python and tensorflow version

[noushinha]

Can you please update the requirements.txt with specific versions of packages that work with this repository?
Also, I appreciate if you mention a working python 3 version. Is it python 3.7? python 3.12?
Which version of tensorflow-gpu?

Chapter 8, trying to train cvae-cnn code throws the following error which is obviously a version-related error

Model: "encoder"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                 ┃ Output Shape              ┃         Param # ┃ Connected to              ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ class_labels (InputLayer)    │ (None, 10)                │               0 │ -                         │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ dense (Dense)                │ (None, 784)               │           8,624 │ class_labels[0][0]        │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ encoder_input (InputLayer)   │ (None, 28, 28, 1)         │               0 │ -                         │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ reshape (Reshape)            │ (None, 28, 28, 1)         │               0 │ dense[0][0]               │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ concatenate (Concatenate)    │ (None, 28, 28, 2)         │               0 │ encoder_input[0][0],      │
│                              │                           │                 │ reshape[0][0]             │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ conv2d (Conv2D)              │ (None, 14, 14, 32)        │             608 │ concatenate[0][0]         │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ conv2d_1 (Conv2D)            │ (None, 7, 7, 64)          │          18,496 │ conv2d[0][0]              │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ flatten (Flatten)            │ (None, 3136)              │               0 │ conv2d_1[0][0]            │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ dense_1 (Dense)              │ (None, 16)                │          50,192 │ flatten[0][0]             │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ z_mean (Dense)               │ (None, 2)                 │              34 │ dense_1[0][0]             │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ z_log_var (Dense)            │ (None, 2)                 │              34 │ dense_1[0][0]             │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ z (Lambda)                   │ (None, 2)                 │               0 │ z_mean[0][0],             │
│                              │                           │                 │ z_log_var[0][0]           │
└──────────────────────────────┴───────────────────────────┴─────────────────┴───────────────────────────┘
 Total params: 77,988 (304.64 KB)
 Trainable params: 77,988 (304.64 KB)
 Non-trainable params: 0 (0.00 B)
Model: "decoder"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                 ┃ Output Shape              ┃         Param # ┃ Connected to              ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ z_sampling (InputLayer)      │ (None, 2)                 │               0 │ -                         │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ class_labels (InputLayer)    │ (None, 10)                │               0 │ -                         │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ concatenate_1 (Concatenate)  │ (None, 12)                │               0 │ z_sampling[0][0],         │
│                              │                           │                 │ class_labels[0][0]        │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ dense_2 (Dense)              │ (None, 3136)              │          40,768 │ concatenate_1[0][0]       │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ reshape_1 (Reshape)          │ (None, 7, 7, 64)          │               0 │ dense_2[0][0]             │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ conv2d_transpose             │ (None, 14, 14, 64)        │          36,928 │ reshape_1[0][0]           │
│ (Conv2DTranspose)            │                           │                 │                           │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ conv2d_transpose_1           │ (None, 28, 28, 32)        │          18,464 │ conv2d_transpose[0][0]    │
│ (Conv2DTranspose)            │                           │                 │                           │
├──────────────────────────────┼───────────────────────────┼─────────────────┼───────────────────────────┤
│ decoder_output               │ (None, 28, 28, 1)         │             289 │ conv2d_transpose_1[0][0]  │
│ (Conv2DTranspose)            │                           │                 │                           │
└──────────────────────────────┴───────────────────────────┴─────────────────┴───────────────────────────┘
 Total params: 96,449 (376.75 KB)
 Trainable params: 96,449 (376.75 KB)
 Non-trainable params: 0 (0.00 B)
CVAE
Traceback (most recent call last):
  File "/scratch/htc/nhajarol/Advanced-Deep-Learning-with-Keras-master/chapter8-vae/cvae-cnn-mnist-8.2.1.py", line 260, in <module>
    reconstruction_loss = mse(K.flatten(inputs), K.flatten(outputs))
                              ^^^^^^^^^^^^^^^^^
  File "/scratch/htc/nhajarol/miniconda3/envs/packt/lib/python3.11/site-packages/keras/src/legacy/backend.py", line 869, in flatten
    return tf.reshape(x, [-1])
           ^^^^^^^^^^^^^^^^^^^
  File "/scratch/htc/nhajarol/miniconda3/envs/packt/lib/python3.11/site-packages/tensorflow/python/ops/weak_tensor_ops.py", line 88, in wrapper
    return op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/scratch/htc/nhajarol/miniconda3/envs/packt/lib/python3.11/site-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/scratch/htc/nhajarol/miniconda3/envs/packt/lib/python3.11/site-packages/keras/src/backend/common/keras_tensor.py", line 194, in __tf_tensor__
    raise ValueError(
ValueError: A KerasTensor cannot be used as input to a TensorFlow function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces `keras.layers` and `keras.ops`). You are likely doing something like:

x = Input(...)
...
tf_fn(x) # Invalid.

What you should do instead is wrap `tf_fn` in a layer:

class MyLayer(Layer):
def call(self, x):
return tf_fn(x)

x = MyLayer()(x)