“sequential_1 层的输入 0 与层不兼容”与 tf.data.Dataset

Question

I am getting

ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [300, 300, 3]. Model Summary shows 4 inputs but it says 3.

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import tensorflow_datasets as tfds
import logging
logger = tf.get_logger()
logger.setLevel(logging.ERROR)
from tensorflow.keras.preprocessing.image import ImageDataGenerator

(train_dataset, test_dataset), metadata = tfds.load('rock_paper_scissors',split=['train', 'test'], as_supervised=True, with_info=True)

class_names = ['rock','paper','scissors']

num_train_examples = metadata.splits['train'].num_examples
num_test_examples = metadata.splits['test'].num_examples
print("Number of training examples: {}".format(num_train_examples))
print("Number of test examples:     {}".format(num_test_examples))

get_label_name = metadata.features['label'].int2str
print(get_label_name(0))
print(get_label_name(1))
print(get_label_name(2))

def format_example(image, label):
    # Make image color values to be float.
    image = tf.cast(image, tf.float32)
    # Make image color values to be in [0..1] range.
    image = image / 255.
    return image, label

dataset_train = train_dataset.map(format_example)
dataset_test =test_dataset.map(format_example)

l1 = tf.keras.layers.Conv2D(32, (3,3), activation = 'relu', input_shape=(300,300,3))
l2 = tf.keras.layers.MaxPooling2D(2,2)

l3 = tf.keras.layers.Conv2D(64, (3,3), activation='relu')
l4 = tf.keras.layers.MaxPooling2D(2,2)

l5 = tf.keras.layers.Conv2D(128, (3,3), activation='relu')
l6 = tf.keras.layers.MaxPooling2D(2,2)

l7 = tf.keras.layers.Flatten()
l8 = tf.keras.layers.Dense(512, activation='relu')
l9 = tf.keras.layers.Dense(3, activation='softmax')

model = tf.keras.Sequential([l1,l2,l3,l4,l5,l6,l7,l8,l9])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy,
              metrics=['accuracy'])

model.summary()

epochs = 10
batch_size = 32

history = model.fit(
    dataset_train,
    validation_data = dataset_test,
    steps_per_epoch = int(np.ceil(num_train_examples/float(batch_size))),
    validation_steps = int(np.ceil(num_test_examples/float(batch_size))),
    epochs = epochs
)

Where am I going wrong? I have not encountered this error with cats and dogs dataset.

Answer 1

You need to batch your dataset in order to get the right shape:

dataset_train = train_dataset.map(format_example).batch(1)
dataset_test =test_dataset.map(format_example).batch(1)

When you don't batch,a picture with shape (h, w, c) will be returned. If you batch, you will get (n, h, w, c) , which is what Keras expects. Do the test yourself:

import tensorflow as tf

images = tf.random.uniform(shape=(10, 224, 224, 3), maxval=256, dtype=tf.int32)

ds = tf.data.Dataset.from_tensor_slices(images)

for pic in ds:
    print(pic.shape)
    break

(224, 224, 3)

With batching:

for pic in ds.batch(4):
    print(pic.shape)
    break

(4, 224, 224, 3)