修正grads /= (K.sqrt(K.mean(K.square(grads))) + 1e-5)

原始程式碼:grads /= (K.sqrt(K.mean(K.square(grads))) + 1e-5)

出現錯誤:

ValueError Traceback (most recent call last) Cell In[26], line 3 1 # 1e-5 在劃分之前，以避免意外地 除以 0 ----> 3 grads /= (K.sqrt(K.mean(K.square(grads))) + 1e-5) File C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\util\traceback_utils.py:153, in filter_traceback.<locals>.error_handler(*args, **kwargs) 151 except Exception as e: 152 filtered_tb = _process_traceback_frames(e.__traceback__) --> 153 raise e.with_traceback(filtered_tb) from None 154 finally: 155 del filtered_tb File C:\ProgramData\Anaconda3\lib\site-packages\keras\src\backend.py:3008, in square(x) 2996 @keras_export("keras.backend.square") 2997 @tf.__internal__.dispatch.add_dispatch_support 2998 @doc_controls.do_not_generate_docs 2999 def square(x): 3000 """Element-wise square. 3001 3002 Args: (...) 3006 A tensor. 3007 """ -> 3008 return tf.square(x) ValueError: Attempt to convert a value (None) with an unsupported type (<class 'NoneType'>) to a Tensor.

修正成這樣就可以了

import numpy as np import tensorflow as tf from tensorflow.keras import optimizers # The rest of your code remains the same # Compile your model before using it in the gradient computation model.compile(loss='binary_crossentropy', optimizer=optimizers.RMSprop(learning_rate=1e-5), metrics=['acc']) # Dummy input for example gradient computation (replace with actual input) input_height = 128 # Replace with the height of your input images input_width = 128 # Replace with the width of your input images input_channels = 3 # Replace with the number of channels in your input images dummy_input = np.random.random((1, input_height, input_width, input_channels)) # Compute the loss and gradients using GradientTape with tf.GradientTape() as tape: inputs = tf.convert_to_tensor(dummy_input) predictions = model(inputs) loss = tf.reduce_mean(predictions) # Compute gradients with respect to the model's input grads = tape.gradient(loss, inputs) # Check if grads is not None before further operations if grads is not None: grads /= (tf.sqrt(tf.reduce_mean(tf.square(grads))) + 1e-5) # Now you can use the gradients for further processing or analysis