch.nn.Module):
def __init__(self):
super().__init__()
self.linear = torch.nn.Linear(2, 1) # 输入2维，输出1维
def forward(self, x):
return self.linear(x)
model = LinearRegression().to(device) # 将模型移至MPS设备
criterion = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
# 训练循环
for epoch in range(500):
# 前向传播
outputs = model(X)
loss = criterion(outputs, y.unsqueeze(1))
# 反向传播
optimizer.zero_grad()
loss.backward()
optimizer.step()
if epoch % 50 == 0:
print(f'Epoch {epoch}, loss: {loss.item():.4f}')
# 输出最终参数
print("Learned weights:", model.linear.weight.data)
print("Learned bias:", model.linear.bias.data)

73
lab/0_mathImage.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

212
lab/5_MLP-tf.ipynb
View File

@@ -20,14 +20,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-01-20T09:22:08.756378Z", "end_time": "2025-02-21T07:47:17.280733Z",
"start_time": "2025-01-20T09:22:08.738301Z" "start_time": "2025-02-21T07:47:17.273671Z"
} }
}, },
"outputs": [],
"source": [ "source": [
"# 导库\n", "# 导库\n",
"import tensorflow as tf\n", "import tensorflow as tf\n",
@@ -38,7 +36,9 @@
"from tensorflow.keras.layers import Dense\n", "from tensorflow.keras.layers import Dense\n",
"from sklearn.metrics import accuracy_score\n", "from sklearn.metrics import accuracy_score\n",
"from tensorflow.keras.models import Sequential" "from tensorflow.keras.models import Sequential"
] ],
"outputs": [],
"execution_count": 2
}, },
{ {
"cell_type": "code", "cell_type": "code",
@@ -158,206 +158,206 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 103ms/step - loss: 60.6063\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 103ms/step - loss: 60.6063\n",
"Epoch 2/100\n", "Epoch 2/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 28.2659\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 28.2659\n",
"Epoch 3/100\n", "Epoch 3/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 1.4893\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 1.4893\n",
"Epoch 4/100\n", "Epoch 4/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 4.0465\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 4.0465\n",
"Epoch 5/100\n", "Epoch 5/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 6.5380\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 6.5380\n",
"Epoch 6/100\n", "Epoch 6/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 8.9314\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 8.9314\n",
"Epoch 7/100\n", "Epoch 7/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 8.9564\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 8.9564\n",
"Epoch 8/100\n", "Epoch 8/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 10.6051\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 10.6051\n",
"Epoch 9/100\n", "Epoch 9/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 12.0071\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 12.0071\n",
"Epoch 10/100\n", "Epoch 10/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 10.6521\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 10.6521\n",
"Epoch 11/100\n", "Epoch 11/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 14.1705\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 14.1705\n",
"Epoch 12/100\n", "Epoch 12/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 13.1806\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 13.1806\n",
"Epoch 13/100\n", "Epoch 13/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 12.1059\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 12.1059\n",
"Epoch 14/100\n", "Epoch 14/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 13.4850\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 13.4850\n",
"Epoch 15/100\n", "Epoch 15/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 12.3003\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 12.3003\n",
"Epoch 16/100\n", "Epoch 16/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 11.7990\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 11.7990\n",
"Epoch 17/100\n", "Epoch 17/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 10.3683\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 10.3683\n",
"Epoch 18/100\n", "Epoch 18/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 9.7598 \n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 9.7598 \n",
"Epoch 19/100\n", "Epoch 19/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 10.2508\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 10.2508\n",
"Epoch 20/100\n", "Epoch 20/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 8.2063\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 8.2063\n",
"Epoch 21/100\n", "Epoch 21/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 6.3501\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 6.3501\n",
"Epoch 22/100\n", "Epoch 22/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 6.1186\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 6.1186\n",
