[==============================] - 77s 968ms/step - loss: 4.5983 - accuracy: 0.3833 - val_loss: 1.8394 - val_accuracy: 0.6833 Epoch 2/100 43/43 [==============================] - 21s 493ms/step - loss: 0.1100 - accuracy: [==============================] - 21s 497ms/step - loss: 2.1797e-07 - accuracy: 1.0000 - val_loss: 1.9971 - val_accuracy: 0.7000 Epoch 99/100 43/43 [==============================] - 21s 496ms/step - loss: 1.9424e-07 val_loss: 1.9958 - val_accuracy: 0.7010 Epoch 100/100 43/43 [==============================] - 21s 497ms/step - loss: 1.6654e-07 - accuracy: 1.0000 - val_loss: 1.9950 - val_accuracy: 0.7010 Figure 3-8 shows

[==============================] - 5s 13ms/step - loss: 0.8423 - accuracy: 0.7685 - val_loss: 0.2341 - val_accuracy: 0.9361 Epoch 2/10 313/313 [==============================] - 3s 11ms/step - loss: 0.1382 - accuracy: [==============================] - 3s 11ms/step - loss: 0.0662 - accuracy: 0.9823 - val_loss: 0.1757 - val_accuracy: 0.9516 Epoch 4/10 313/313 [==============================] - 3s 11ms/step - loss: 0.0343 - accuracy: [==============================] - 3s 11ms/step - loss: 0.0211 - accuracy: 0.9944 - val_loss: 0.1833 - val_accuracy: 0.9561 Epoch 6/10 313/313 [==============================] - 3s 11ms/step - loss: 0.0120 - accuracy:

=] - 3s 6ms/step - loss: 0.1729 - sparse_categorical_accuracy: 0.9500 - val_loss: 0.0753 - val_sparse_categorical_accuracy: 0.9789 Epoch 2/15 469/469 [==============================] - 2s 5ms/step - loss: =] - 2s 5ms/step - loss: 0.0412 - sparse_categorical_accuracy: 0.9873 - val_loss: 0.0486 - val_sparse_categorical_accuracy: 0.9837 Epoch 4/15 469/469 [==============================] - 2s 5ms/step - loss: =] - 3s 6ms/step - loss: 0.0279 - sparse_categorical_accuracy: 0.9916 - val_loss: 0.0368 - val_sparse_categorical_accuracy: 0.9887 Epoch 6/15 469/469 [==============================] - 3s 6ms/step - loss:

[==============================] - 84s 1ms/step - loss: 0.2687 - acc: 0.9173 - val_loss: 0.0549 - val_acc: 0.9827 Epoch 2/12 60000/60000 [==============================] - 86s 1ms/step - loss: 0.0899 - acc: 0 [==============================] - 83s 1ms/step - loss: 0.0666 - acc: 0.9804 - val_loss: 0.0362 - val_acc: 0.9879 Epoch 4/12 60000/60000 [==============================] - 81s 1ms/step - loss: 0.0564 - acc: 0 [==============================] - 86s 1ms/step - loss: 0.0472 - acc: 0.9861 - val_loss: 0.0312 - val_acc: 0.9901 Epoch 6/12 60000/60000 [==============================] - 83s 1ms/step - loss: 0.0414 - acc: 0

[==============================] - 34s 90ms/step - loss: 0.8422 - accuracy: 0.6502 - val_loss: 0.8573 - val_accuracy: 0.6633 Epoch 2/50 184/184 [==============================] - 10s 56ms/step - loss: 0.7534 - accuracy: 10s 57ms/step - loss: 0.6946 - accuracy: 0.7139 - val_loss: 0.7629 - val_accuracy: 0.6743 xxxxxxxxx Skip to 48th epoch xxxxxxxxx Epoch 48/50 184/184 [==============================] - 11s 59ms/step [==============================] - 10s 56ms/step - loss: 0.0910 - accuracy: 0.9561 - val_loss: 0.5369 - val_accuracy: 0.8473 Epoch 50/50 184/184 [==============================] - 11s 58ms/step - loss: 0.0819 - accuracy:

取 pd.read_sql() | 从 SQL 表 或 数 据 库 读 取 pd.read_json() | 从JSON格式的URL或文件读取 pd.read_clipboard() | 从剪切板读取 将DataFrame写入⽂件 df.to_csv() | 写入CSV文件 df.to_excel() | 写入Excel文件 df.to_sql() | 写入SQL表或数据库 df.to_json()

取 pd.read_sql() | 从 SQL 表 或 数 据 库 读 取 pd.read_json() | 从JSON格式的URL或文件读取 pd.read_clipboard() | 从剪切板读取 将DataFrame写入⽂件 df.to_csv() | 写入CSV文件 df.to_excel() | 写入Excel文件 df.to_sql() | 写入SQL表或数据库 df.to_json()

[==============================] - 51s 59ms/step - loss: 0.7432 - accuracy: 0.6898 - val_loss: 0.3910 - val_accuracy: 0.8642 Epoch 2/4 469/469 [==============================] - 16s 33ms/step - loss: 0.3552 - accuracy: [==============================] - 16s 34ms/step - loss: 0.2856 - accuracy: 0.9022 - val_loss: 0.2925 - val_accuracy: 0.9000 Epoch 4/4 469/469 [==============================] - 16s 33ms/step - loss: 0.2481 - accuracy: [==============================] - 41s 54ms/step - loss: 0.4249 - accuracy: 0.8590 - val_loss: 0.2892 - val_accuracy: 0.9021 Epoch 2/4 469/469 [==============================] - 16s 34ms/step - loss: 0.2663 - accuracy:

本页图片均来自公开摄像头 SACC2017 检测-人脸检测/人形检测 手机 服务器 可缩小尺寸 240P 720P CPU ARM（千元机） E5-2630 时间 50ms 120ms GPU 2-5ms(K40) SACC2017 图像技术的三个核心难点>>小、快、准 小模型 线上速度快 预测准 Frequent remote upgrade CPU-constrained

Office: N3-312-1 Education: 2010-2015, PhD, Nanyang Technological University, Singapore. 2007-2010, MS, Shandong University, China. 2003-2007, BS, Shandong Normal University, China. Employment: Sep 2022 (15%) + Final exam (50%) Website: https://funglee.github.io/ml/ml.html Teaching Assistants (TAs): Ms Lina Wang Mr Fangzheng Duan Feng Li (SDU) Overview September 6, 2023 4 / 57 Suggested Readings Hang