how to fix Tensorflow InvalidArgumentError

Question

this is my model

model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Conv2D(256, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(1, activation='softmax') )

Model fit:

testing = model.fit(
  train_generator,
  steps_per_epoch=25,
  epochs=20,
  validation_data=validation_generator,
  validation_steps=5,
  verbose=1)

The error:

InvalidArgumentError:  Matrix size-incompatible: In[0]: [32,3], In[1]: [512,1]
     [[node gradient_tape/sequential/dense_1/MatMul (defined at <ipython-input-11-34d2a6f3254c>:7) ]] [Op:__inference_train_function_935]


Function call stack:
train_function

my training shape is 1312 images

i couldnt find the error Anyone could help me explain how to fix it?

Answer 1

Patch size is incorrect. Please go with the below discussion.

https://github.com/tensorlayer/srgan/issues/152