Chapter 6: resizing notebook giving error:

[andysingal]

Hi,
I was running code:

import tensorflow_hub as hub
import os
# Load compressed models from tensorflow_hub
os.environ['TFHUB_MODEL_LOAD_FORMAT'] = 'COMPRESSED'

preproc_layers = tf.keras.Sequential([
    tf.keras.layers.Lambda(lambda img:
                           tf.image.resize_with_pad(
                               img, 2*IMG_HEIGHT, 2*IMG_WIDTH),
                           input_shape=(None, None, 3)),
    tf.keras.layers.experimental.preprocessing.CenterCrop(
        height=IMG_HEIGHT, width=IMG_WIDTH)
    ])

def apply_preproc(img, label):
    # add to a batch, call preproc, remove from batch
    x = tf.expand_dims(img, 0)
    x = preproc_layers(x)
    x = tf.squeeze(x, 0)
    return x, label

# parameterize to the values in the previous cell
def train_and_evaluate(batch_size = 32,
                       lrate = 0.001,
                       l1 = 0.,
                       l2 = 0.,
                       num_hidden = 16):
  regularizer = tf.keras.regularizers.l1_l2(l1, l2)

  train_dataset = tf.data.TFRecordDataset(
    [filename for filename in tf.io.gfile.glob(
        'gs://practical-ml-vision-book/flowers_tfr/train-*')
    ],
    compression_type='GZIP'
  ).map(parse_tfr).map(apply_preproc).batch(batch_size)

  eval_dataset = tf.data.TFRecordDataset(
    [filename for filename in tf.io.gfile.glob(
        'gs://practical-ml-vision-book/flowers_tfr/valid-*')
    ],
    compression_type='GZIP'
  ).map(parse_tfr).map(apply_preproc).batch(batch_size)

  layers = [
      hub.KerasLayer(
          "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4",
          input_shape=(IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS),
          trainable=False,
          name='mobilenet_embedding'),
      tf.keras.layers.Dense(num_hidden,
                            kernel_regularizer=regularizer, 
                            activation=tf.keras.activations.relu,
                            name='dense_hidden'),
      tf.keras.layers.Dense(len(CLASS_NAMES), 
                            kernel_regularizer=regularizer,
                            activation='softmax',
                            name='flower_prob')
  ]

  model = tf.keras.Sequential(layers, name='flower_classification')
  model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=lrate),
                loss=tf.keras.losses.SparseCategoricalCrossentropy(
                    from_logits=False),
                metrics=['accuracy'])
  print(model.summary())
  history = model.fit(train_dataset, validation_data=eval_dataset, epochs=10)
  training_plot(['loss', 'accuracy'], history)
  return model

and got the following error:

ValueError Traceback (most recent call last)
in <cell line: 1>()
----> 1 model = train_and_evaluate()

20 frames
/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def, extract_traceback)
1971 except errors.InvalidArgumentError as e:
1972 # Convert to ValueError for backwards compatibility.
-> 1973 raise ValueError(e.message)
1974
1975 # Record the current Python stack trace as the creating stacktrace of this

ValueError: in user code:

File "<ipython-input-29-30d7b53cf7ed>", line 19, in apply_preproc  *
    x = tf.squeeze(x, 0)

ValueError: Can not squeeze dim[0], expected a dimension of 1, got 224 for '{{node Squeeze}} = Squeeze[T=DT_FLOAT, squeeze_dims=[0]](sequential_5/center_crop_3/cond/Identity)' with input shapes: [224,224,?].

Even though the code is good in your book but contains several errors.

I hope you can assist in fixing the error.
Thanks,
Ankush Singal

[hariharan382]

hi can you say what notebook are you using?