My code runs fine but i get a ValueError "f'Output tensors of a {cls_name} model must be 'the output of a TensorFlow `Layer` '

Question

I am trying to build a DeepLabV3+ model from an article tutorial but I'm getting a ValueError related to the Tensorflow input and output. Please look through it and help me understand what I'm getting wrong. Thank you.

Here is the code:

import os
import cv2
import numpy as np
from glob import glob
from scipy.io import loadmat
import matplotlib.pyplot as plt

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

!gdown https://drive.google.com/uc?id=1B9A9UCJYMwTL4oBEo4RZfbMZMaZhKJaz
!unzip -q instance-level-human-parsing.zip

#Organizing the dataset

IMAGE_SIZE = 512
BATCH_SIZE = 4
NUM_CLASSES = 20
DATA_DIR = "./instance-level_human_parsing/instance-level_human_parsing/Training"
NUM_TRAIN_IMAGES = 1000
NUM_VAL_IMAGES = 50

train_images = sorted(glob(os.path.join(DATA_DIR, "Images/*")))[:NUM_TRAIN_IMAGES]
train_masks = sorted(glob(os.path.join(DATA_DIR, "Category_ids/*")))[:NUM_TRAIN_IMAGES]
val_images = sorted(glob(os.path.join(DATA_DIR, "Images/*")))[
    NUM_TRAIN_IMAGES : NUM_VAL_IMAGES + NUM_TRAIN_IMAGES
]
val_masks = sorted(glob(os.path.join(DATA_DIR, "Category_ids/*")))[
    NUM_TRAIN_IMAGES : NUM_VAL_IMAGES + NUM_TRAIN_IMAGES
]


def read_image(image_path, mask=False):
    image = tf.io.read_file(image_path)
    if mask:
        image = tf.image.decode_png(image, channels=1)
        image.set_shape([None, None, 1])
        image = tf.image.resize(images=image, size=[IMAGE_SIZE, IMAGE_SIZE])
    else:
        image = tf.image.decode_png(image, channels=3)
        image.set_shape([None, None, 3])
        image = tf.image.resize(images=image, size=[IMAGE_SIZE, IMAGE_SIZE])
        image = image / 127.5 - 1
    return image


def load_data(image_list, mask_list):
    image = read_image(image_list)
    mask = read_image(mask_list, mask=True)
    return image, mask


def data_generator(image_list, mask_list):
    dataset = tf.data.Dataset.from_tensor_slices((image_list, mask_list))
    dataset = dataset.map(load_data, num_parallel_calls=tf.data.AUTOTUNE)
    dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)
    return dataset


train_dataset = data_generator(train_images, train_masks)
val_dataset = data_generator(val_images, val_masks)

print("Train Dataset:", train_dataset)
print("Val Dataset:", val_dataset)


#Building the model

def convolution_block(
    block_input,
    num_filters=256,
    kernel_size=3,
    dilation_rate=1,
    padding="same",
    use_bias=False,
):
    x = layers.Conv2D(
        num_filters,
        kernel_size=kernel_size,
        dilation_rate=dilation_rate,
        padding="same",
        use_bias=use_bias,
        kernel_initializer=keras.initializers.HeNormal(),
    )(block_input)
    x = layers.BatchNormalization()(x)
    return tf.nn.relu(x)


def DilatedSpatialPyramidPooling(dspp_input):
    dims = dspp_input.shape
    x = layers.AveragePooling2D(pool_size=(dims[-3], dims[-2]))(dspp_input)
    x = convolution_block(x, kernel_size=1, use_bias=True)
    out_pool = layers.UpSampling2D(
        size=(dims[-3] // x.shape[1], dims[-2] // x.shape[2]), interpolation="bilinear",
    )(x)

    out_1 = convolution_block(dspp_input, kernel_size=1, dilation_rate=1)
    out_6 = convolution_block(dspp_input, kernel_size=3, dilation_rate=6)
    out_12 = convolution_block(dspp_input, kernel_size=3, dilation_rate=12)
    out_18 = convolution_block(dspp_input, kernel_size=3, dilation_rate=18)

    x = layers.Concatenate(axis=-1)([out_pool, out_1, out_6, out_12, out_18])
    output = convolution_block(x, kernel_size=1)
    return output
def DeeplabV3Plus(image_size, num_classes):
    model_input = keras.Input(shape=(image_size, image_size, 3))
    resnet50 = keras.applications.ResNet50(
        weights="imagenet", include_top=False, input_tensor=model_input
    )
    x = resnet50.get_layer("conv4_block6_2_relu").output
    x = DilatedSpatialPyramidPooling(x)

    input_a = layers.UpSampling2D(
        size=(image_size // 4 // x.shape[1], image_size // 4 // x.shape[2]),
        interpolation="bilinear",
    )(x)
    input_b = resnet50.get_layer("conv2_block3_2_relu").output
    input_b = convolution_block(input_b, num_filters=48, kernel_size=1)

    x = layers.Concatenate(axis=-1)([input_a, input_b])
    x = convolution_block(x)
    x = convolution_block(x)
    x = layers.UpSampling2D(
        size=(image_size // x.shape[1], image_size // x.shape[2]),
        interpolation="bilinear",
    )(x)
    model_output = layers.Conv2D(num_classes, kernel_size=(1, 1), padding="same")(x)
    return keras.Model(inputs=model_input, outputs=model_output)


model = DeeplabV3Plus(image_size=IMAGE_SIZE, num_classes=NUM_CLASSES)
model.summary()

Running the code produces the error below;

ValueError Traceback (most recent call last)

in 56 57 ---> 58 model = DeeplabV3Plus(image_size = IMAGE_SIZE, num_classes = NUM_CLASSES) 59 model.summary() 60

5 frames

/usr/local/lib/python3.7/dist-packages/keras/engine/functional.py in _validate_graph_inputs_and_outputs(self) 738 if not hasattr(x, '_keras_history'): 739 cls_name = self.class.name --> 740 raise ValueError(f'Output tensors of a {cls_name} model must be ' 741 'the output of a TensorFlow Layer ' 742 f'(thus holding past layer metadata). Found: {x}')

ValueError: Output tensors of a Functional model must be the output of a TensorFlow Layer (thus holding past layer metadata). Found: <tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f5c1c3b6310>