Utilizing GPU fails with tensorflow and CUDA with process finished with exit code -1073740791 (0xC0000409)

Question

I try to use my GPU for the first time to run a model with Tensorflow it exits whenever training starts with message:

Epoch 1/15
2022-05-07 00:46:23.749793: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8303

Process finished with exit code -1073740791 (0xC0000409)

My setup:

GTX 1650

tensorflow 2.7.0

CUDA 11.5

cudNN 8.3.3

Python 3.8.0

Here is the model and the preprocessing:

model = tf.keras.models.Sequential([
        tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(150, 150, 3)),
        tf.keras.layers.MaxPooling2D(2, 2),
        tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(2,2),
        tf.keras.layers.Conv2D(64, (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='sigmoid')
    ])


model.compile(loss='binary_crossentropy',
              optimizer=RMSprop(learning_rate=0.001),
              metrics=['accuracy'])

from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale=1 / 255)
validation_datagen = ImageDataGenerator(rescale=1 / 255)

train_generator = train_datagen.flow_from_directory(
    './horse-or-human/',  # This is the source directory for training images
    target_size=(150, 150),  # All images will be resized to 150x150
    batch_size=128,
    # Since you used binary_crossentropy loss, you need binary labels
    class_mode='binary')

validation_generator = validation_datagen.flow_from_directory(
    './validation-horse-or-human/',  # This is the source directory for training images
    target_size=(150, 150),  # All images will be resized to 150x150
    batch_size=32,
    # Since you used binary_crossentropy loss, you need binary labels
    class_mode='binary')

history = model.fit(
    train_generator,
    steps_per_epoch=8,
    epochs=15,
    verbose=1,
    validation_data=validation_generator,
    validation_steps=8)