How to load a saved model with keras? (Error : : TypeError: __init__() got an unexpected keyword argument 'trainable')
How to load a saved model with keras? (Error : : TypeError: __init__() got an unexpected keyword argument 'trainable')
我根据 Keras 代码示例中提供的内容创建了一个验证码模型。
但是当我加载模型时，会弹出一个错误。
我给你看我在 Jupyter notebook 上写的代码。
第 1 步）模型构建
class CTCLayer(layers.Layer):
def __init__(self, name=None):
super().__init__(name=name)
self.loss_fn = keras.backend.ctc_batch_cost
def call(self, y_true, y_pred):
# Compute the training-time loss value and add it
# to the layer using `self.add_loss()`.
batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")
input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")
loss = self.loss_fn(y_true, y_pred, input_length, label_length)
self.add_loss(loss)
# At test time, just return the computed predictions
return y_pred
def build_model():
# Inputs to the model
input_img = layers.Input(
shape=(img_width, img_height, 1), name="image", dtype="float32"
)
labels = layers.Input(name="label", shape=(None,), dtype="float32")
# First conv block
x = layers.Conv2D(
32,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv1",
)(input_img)
x = layers.MaxPooling2D((2, 2), name="pool1")(x)
# Second conv block
x = layers.Conv2D(
64,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv2",
)(x)
x = layers.MaxPooling2D((2, 2), name="pool2")(x)
# We have used two max pool with pool size and strides 2.
# Hence, downsampled feature maps are 4x smaller. The number of
# filters in the last layer is 64. Reshape accordingly before
# passing the output to the RNN part of the model
new_shape = ((img_width // 4), (img_height // 4) * 64)
x = layers.Reshape(target_shape=new_shape, name="reshape")(x)
x = layers.Dense(64, activation="relu", name="dense1")(x)
x = layers.Dropout(0.2)(x)
# RNNs
x = layers.Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)
# Output layer
x = layers.Dense(
len(char_to_num.get_vocabulary()) + 1, activation="softmax", name="dense2"
)(x)
# Add CTC layer for calculating CTC loss at each step
output = CTCLayer(name="ctc_loss")(labels, x)
# Define the model
model = keras.models.Model(
inputs=[input_img, labels], outputs=output, name="ocr_model_v1"
)
# Optimizer
opt = keras.optimizers.Adam()
# Compile the model and return
model.compile(optimizer=opt)
return model
# Get the model
model = build_model()
model.summary()
STEP2) 训练模型
epochs = 100
early_stopping_patience = 10
# Add early stopping
early_stopping = keras.callbacks.EarlyStopping(
monitor="val_loss", patience=early_stopping_patience, restore_best_weights=True
)
# Train the model
history = model.fit(
train_dataset,
validation_data=validation_dataset,
epochs=epochs,
callbacks=[early_stopping],
)
第 3 步）检查预测
# Get the prediction model by extracting layers till the output layer
prediction_model = keras.models.Model(
model.get_layer(name="image").input, model.get_layer(name="dense2").output
)
prediction_model.summary()
# A utility function to decode the output of the network
def decode_batch_predictions(pred):
input_len = np.ones(pred.shape[0]) * pred.shape[1]
# Use greedy search. For complex tasks, you can use beam search
results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0][
:, :max_length
]
# Iterate over the results and get back the text
output_text = []
for res in results:
res = tf.strings.reduce_join(num_to_char(res)).numpy().decode("utf-8")
output_text.append(res)
return output_text
# Let's check results on some validation samples
for batch in validation_dataset.take(1):
batch_images = batch["image"]
batch_labels = batch["label"]
preds = prediction_model.predict(batch_images)
pred_texts = decode_batch_predictions(preds)
orig_texts = []
for label in batch_labels:
label = tf.strings.reduce_join(num_to_char(label)).numpy().decode("utf-8")
orig_texts.append(label)
_, ax = plt.subplots(4, 4, figsize=(15, 8))
for i in range(len(pred_texts)):
img = (batch_images[i, :, :, 0] * 255).numpy().astype(np.uint8)
img = img.T
title = f"Prediction: {pred_texts[i]}"
ax[i // 4, i % 4].imshow(img, cmap="gray")
ax[i // 4, i % 4].set_title(title)
ax[i // 4, i % 4].axis("off")
plt.show()
第 4 步）保存模型
model.save("ocr_model.h5")
第 5 步）加载模型
model = load_model('./ocr_model.h5',custom_objects={'CTCLayer':CTCLayer})
我收到以下错误消息。
TypeError: init() 得到了一个意外的关键字参数 'trainable'
我又试了一次这个代码。
model = load_model('./ocr_model.h5')
我收到以下错误消息。
ValueError：未知层：CTCLayer。请确保将此对象传递给 custom_objects 参数。有关详细信息，请参阅 https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object。
如何使用存储的模型？
根据这个线程：，
您应该更新 __init__ 以包含 **kwargs 来解决您的问题（奇怪的是，我在 TensorFlow 2.3.0 中使用了准确的模型+配置，但无法重现此问题（Ubuntu 18.04)
我根据 Keras 代码示例中提供的内容创建了一个验证码模型。 但是当我加载模型时，会弹出一个错误。
我给你看我在 Jupyter notebook 上写的代码。
第 1 步）模型构建
class CTCLayer(layers.Layer):
def __init__(self, name=None):
super().__init__(name=name)
self.loss_fn = keras.backend.ctc_batch_cost
def call(self, y_true, y_pred):