"Epoch 23/100\n", "Epoch 23/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 4.8664\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 4.8664\n",
"Epoch 24/100\n", "Epoch 24/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 4.0431\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 4.0431\n",
"Epoch 25/100\n", "Epoch 25/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 3.5386\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 3.5386\n",
"Epoch 26/100\n", "Epoch 26/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 2.7600\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 2.7600\n",
"Epoch 27/100\n", "Epoch 27/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 1.3724\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 1.3724\n",
"Epoch 28/100\n", "Epoch 28/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.5045\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.5045\n",
"Epoch 29/100\n", "Epoch 29/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 1.9855\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 1.9855\n",
"Epoch 30/100\n", "Epoch 30/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 1.0879\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 1.0879\n",
"Epoch 31/100\n", "Epoch 31/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.6851\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.6851\n",
"Epoch 32/100\n", "Epoch 32/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 1.2047\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 1.2047\n",
"Epoch 33/100\n", "Epoch 33/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 1.5541\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 1.5541\n",
"Epoch 34/100\n", "Epoch 34/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 1.2758\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 1.2758\n",
"Epoch 35/100\n", "Epoch 35/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 1.3003\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 1.3003\n",
"Epoch 36/100\n", "Epoch 36/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.8837\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.8837\n",
"Epoch 37/100\n", "Epoch 37/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.5647\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.5647\n",
"Epoch 38/100\n", "Epoch 38/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.6855\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.6855\n",
"Epoch 39/100\n", "Epoch 39/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.5609\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.5609\n",
"Epoch 40/100\n", "Epoch 40/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 0.4828\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 0.4828\n",
"Epoch 41/100\n", "Epoch 41/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 0.6055\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 29ms/step - loss: 0.6055\n",
"Epoch 42/100\n", "Epoch 42/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - loss: 0.5680\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 65ms/step - loss: 0.5680\n",
"Epoch 43/100\n", "Epoch 43/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 0.3890\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 0.3890\n",
"Epoch 44/100\n", "Epoch 44/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4543\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4543\n",
"Epoch 45/100\n", "Epoch 45/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4878\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4878\n",
"Epoch 46/100\n", "Epoch 46/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 0.4287\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 0.4287\n",
"Epoch 47/100\n", "Epoch 47/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4933\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4933\n",
"Epoch 48/100\n", "Epoch 48/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 0.5080\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 27ms/step - loss: 0.5080\n",
"Epoch 49/100\n", "Epoch 49/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4485\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4485\n",
"Epoch 50/100\n", "Epoch 50/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4195\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4195\n",
"Epoch 51/100\n", "Epoch 51/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4215\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4215\n",
"Epoch 52/100\n", "Epoch 52/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4477\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4477\n",
"Epoch 53/100\n", "Epoch 53/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 0.4759\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 32ms/step - loss: 0.4759\n",
