模型已经训练后的 TensorFlow 形状错误
TensorFlow Shape Error After Model is Already Trained
我正在使用 LSTM 层训练 TensorFlow RNN 模型，以确定声音在立体声音频信号中是更多地来自右侧还是左侧。模型训练进行得很顺利，然后，一旦完成训练，我就会得到一个无效参数错误，如下所示。有谁知道这可能是什么原因造成的？我尝试使用找到的类似问题的解决方案修复它 here，但无济于事。
我不明白为什么它需要形状为 [32,2] 的张量。我是否在我不知道的地方定义了它？
这是我的代码：
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 18 15:51:56 2022
@author: andre
"""
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras import layers
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint
from sklearn.model_selection import train_test_split
from datetime import datetime
from sklearn import metrics
from scipy.io import wavfile
import os
import glob
# Load in Right Side .WAV Data.
X1 = []
count1 = 0
database_path = "C:\Users\andre\OneDrive\Documents\ESI2022\MLDatabases\Right\"
for filename in glob.glob(os.path.join(database_path, '*.wav')):
X1.append(wavfile.read(filename)[1])
count1 = count1 + 1
# Load in Left side .WAV Data.
X2 = []
count2 = 0
database_path2 = "C:\Users\andre\OneDrive\Documents\ESI2022\MLDatabases\Right\"
for filename2 in glob.glob(os.path.join(database_path2, '*.wav')):
X2.append(wavfile.read(filename2)[1])
count2 = count2 + 1
# Get the smallest size audio file (this will be sample size input to model)
sample_size = len(X1[0])
for data in X1:
if len(data) < sample_size:
sample_size = len(data)
# Make audio data into equal size chunks
X1e = []
for i in X1:
num_chunks = len(i)//sample_size
for j in range(num_chunks):
X1e.append(i[(j+1)*sample_size-sample_size:(j+1)*sample_size])
X1 = X1e
X2e = []
for i in X2:
num_chunks = len(i)//sample_size
for j in range(num_chunks):
X2e.append(i[(j+1)*sample_size-sample_size:(j+1)*sample_size])
X2=X2e
del X1e
del X2e
# Create Output data that is the same length as the input data.
Y1 = np.ones([X1.__len__()],dtype='float32').tolist()
Y2 = np.zeros([X2.__len__()],dtype='float32').tolist()
# Concatenate Left and Right .WAV data and output data as numpy arrays.
X1.extend(X2)
X = np.asarray(X1)
Y = np.asarray(Y1+Y2).astype(np.int16)
Xnew=X[0:4900][:][:]
Ynew=Y[0:4900][:][:]
# Split data into test training data.
X_train,X_test,Y_train,Y_test=train_test_split(Xnew,Ynew,test_size=0.204,random_state=0,shuffle=True)
'''
print(X[1])
time = np.linspace(0.,33792, 33792)
plt.plot(time, X[1][:,1], label="Left channel")
plt.plot(time, X[1][:,0], label="Right channel")
plt.legend()
plt.xlabel("Time [s]")
plt.ylabel("Amplitude")
plt.show()
'''
# Create the Model
model = Sequential()