# Compute the training-time loss value and add it
# to the layer using `self.add_loss()`.
batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")
input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")
loss = self.loss_fn(y_true, y_pred, input_length, label_length)
self.add_loss(loss)
# At test time, just return the computed predictions
return y_pred
def build_model():
# Inputs to the model
input_img = layers.Input(
shape=(img_width, img_height, 1), name="image", dtype="float32"
)
labels = layers.Input(name="label", shape=(None,), dtype="float32")
# First conv block
x = layers.Conv2D(
32,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv1",
)(input_img)
x = layers.MaxPooling2D((2, 2), name="pool1")(x)
# Second conv block
x = layers.Conv2D(
64,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv2",
)(x)
x = layers.MaxPooling2D((2, 2), name="pool2")(x)
# We have used two max pool with pool size and strides 2.
# Hence, downsampled feature maps are 4x smaller. The number of
# filters in the last layer is 64. Reshape accordingly before
# passing the output to the RNN part of the model
new_shape = ((img_width // 4), (img_height // 4) * 64)
x = layers.Reshape(target_shape=new_shape, name="reshape")(x)
x = layers.Dense(64, activation="relu", name="dense1")(x)
x = layers.Dropout(0.2)(x)
# RNNs
x = layers.Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)
# Output layer
x = layers.Dense(
len(char_to_num.get_vocabulary()) + 1, activation="softmax", name="dense2"
)(x)
# Add CTC layer for calculating CTC loss at each step
output = CTCLayer(name="ctc_loss")(labels, x)
# Define the model
model = keras.models.Model(
inputs=[input_img, labels], outputs=output, name="ocr_model_v1"
)
# Optimizer
opt = keras.optimizers.Adam()
# Compile the model and return
model.compile(optimizer=opt)
return model
# Get the model
model = build_model()
model.summary()
STEP2) 训练模型
epochs = 100
early_stopping_patience = 10
# Add early stopping
early_stopping = keras.callbacks.EarlyStopping(
monitor="val_loss", patience=early_stopping_patience, restore_best_weights=True
)
# Train the model
history = model.fit(
train_dataset,
validation_data=validation_dataset,
epochs=epochs,
callbacks=[early_stopping],
)
第 3 步）检查预测
# Get the prediction model by extracting layers till the output layer
prediction_model = keras.models.Model(
model.get_layer(name="image").input, model.get_layer(name="dense2").output
)
prediction_model.summary()
# A utility function to decode the output of the network
def decode_batch_predictions(pred):
input_len = np.ones(pred.shape[0]) * pred.shape[1]
# Use greedy search. For complex tasks, you can use beam search
results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0][
:, :max_length
]
# Iterate over the results and get back the text
output_text = []
for res in results:
res = tf.strings.reduce_join(num_to_char(res)).numpy().decode("utf-8")
output_text.append(res)
return output_text
# Let's check results on some validation samples
for batch in validation_dataset.take(1):
batch_images = batch["image"]
batch_labels = batch["label"]
preds = prediction_model.predict(batch_images)
pred_texts = decode_batch_predictions(preds)
orig_texts = []
for label in batch_labels:
label = tf.strings.reduce_join(num_to_char(label)).numpy().decode("utf-8")
orig_texts.append(label)
_, ax = plt.subplots(4, 4, figsize=(15, 8))
for i in range(len(pred_texts)):
img = (batch_images[i, :, :, 0] * 255).numpy().astype(np.uint8)
img = img.T
title = f"Prediction: {pred_texts[i]}"
ax[i // 4, i % 4].imshow(img, cmap="gray")
ax[i // 4, i % 4].set_title(title)
ax[i // 4, i % 4].axis("off")
plt.show()
第 4 步）保存模型
model.save("ocr_model.h5")
第 5 步）加载模型
model = load_model('./ocr_model.h5',custom_objects={'CTCLayer':CTCLayer})
我收到以下错误消息。
TypeError: init() 得到了一个意外的关键字参数 'trainable'
我又试了一次这个代码。
model = load_model('./ocr_model.h5')
我收到以下错误消息。
ValueError：未知层：CTCLayer。请确保将此对象传递给 custom_objects 参数。有关详细信息，请参阅 https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object。
如何使用存储的模型？
根据这个线程：
您应该更新 __init__ 以包含 **kwargs 来解决您的问题（奇怪的是，我在 TensorFlow 2.3.0 中使用了准确的模型+配置，但无法重现此问题（Ubuntu 18.04)