overfit_and_underfit

ShadowEditor.AI/README.md

@@ -35,6 +35,7 @@ pip install tensorflow-gpu==2.0.0-rc0
 6. tensorflow/basic_text_classification.py: 评论文本分类，准确度：86.2%
 7. tensorflow/feature_columns.py: 对结构化数据进行分类，准确度：72.54%
 8. tensorflow/basic_regression.py: 线性回归
+9. tensorflow/overfit_and_underfit.py: 过拟合和欠拟合，准确度：99.99%
 
 ## 相关地址
 

ShadowEditor.AI/tensorflow/overfit_and_underfit.py

@@ -0,0 +1,151 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
+import tensorflow as tf
+from tensorflow import keras
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+print(tf.__version__)
+
+NUM_WORDS = 10000
+
+(train_data, train_labels), (test_data,
+                             test_labels) = keras.datasets.imdb.load_data(num_words=NUM_WORDS)
+
+
+def multi_hot_sequences(sequences, dimension):
+    # Create an all-zero matrix of shape (len(sequences), dimension)
+    results = np.zeros((len(sequences), dimension))
+    for i, word_indices in enumerate(sequences):
+        # set specific indices of results[i] to 1s
+        results[i, word_indices] = 1.0
+    return results
+
+
+train_data = multi_hot_sequences(train_data, dimension=NUM_WORDS)
+test_data = multi_hot_sequences(test_data, dimension=NUM_WORDS)
+
+plt.plot(train_data[0])
+
+baseline_model = keras.Sequential([
+    # `input_shape` is only required here so that `.summary` works.
+    keras.layers.Dense(16, activation='relu', input_shape=(NUM_WORDS,)),
+    keras.layers.Dense(16, activation='relu'),
+    keras.layers.Dense(1, activation='sigmoid')
+])
+
+baseline_model.compile(optimizer='adam',
+                       loss='binary_crossentropy',
+                       metrics=['accuracy', 'binary_crossentropy'])
+
+baseline_model.summary()
+
+baseline_history = baseline_model.fit(train_data,
+                                      train_labels,
+                                      epochs=20,
+                                      batch_size=512,
+                                      validation_data=(test_data, test_labels),
+                                      verbose=2)
+
+smaller_model = keras.Sequential([
+    keras.layers.Dense(4, activation='relu', input_shape=(NUM_WORDS,)),
+    keras.layers.Dense(4, activation='relu'),
+    keras.layers.Dense(1, activation='sigmoid')
+])
+
+smaller_model.compile(optimizer='adam',
+                      loss='binary_crossentropy',
+                      metrics=['accuracy', 'binary_crossentropy'])
+
+smaller_model.summary()
+
+smaller_history = smaller_model.fit(train_data,
+                                    train_labels,
+                                    epochs=20,
+                                    batch_size=512,
+                                    validation_data=(test_data, test_labels),
+                                    verbose=2)
+
+bigger_model = keras.models.Sequential([
+    keras.layers.Dense(512, activation='relu', input_shape=(NUM_WORDS,)),
+    keras.layers.Dense(512, activation='relu'),
+    keras.layers.Dense(1, activation='sigmoid')
+])
+
+bigger_model.compile(optimizer='adam',
+                     loss='binary_crossentropy',
+                     metrics=['accuracy', 'binary_crossentropy'])
+
+bigger_model.summary()
+
+bigger_history = bigger_model.fit(train_data, train_labels,
+                                  epochs=20,
+                                  batch_size=512,
+                                  validation_data=(test_data, test_labels),
+                                  verbose=2)
+
+
+def plot_history(histories, key='binary_crossentropy'):
+  plt.figure(figsize=(16, 10))
+
+  for name, history in histories:
+    val = plt.plot(history.epoch, history.history['val_'+key],
+                   '--', label=name.title()+' Val')
+    plt.plot(history.epoch, history.history[key], color=val[0].get_color(),
+             label=name.title()+' Train')
+
+  plt.xlabel('Epochs')
+  plt.ylabel(key.replace('_', ' ').title())
+  plt.legend()
+
+  plt.xlim([0, max(history.epoch)])
+
+
+plot_history([('baseline', baseline_history),
+              ('smaller', smaller_history),
+              ('bigger', bigger_history)])
+
+
+l2_model = keras.models.Sequential([
+    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),
+                       activation='relu', input_shape=(NUM_WORDS,)),
+    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),
+                       activation='relu'),
+    keras.layers.Dense(1, activation='sigmoid')
+])
+
+l2_model.compile(optimizer='adam',
+                 loss='binary_crossentropy',
+                 metrics=['accuracy', 'binary_crossentropy'])
+
+l2_model_history = l2_model.fit(train_data, train_labels,
+                                epochs=20,
+                                batch_size=512,
+                                validation_data=(test_data, test_labels),
+                                verbose=2)
+
+
+plot_history([('baseline', baseline_history),
+              ('l2', l2_model_history)])
+
+dpt_model = keras.models.Sequential([
+    keras.layers.Dense(16, activation='relu', input_shape=(NUM_WORDS,)),
+    keras.layers.Dropout(0.5),
+    keras.layers.Dense(16, activation='relu'),
+    keras.layers.Dropout(0.5),
+    keras.layers.Dense(1, activation='sigmoid')
+])
+
+dpt_model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  metrics=['accuracy', 'binary_crossentropy'])
+
+dpt_model_history = dpt_model.fit(train_data, train_labels,
+                                  epochs=20,
+                                  batch_size=512,
+                                  validation_data=(test_data, test_labels),
+                                  verbose=2)
+
+plot_history([('baseline', baseline_history),
+              ('dropout', dpt_model_history)])