"Epoch 54/100\n", "Epoch 54/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4077\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4077\n",
"Epoch 55/100\n", "Epoch 55/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4073\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4073\n",
"Epoch 56/100\n", "Epoch 56/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.3936\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.3936\n",
"Epoch 57/100\n", "Epoch 57/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4006\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4006\n",
"Epoch 58/100\n", "Epoch 58/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4254\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4254\n",
"Epoch 59/100\n", "Epoch 59/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4196\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4196\n",
"Epoch 60/100\n", "Epoch 60/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4221\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4221\n",
"Epoch 61/100\n", "Epoch 61/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4271\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4271\n",
"Epoch 62/100\n", "Epoch 62/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4239\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4239\n",
"Epoch 63/100\n", "Epoch 63/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.3905\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.3905\n",
"Epoch 64/100\n", "Epoch 64/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4415\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4415\n",
"Epoch 65/100\n", "Epoch 65/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.4230\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 66ms/step - loss: 0.4230\n",
"Epoch 66/100\n", "Epoch 66/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 0.3950\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 0.3950\n",
"Epoch 67/100\n", "Epoch 67/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4236\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4236\n",
"Epoch 68/100\n", "Epoch 68/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4291\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4291\n",
"Epoch 69/100\n", "Epoch 69/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4066\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4066\n",
"Epoch 70/100\n", "Epoch 70/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 0.4228\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 30ms/step - loss: 0.4228\n",
"Epoch 71/100\n", "Epoch 71/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.3788\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.3788\n",
"Epoch 72/100\n", "Epoch 72/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4248\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4248\n",
"Epoch 73/100\n", "Epoch 73/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4265\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4265\n",
"Epoch 74/100\n", "Epoch 74/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4165\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4165\n",
"Epoch 75/100\n", "Epoch 75/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4262\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4262\n",
"Epoch 76/100\n", "Epoch 76/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4238\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4238\n",
"Epoch 77/100\n", "Epoch 77/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4055\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4055\n",
"Epoch 78/100\n", "Epoch 78/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4483\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4483\n",
"Epoch 79/100\n", "Epoch 79/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4379\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4379\n",
"Epoch 80/100\n", "Epoch 80/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4697\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4697\n",
"Epoch 81/100\n", "Epoch 81/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4096\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4096\n",
"Epoch 82/100\n", "Epoch 82/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4069\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4069\n",
"Epoch 83/100\n", "Epoch 83/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4518\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4518\n",
"Epoch 84/100\n", "Epoch 84/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4145\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4145\n",
"Epoch 85/100\n", "Epoch 85/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.3853\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.3853\n",
"Epoch 86/100\n", "Epoch 86/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.4064\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 60ms/step - loss: 0.4064\n",