# Add a LSTM layer with 1 output, and ambiguous input data length.
model.add(layers.LSTM(2,batch_input_shape=(100,sample_size,2),return_sequences=True))
model.add(layers.LSTM(2,return_sequences=False))
# Compile Model
#history = model.compile(loss='mean_absolute_error', metrics=['accuracy'],optimizer='adam',output='sparse_categorical_crossentropy')
optimizer = Adam(learning_rate=2*1e-4)
history = model.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer="adam",
metrics=["accuracy"],
)
model.summary()
# Define Training Parameters
num_epochs = 5
num_batch_size = 100
# Save the most accurate model to file. (Verbosity Gives more information)
checkpointer = ModelCheckpoint(filepath="SavedModels/checkpointModel.hdf5", verbose=1,save_best_only=True)
# Start the timer
start = datetime.now()
# Train the model
model.fit(X_train,Y_train,batch_size=num_batch_size, epochs=num_epochs, validation_data=(X_test,Y_test), callbacks=[checkpointer],verbose=1)
# Get and Print Model Validation Accuracy
test_accuracy=model.evaluate(X_test,Y_test,verbose=0)
print(test_accuracy[1])
这里是完整的错误信息：
runfile('C:/Users/andre/OneDrive/Documents/ESI2022/PythonScripts/BeltML/testML.py', wdir='C:/Users/andre/OneDrive/Documents/ESI2022/PythonScripts/BeltML')
Model: "sequential_14"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_28 (LSTM) (100, 3072, 2) 40
lstm_29 (LSTM) (100, 2) 40
=================================================================
Total params: 80
Trainable params: 80
Non-trainable params: 0
_________________________________________________________________
Epoch 1/5
39/39 [==============================] - ETA: 0s - loss: 0.7387 - accuracy: 0.4936
Epoch 00001: val_loss improved from inf to 0.71954, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 60s 1s/step - loss: 0.7387 - accuracy: 0.4936 - val_loss: 0.7195 - val_accuracy: 0.5100
Epoch 2/5
39/39 [==============================] - ETA: 0s - loss: 0.7217 - accuracy: 0.4995
Epoch 00002: val_loss improved from 0.71954 to 0.70838, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7217 - accuracy: 0.4995 - val_loss: 0.7084 - val_accuracy: 0.5090
Epoch 3/5
39/39 [==============================] - ETA: 0s - loss: 0.7105 - accuracy: 0.4990
Epoch 00003: val_loss improved from 0.70838 to 0.70385, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7105 - accuracy: 0.4990 - val_loss: 0.7038 - val_accuracy: 0.5070
Epoch 4/5
39/39 [==============================] - ETA: 0s - loss: 0.7043 - accuracy: 0.4995
Epoch 00004: val_loss improved from 0.70385 to 0.70144, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7043 - accuracy: 0.4995 - val_loss: 0.7014 - val_accuracy: 0.5070
Epoch 5/5
39/39 [==============================] - ETA: 0s - loss: 0.7010 - accuracy: 0.5018
Epoch 00005: val_loss improved from 0.70144 to 0.69969, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7010 - accuracy: 0.5018 - val_loss: 0.6997 - val_accuracy: 0.5130
Traceback (most recent call last):
File "C:\Users\andre\OneDrive\Documents\ESI2022\PythonScripts\BeltML\testML.py", line 124, in <module>
test_accuracy=model.evaluate(X_test,Y_test,verbose=0)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\execute.py", line 58, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
InvalidArgumentError: Specified a list with shape [100,2] from a tensor with shape [32,2]
[[{{node TensorArrayUnstack/TensorListFromTensor}}]]
[[sequential_14/lstm_28/PartitionedCall]] [Op:__inference_test_function_121112]
Function call stack:
test_function -> test_function -> test_function
你得到这个错误是因为你 hard-coded 第一个 LSTM 层的批量大小和数据样本的数量不能被 100 整除。你必须以某种方式处理余数.我建议从第一层中删除批量大小，只在 model.fit 中输入批量大小。这样您的模型将能够处理剩余的较小批次。这是一个例子：
X_train = tf.random.normal((2632, 5, 2))
Y_train = tf.random.uniform((2632, 1), maxval=2, dtype=tf.int32)
model = Sequential()
model.add(layers.LSTM(2,input_shape=(5,2),return_sequences=True))
model.add(layers.LSTM(2,return_sequences=False))
optimizer = Adam(learning_rate=2*1e-4)
history = model.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer="adam",
metrics=["accuracy"],
)
model.summary()
num_epochs = 5
num_batch_size = 100
checkpointer = ModelCheckpoint(filepath="SavedModels/checkpointModel.hdf5", verbose=1,save_best_only=True)
start = datetime.now()
num_epochs = 5
num_batch_size = 100
model.fit(X_train,Y_train,batch_size=num_batch_size, epochs=num_epochs , callbacks=[checkpointer],verbose=1)
此外，您链接到的 post 实际上应该对您有所帮助。
我正在使用 LSTM 层训练 TensorFlow RNN 模型，以确定声音在立体声音频信号中是更多地来自右侧还是左侧。模型训练进行得很顺利，然后，一旦完成训练，我就会得到一个无效参数错误，如下所示。有谁知道这可能是什么原因造成的？我尝试使用找到的类似问题的解决方案修复它 here，但无济于事。
我不明白为什么它需要形状为 [32,2] 的张量。我是否在我不知道的地方定义了它？
这是我的代码：
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 18 15:51:56 2022
@author: andre
"""
