TensorFlow дает ошибку при прогнозировании: ожидаемая ось -1 формы ввода, чтобы иметь значение 2034, но получил ввод с ф ⇐ Python

[Anonymous]

Когда я иду и пытаюсь установить мою модель, я получаю следующую ошибку: < /p>

Код: Выделить всё

ValueError: Exception encountered when calling Sequential.call().
Input 0 of layer "dense_82" is incompatible with the layer: expected axis -1
of input shape to have value 2304, but received input with shape (None, 118336)
< /code>
Мой код: < /p>
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
from tensorflow.keras.utils import to_categorical

from google.colab import drive
from google.colab.patches import cv2_imshow
drive.mount('/content/drive')

img_height = 180
img_width = 180

training = tf.keras.utils.image_dataset_from_directory(
"/content/drive/MyDrive/Redes neuronais/ISIC_data/Train",
labels="inferred",
label_mode="int",
color_mode="rgb",
batch_size=32,
image_size=(img_height, img_width),
shuffle=True,
seed=1256,
validation_split=None,
subset=None,
interpolation="bilinear",
follow_links=False,
crop_to_aspect_ratio=False,
pad_to_aspect_ratio=False,
data_format=None,
verbose=True
)

testing = tf.keras.utils.image_dataset_from_directory(
"/content/drive/MyDrive/Redes neuronais/ISIC_data/Test",
labels="inferred",
label_mode="int",
color_mode="rgb",
batch_size=32,
image_size=(img_height, img_width),
shuffle=True,
seed=1256,
validation_split=None,
subset=None,
interpolation="bilinear",
follow_links=False,
crop_to_aspect_ratio=False,
pad_to_aspect_ratio=False,
data_format=None,
verbose=True
)

normalization_layer = tf.keras.layers.Rescaling(1./255)
normalized_ds = training.map(lambda x, y: (normalization_layer(x), y))

AUTOTUNE = tf.data.AUTOTUNE

training = training.cache().prefetch(buffer_size=AUTOTUNE)
testing = testing.cache().prefetch(buffer_size=AUTOTUNE)

num_classes = 9

model = Sequential([
Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
MaxPooling2D(2, 2),
Conv2D(64, (3, 3), activation='relu'),
MaxPooling2D(2, 2),
Flatten(),
Dense(128, activation='relu'),
Dense(num_classes, activation='softmax')
])

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

model.summary()

history = model.fit(training, batch_size=64, epochs=20,validation_data=testing)

Как это исправить?

Подробнее здесь: https://stackoverflow.com/questions/795 ... pe-to-have