"Epoch 87/100\n", "Epoch 87/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4533\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4533\n",
"Epoch 88/100\n", "Epoch 88/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4798\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4798\n",
"Epoch 89/100\n", "Epoch 89/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4093\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4093\n",
"Epoch 90/100\n", "Epoch 90/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 0.4176\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 0.4176\n",
"Epoch 91/100\n", "Epoch 91/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 0.4351\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 0.4351\n",
"Epoch 92/100\n", "Epoch 92/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4422\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4422\n",
"Epoch 93/100\n", "Epoch 93/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 0.4550\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 26ms/step - loss: 0.4550\n",
"Epoch 94/100\n", "Epoch 94/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4387\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4387\n",
"Epoch 95/100\n", "Epoch 95/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 0.4847\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 24ms/step - loss: 0.4847\n",
"Epoch 96/100\n", "Epoch 96/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4777\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4777\n",
"Epoch 97/100\n", "Epoch 97/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4309\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4309\n",
"Epoch 98/100\n", "Epoch 98/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.4221\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 25ms/step - loss: 0.4221\n",
"Epoch 99/100\n", "Epoch 99/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 0.4159\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 23ms/step - loss: 0.4159\n",
"Epoch 100/100\n", "Epoch 100/100\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 0.3821\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step - loss: 0.3821\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step\n", "\u001B[1m2/2\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 34ms/step\n",
"模型的精准度: 0.85\n" "模型的精准度: 0.85\n"
] ]
} }

157
lab/7_Muticlass.ipynb
View File

@@ -24,7 +24,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -37,98 +37,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"# TEST\n", "# TEST\n",
"model = Sequential([Dense(units=25,activation='relu'),\n", "model = Sequential([Dense(units=25,activation='relu'),\n",
@@ -141,50 +52,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"# 官方实例\n", "# 官方实例\n",
"\n", "\n",
@@ -211,22 +81,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"# 用torch实现\n", "# 用torch实现\n",
"\n", "\n",

188
lab/8_cnn-yolo.ipynb Normal file
View File

@@ -0,0 +1,188 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 全链接层实现手写数字识别,tensorflow版本"
]
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-13T10:10:31.080622Z",
"start_time": "2025-03-13T10:10:31.074650Z"
}
},
"cell_type": "code",
"source": [
"import tensorflow as tf\n",
"print(tf.__version__) # 确保输出为2.16.x\n",
"print(tf.keras.__version__)"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.16.2\n",
"3.8.0\n"
]
}
],
"execution_count": 5
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-13T10:00:58.363886Z",
"start_time": "2025-03-13T10:00:34.418446Z"
}
},
"source": [
"import tensorflow as tf\n",
"from tensorflow.keras import layers, models\n",
"from tensorflow.keras.datasets import mnist\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# 加载MNIST数据集\n",
"(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
"\n",
"# 数据预处理\n",
"x_train = x_train.reshape(-1, 28*28).astype('float32') / 255.0\n",
"x_test = x_test.reshape(-1, 28*28).astype('float32') / 255.0\n",
"\n",
"# 将标签转换为one-hot编码\n",
"y_train = tf.keras.utils.to_categorical(y_train, 10)\n",
"y_test = tf.keras.utils.to_categorical(y_test, 10)\n",
"\n",
"# 构建全连接神经网络模型\n",
"model = models.Sequential([\n",
" layers.Dense(512, activation='relu', input_shape=(28*28,)),\n",
" layers.Dropout(0.2),\n",
" layers.Dense(256, activation='relu'),\n",
" layers.Dropout(0.2),\n",
" layers.Dense(10, activation='softmax')\n",
"])\n",
"\n",
"# 编译模型\n",
"model.compile(optimizer='adam',\n",
" loss='categorical_crossentropy',\n",
" metrics=['accuracy'])\n",
"\n",
"# 训练模型\n",
"history = model.fit(x_train, y_train, \n",
" epochs=10, \n",
" batch_size=128, \n",
" validation_split=0.2)\n",
"\n",
"# 评估模型\n",
"test_loss, test_acc = model.evaluate(x_test, y_test)\n",
"print(f'accuracy: {test_acc:.4f}')\n",
"\n",
"# 绘制训练过程\n",
"plt.figure(figsize=(12, 4))\n",