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras import layers
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint
from sklearn.model_selection import train_test_split
from datetime import datetime
from sklearn import metrics
from scipy.io import wavfile
import os
import glob
# Load in Right Side .WAV Data.
X1 = []
count1 = 0
database_path = "C:\Users\andre\OneDrive\Documents\ESI2022\MLDatabases\Right\"
for filename in glob.glob(os.path.join(database_path, '*.wav')):
X1.append(wavfile.read(filename)[1])
count1 = count1 + 1
# Load in Left side .WAV Data.
X2 = []
count2 = 0
database_path2 = "C:\Users\andre\OneDrive\Documents\ESI2022\MLDatabases\Right\"
for filename2 in glob.glob(os.path.join(database_path2, '*.wav')):
X2.append(wavfile.read(filename2)[1])
count2 = count2 + 1
# Get the smallest size audio file (this will be sample size input to model)
sample_size = len(X1[0])
for data in X1:
if len(data) < sample_size:
sample_size = len(data)
# Make audio data into equal size chunks
X1e = []
for i in X1:
num_chunks = len(i)//sample_size
for j in range(num_chunks):
X1e.append(i[(j+1)*sample_size-sample_size:(j+1)*sample_size])
X1 = X1e
X2e = []
for i in X2:
num_chunks = len(i)//sample_size
for j in range(num_chunks):
X2e.append(i[(j+1)*sample_size-sample_size:(j+1)*sample_size])
X2=X2e
del X1e
del X2e
# Create Output data that is the same length as the input data.
Y1 = np.ones([X1.__len__()],dtype='float32').tolist()
Y2 = np.zeros([X2.__len__()],dtype='float32').tolist()
# Concatenate Left and Right .WAV data and output data as numpy arrays.
X1.extend(X2)
X = np.asarray(X1)
Y = np.asarray(Y1+Y2).astype(np.int16)
Xnew=X[0:4900][:][:]
Ynew=Y[0:4900][:][:]
# Split data into test training data.
X_train,X_test,Y_train,Y_test=train_test_split(Xnew,Ynew,test_size=0.204,random_state=0,shuffle=True)
'''
print(X[1])
time = np.linspace(0.,33792, 33792)
plt.plot(time, X[1][:,1], label="Left channel")
plt.plot(time, X[1][:,0], label="Right channel")
plt.legend()
plt.xlabel("Time [s]")
plt.ylabel("Amplitude")
plt.show()
'''
# Create the Model
model = Sequential()
# Add a LSTM layer with 1 output, and ambiguous input data length.
model.add(layers.LSTM(2,batch_input_shape=(100,sample_size,2),return_sequences=True))
model.add(layers.LSTM(2,return_sequences=False))
# Compile Model
#history = model.compile(loss='mean_absolute_error', metrics=['accuracy'],optimizer='adam',output='sparse_categorical_crossentropy')
optimizer = Adam(learning_rate=2*1e-4)
history = model.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer="adam",
metrics=["accuracy"],
)
model.summary()
# Define Training Parameters
num_epochs = 5
num_batch_size = 100
# Save the most accurate model to file. (Verbosity Gives more information)
checkpointer = ModelCheckpoint(filepath="SavedModels/checkpointModel.hdf5", verbose=1,save_best_only=True)
# Start the timer
start = datetime.now()
# Train the model
model.fit(X_train,Y_train,batch_size=num_batch_size, epochs=num_epochs, validation_data=(X_test,Y_test), callbacks=[checkpointer],verbose=1)
# Get and Print Model Validation Accuracy
test_accuracy=model.evaluate(X_test,Y_test,verbose=0)
print(test_accuracy[1])
这里是完整的错误信息：
runfile('C:/Users/andre/OneDrive/Documents/ESI2022/PythonScripts/BeltML/testML.py', wdir='C:/Users/andre/OneDrive/Documents/ESI2022/PythonScripts/BeltML')
Model: "sequential_14"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_28 (LSTM) (100, 3072, 2) 40
lstm_29 (LSTM) (100, 2) 40
=================================================================
Total params: 80
Trainable params: 80
Non-trainable params: 0
_________________________________________________________________
Epoch 1/5
39/39 [==============================] - ETA: 0s - loss: 0.7387 - accuracy: 0.4936
Epoch 00001: val_loss improved from inf to 0.71954, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 60s 1s/step - loss: 0.7387 - accuracy: 0.4936 - val_loss: 0.7195 - val_accuracy: 0.5100
Epoch 2/5
39/39 [==============================] - ETA: 0s - loss: 0.7217 - accuracy: 0.4995
Epoch 00002: val_loss improved from 0.71954 to 0.70838, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7217 - accuracy: 0.4995 - val_loss: 0.7084 - val_accuracy: 0.5090
Epoch 3/5
39/39 [==============================] - ETA: 0s - loss: 0.7105 - accuracy: 0.4990
Epoch 00003: val_loss improved from 0.70838 to 0.70385, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7105 - accuracy: 0.4990 - val_loss: 0.7038 - val_accuracy: 0.5070
Epoch 4/5
39/39 [==============================] - ETA: 0s - loss: 0.7043 - accuracy: 0.4995
Epoch 00004: val_loss improved from 0.70385 to 0.70144, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7043 - accuracy: 0.4995 - val_loss: 0.7014 - val_accuracy: 0.5070
Epoch 5/5
39/39 [==============================] - ETA: 0s - loss: 0.7010 - accuracy: 0.5018
Epoch 00005: val_loss improved from 0.70144 to 0.69969, saving model to SavedModels\checkpointModel.hdf5
39/39 [==============================] - 57s 1s/step - loss: 0.7010 - accuracy: 0.5018 - val_loss: 0.6997 - val_accuracy: 0.5130
Traceback (most recent call last):
File "C:\Users\andre\OneDrive\Documents\ESI2022\PythonScripts\BeltML\testML.py", line 124, in <module>
test_accuracy=model.evaluate(X_test,Y_test,verbose=0)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\execute.py", line 58, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
InvalidArgumentError: Specified a list with shape [100,2] from a tensor with shape [32,2]
[[{{node TensorArrayUnstack/TensorListFromTensor}}]]
[[sequential_14/lstm_28/PartitionedCall]] [Op:__inference_test_function_121112]
Function call stack:
test_function -> test_function -> test_function
你得到这个错误是因为你 hard-coded 第一个 LSTM 层的批量大小和数据样本的数量不能被 100 整除。你必须以某种方式处理余数.我建议从第一层中删除批量大小，只在 model.fit 中输入批量大小。这样您的模型将能够处理剩余的较小批次。这是一个例子：
X_train = tf.random.normal((2632, 5, 2))
Y_train = tf.random.uniform((2632, 1), maxval=2, dtype=tf.int32)
model = Sequential()
model.add(layers.LSTM(2,input_shape=(5,2),return_sequences=True))
model.add(layers.LSTM(2,return_sequences=False))
optimizer = Adam(learning_rate=2*1e-4)
history = model.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer="adam",
metrics=["accuracy"],
)
model.summary()
num_epochs = 5
num_batch_size = 100
checkpointer = ModelCheckpoint(filepath="SavedModels/checkpointModel.hdf5", verbose=1,save_best_only=True)
start = datetime.now()
num_epochs = 5
num_batch_size = 100
model.fit(X_train,Y_train,batch_size=num_batch_size, epochs=num_epochs , callbacks=[checkpointer],verbose=1)
此外，您链接到的 post 实际上应该对您有所帮助。