"\n",
"plt.subplot(1, 2, 1)\n",
"plt.plot(history.history['accuracy'], label='train accuracy')\n",
"plt.plot(history.history['val_accuracy'], label='verify accuracy')\n",
"plt.title('accuracy')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Accuracy')\n",
"plt.legend()\n",
"\n",
"plt.subplot(1, 2, 2)\n",
"plt.plot(history.history['loss'], label='train loss')\n",
"plt.plot(history.history['val_loss'], label='val loss')\n",
"plt.title('loss')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Loss')\n",
"plt.legend()\n",
"\n",
"plt.show()\n"
],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/wolves/mambaforge/envs/ail/lib/python3.10/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
" super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n",
"2025-03-13 18:00:52.176862: I metal_plugin/src/device/metal_device.cc:1154] Metal device set to: Apple M1\n",
"2025-03-13 18:00:52.176900: I metal_plugin/src/device/metal_device.cc:296] systemMemory: 16.00 GB\n",
"2025-03-13 18:00:52.176905: I metal_plugin/src/device/metal_device.cc:313] maxCacheSize: 5.33 GB\n",
"2025-03-13 18:00:52.176939: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.\n",
"2025-03-13 18:00:52.176949: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2025-03-13 18:00:52.721501: 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[1m302/375\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m━━━━\u001B[0m \u001B[1m1s\u001B[0m 14ms/step - accuracy: 0.7914 - loss: 0.6815"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
"\u001B[0;31mKeyboardInterrupt\u001B[0m Traceback (most recent call last)",
"Cell \u001B[0;32mIn[2], line 32\u001B[0m\n\u001B[1;32m 27\u001B[0m model\u001B[38;5;241m.\u001B[39mcompile(optimizer\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124madam\u001B[39m\u001B[38;5;124m'\u001B[39m,\n\u001B[1;32m 28\u001B[0m loss\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mcategorical_crossentropy\u001B[39m\u001B[38;5;124m'\u001B[39m,\n\u001B[1;32m 29\u001B[0m metrics\u001B[38;5;241m=\u001B[39m[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124maccuracy\u001B[39m\u001B[38;5;124m'\u001B[39m])\n\u001B[1;32m 31\u001B[0m \u001B[38;5;66;03m# 训练模型\u001B[39;00m\n\u001B[0;32m---> 32\u001B[0m history \u001B[38;5;241m=\u001B[39m \u001B[43mmodel\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfit\u001B[49m\u001B[43m(\u001B[49m\u001B[43mx_train\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43my_train\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\n\u001B[1;32m 33\u001B[0m \u001B[43m \u001B[49m\u001B[43mepochs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m10\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\n\u001B[1;32m 34\u001B[0m \u001B[43m \u001B[49m\u001B[43mbatch_size\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m128\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\n\u001B[1;32m 35\u001B[0m \u001B[43m \u001B[49m\u001B[43mvalidation_split\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m0.2\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[1;32m 37\u001B[0m \u001B[38;5;66;03m# 评估模型\u001B[39;00m\n\u001B[1;32m 38\u001B[0m test_loss, test_acc \u001B[38;5;241m=\u001B[39m model\u001B[38;5;241m.\u001B[39mevaluate(x_test, y_test)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py:117\u001B[0m, in \u001B[0;36mfilter_traceback.<locals>.error_handler\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m 115\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[1;32m 116\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[0;32m--> 117\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfn\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 118\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m 119\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m _process_traceback_frames(e\u001B[38;5;241m.\u001B[39m__traceback__)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/keras/src/backend/tensorflow/trainer.py:371\u001B[0m, in \u001B[0;36mTensorFlowTrainer.fit\u001B[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)\u001B[0m\n\u001B[1;32m 369\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m step, iterator \u001B[38;5;129;01min\u001B[39;00m epoch_iterator:\n\u001B[1;32m 370\u001B[0m callbacks\u001B[38;5;241m.\u001B[39mon_train_batch_begin(step)\n\u001B[0;32m--> 371\u001B[0m logs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtrain_function\u001B[49m\u001B[43m(\u001B[49m\u001B[43miterator\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 372\u001B[0m callbacks\u001B[38;5;241m.\u001B[39mon_train_batch_end(step, logs)\n\u001B[1;32m 373\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mstop_training:\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/keras/src/backend/tensorflow/trainer.py:219\u001B[0m, in \u001B[0;36mTensorFlowTrainer._make_function.<locals>.function\u001B[0;34m(iterator)\u001B[0m\n\u001B[1;32m 215\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;21mfunction\u001B[39m(iterator):\n\u001B[1;32m 216\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(\n\u001B[1;32m 217\u001B[0m iterator, (tf\u001B[38;5;241m.\u001B[39mdata\u001B[38;5;241m.\u001B[39mIterator, tf\u001B[38;5;241m.\u001B[39mdistribute\u001B[38;5;241m.\u001B[39mDistributedIterator)\n\u001B[1;32m 218\u001B[0m ):\n\u001B[0;32m--> 219\u001B[0m opt_outputs \u001B[38;5;241m=\u001B[39m \u001B[43mmulti_step_on_iterator\u001B[49m\u001B[43m(\u001B[49m\u001B[43miterator\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 220\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m opt_outputs\u001B[38;5;241m.\u001B[39mhas_value():\n\u001B[1;32m 221\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mStopIteration\u001B[39;00m\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/util/traceback_utils.py:150\u001B[0m, in \u001B[0;36mfilter_traceback.<locals>.error_handler\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m 148\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[1;32m 149\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[0;32m--> 150\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfn\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 151\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m 152\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m _process_traceback_frames(e\u001B[38;5;241m.\u001B[39m__traceback__)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:833\u001B[0m, in \u001B[0;36mFunction.__call__\u001B[0;34m(self, *args, **kwds)\u001B[0m\n\u001B[1;32m 830\u001B[0m compiler \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mxla\u001B[39m\u001B[38;5;124m\"\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_jit_compile \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mnonXla\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m 832\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m OptionalXlaContext(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_jit_compile):\n\u001B[0;32m--> 833\u001B[0m result \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwds\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 835\u001B[0m new_tracing_count \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mexperimental_get_tracing_count()\n\u001B[1;32m 836\u001B[0m without_tracing \u001B[38;5;241m=\u001B[39m (tracing_count \u001B[38;5;241m==\u001B[39m new_tracing_count)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:878\u001B[0m, in \u001B[0;36mFunction._call\u001B[0;34m(self, *args, **kwds)\u001B[0m\n\u001B[1;32m 875\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_lock\u001B[38;5;241m.\u001B[39mrelease()\n\u001B[1;32m 876\u001B[0m \u001B[38;5;66;03m# In this case we have not created variables on the first call. So we can\u001B[39;00m\n\u001B[1;32m 877\u001B[0m \u001B[38;5;66;03m# run the first trace but we should fail if variables are created.\u001B[39;00m\n\u001B[0;32m--> 878\u001B[0m results \u001B[38;5;241m=\u001B[39m \u001B[43mtracing_compilation\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_function\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 879\u001B[0m \u001B[43m \u001B[49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mkwds\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_variable_creation_config\u001B[49m\n\u001B[1;32m 880\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 881\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_created_variables:\n\u001B[1;32m 882\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mValueError\u001B[39;00m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mCreating variables on a non-first call to a function\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m 883\u001B[0m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m decorated with tf.function.\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/tracing_compilation.py:139\u001B[0m, in \u001B[0;36mcall_function\u001B[0;34m(args, kwargs, tracing_options)\u001B[0m\n\u001B[1;32m 137\u001B[0m bound_args \u001B[38;5;241m=\u001B[39m function\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39mbind(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n\u001B[1;32m 138\u001B[0m flat_inputs \u001B[38;5;241m=\u001B[39m function\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39munpack_inputs(bound_args)\n\u001B[0;32m--> 139\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfunction\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call_flat\u001B[49m\u001B[43m(\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;66;43;03m# pylint: disable=protected-access\u001B[39;49;00m\n\u001B[1;32m 140\u001B[0m \u001B[43m \u001B[49m\u001B[43mflat_inputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcaptured_inputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mfunction\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcaptured_inputs\u001B[49m\n\u001B[1;32m 141\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/concrete_function.py:1322\u001B[0m, in \u001B[0;36mConcreteFunction._call_flat\u001B[0;34m(self, tensor_inputs, captured_inputs)\u001B[0m\n\u001B[1;32m 1318\u001B[0m possible_gradient_type \u001B[38;5;241m=\u001B[39m gradients_util\u001B[38;5;241m.\u001B[39mPossibleTapeGradientTypes(args)\n\u001B[1;32m 1319\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m (possible_gradient_type \u001B[38;5;241m==\u001B[39m gradients_util\u001B[38;5;241m.\u001B[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001B[1;32m 1320\u001B[0m \u001B[38;5;129;01mand\u001B[39;00m executing_eagerly):\n\u001B[1;32m 1321\u001B[0m \u001B[38;5;66;03m# No tape is watching; skip to running the function.\u001B[39;00m\n\u001B[0;32m-> 1322\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_inference_function\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_preflattened\u001B[49m\u001B[43m(\u001B[49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 1323\u001B[0m forward_backward \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_select_forward_and_backward_functions(\n\u001B[1;32m 1324\u001B[0m args,\n\u001B[1;32m 1325\u001B[0m possible_gradient_type,\n\u001B[1;32m 1326\u001B[0m executing_eagerly)\n\u001B[1;32m 1327\u001B[0m forward_function, args_with_tangents \u001B[38;5;241m=\u001B[39m forward_backward\u001B[38;5;241m.\u001B[39mforward()\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:216\u001B[0m, in \u001B[0;36mAtomicFunction.call_preflattened\u001B[0;34m(self, args)\u001B[0m\n\u001B[1;32m 214\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;21mcall_preflattened\u001B[39m(\u001B[38;5;28mself\u001B[39m, args: Sequence[core\u001B[38;5;241m.\u001B[39mTensor]) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Any:\n\u001B[1;32m 215\u001B[0m \u001B[38;5;250m \u001B[39m\u001B[38;5;124;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001B[39;00m\n\u001B[0;32m--> 216\u001B[0m flat_outputs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_flat\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 217\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39mpack_output(flat_outputs)\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:251\u001B[0m, in \u001B[0;36mAtomicFunction.call_flat\u001B[0;34m(self, *args)\u001B[0m\n\u001B[1;32m 249\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m record\u001B[38;5;241m.\u001B[39mstop_recording():\n\u001B[1;32m 250\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_bound_context\u001B[38;5;241m.\u001B[39mexecuting_eagerly():\n\u001B[0;32m--> 251\u001B[0m outputs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_bound_context\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_function\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 252\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mname\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 253\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;28;43mlist\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 254\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;28;43mlen\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunction_type\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mflat_outputs\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 255\u001B[0m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 256\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m 257\u001B[0m outputs \u001B[38;5;241m=\u001B[39m make_call_op_in_graph(\n\u001B[1;32m 258\u001B[0m \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m 259\u001B[0m \u001B[38;5;28mlist\u001B[39m(args),\n\u001B[1;32m 260\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_bound_context\u001B[38;5;241m.\u001B[39mfunction_call_options\u001B[38;5;241m.\u001B[39mas_attrs(),\n\u001B[1;32m 261\u001B[0m )\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/context.py:1500\u001B[0m, in \u001B[0;36mContext.call_function\u001B[0;34m(self, name, tensor_inputs, num_outputs)\u001B[0m\n\u001B[1;32m 1498\u001B[0m cancellation_context \u001B[38;5;241m=\u001B[39m cancellation\u001B[38;5;241m.\u001B[39mcontext()\n\u001B[1;32m 1499\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m cancellation_context \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1500\u001B[0m outputs \u001B[38;5;241m=\u001B[39m \u001B[43mexecute\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 1501\u001B[0m \u001B[43m \u001B[49m\u001B[43mname\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mdecode\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mutf-8\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 1502\u001B[0m \u001B[43m \u001B[49m\u001B[43mnum_outputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mnum_outputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 1503\u001B[0m \u001B[43m \u001B[49m\u001B[43minputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mtensor_inputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 1504\u001B[0m \u001B[43m \u001B[49m\u001B[43mattrs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mattrs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 1505\u001B[0m \u001B[43m \u001B[49m\u001B[43mctx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 1506\u001B[0m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 1507\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m 1508\u001B[0m outputs \u001B[38;5;241m=\u001B[39m execute\u001B[38;5;241m.\u001B[39mexecute_with_cancellation(\n\u001B[1;32m 1509\u001B[0m name\u001B[38;5;241m.\u001B[39mdecode(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mutf-8\u001B[39m\u001B[38;5;124m\"\u001B[39m),\n\u001B[1;32m 1510\u001B[0m num_outputs\u001B[38;5;241m=\u001B[39mnum_outputs,\n\u001B[0;32m (...)\u001B[0m\n\u001B[1;32m 1514\u001B[0m cancellation_manager\u001B[38;5;241m=\u001B[39mcancellation_context,\n\u001B[1;32m 1515\u001B[0m )\n",
"File \u001B[0;32m~/mambaforge/envs/ail/lib/python3.10/site-packages/tensorflow/python/eager/execute.py:53\u001B[0m, in \u001B[0;36mquick_execute\u001B[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001B[0m\n\u001B[1;32m 51\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m 52\u001B[0m ctx\u001B[38;5;241m.\u001B[39mensure_initialized()\n\u001B[0;32m---> 53\u001B[0m tensors \u001B[38;5;241m=\u001B[39m \u001B[43mpywrap_tfe\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mTFE_Py_Execute\u001B[49m\u001B[43m(\u001B[49m\u001B[43mctx\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_handle\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdevice_name\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mop_name\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 54\u001B[0m \u001B[43m \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mattrs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum_outputs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 55\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m core\u001B[38;5;241m.\u001B[39m_NotOkStatusException \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m 56\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m name \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n",
"\u001B[0;31mKeyboardInterrupt\u001B[0m: "
]
}
],
"execution_count": 2
}
],
"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
}

54
plt/lenet-5.py Normal file
View File

@@ -0,0 +1,54 @@
from graphviz import Digraph
# 创建有向图
dot = Digraph(comment='LeNet-5', format='png',
graph_attr={'rankdir': 'LR', 'splines': 'line', 'nodesep': '0.5'})
# 定义节点样式
input_style = {'shape': 'box', 'style': 'filled', 'fillcolor': 'lightblue'}
conv_style = {'shape': 'box', 'style': 'filled', 'fillcolor': 'lightgreen'}
pool_style = {'shape': 'box', 'style': 'filled', 'fillcolor': 'lightcoral'}
fc_style = {'shape': 'box', 'style': 'filled', 'fillcolor': 'lightyellow'}
output_style = {'shape': 'box', 'style': 'filled', 'fillcolor': 'lightpink'}
# 添加节点，包含更多详细信息
dot.node('input', 'Input\n32x32x1\nGrayscale', **input_style)
dot.node('C1', 'Conv1\n5x5 kernel\n6 filters\nStride=1\n28x28x6', **conv_style)
dot.node('S2', 'Pool1\n2x2 kernel\nStride=2\n14x14x6', **pool_style)
dot.node('C3', 'Conv2\n5x5 kernel\n16 filters\nStride=1\n10x10x16', **conv_style)
dot.node('S4', 'Pool2\n2x2 kernel\nStride=2\n5x5x16', **pool_style)
dot.node('C5', 'FC1\n120 neurons', **fc_style)
dot.node('F6', 'FC2\n84 neurons', **fc_style)
dot.node('output', 'Output\n10 classes\n(Softmax)', **output_style)
# 添加边，带箭头
dot.edge('input', 'C1', label='Conv')
dot.edge('C1', 'S2', label='MaxPool')
dot.edge('S2', 'C3', label='Conv')
dot.edge('C3', 'S4', label='MaxPool')
dot.edge('S4', 'C5', label='Flatten\n+ FC')
dot.edge('C5', 'F6', label='FC')
dot.edge('F6', 'output', label='Softmax')
# 修改层数标注的显示方式
with dot.subgraph() as s:
s.attr(rank='same')
s.node('L1', 'Layer 1', shape='plaintext', pos='0,0!')
s.node('L2', 'Layer 2', shape='plaintext', pos='1,0!')
s.node('L3', 'Layer 3', shape='plaintext', pos='2,0!')
s.node('L4', 'Layer 4', shape='plaintext', pos='3,0!')
s.node('L5', 'Layer 5', shape='plaintext', pos='4,0!')
s.node('L6', 'Layer 6', shape='plaintext', pos='5,0!')
s.node('L7', 'Layer 7', shape='plaintext', pos='6,0!')
# 添加层数标注与模型结构的连接
dot.edge('L1', 'C1', style='invis')
dot.edge('L2', 'S2', style='invis')
dot.edge('L3', 'C3', style='invis')
dot.edge('L4', 'S4', style='invis')
dot.edge('L5', 'C5', style='invis')
dot.edge('L6', 'F6', style='invis')
dot.edge('L7', 'output', style='invis')
# 保存并渲染图像
dot.render('plt/lenet-5', view=False, cleanup=True)

3
requirements.txt
View File

@@ -5,4 +5,5 @@ matplotlib
ipywidgets ipywidgets
jupyter jupyter
scikit-learn scikit-learn
mnist mnist
graphviz