如何將圖像數據正確擬合到 python 中的 model？ 有人可以告訴我我做錯了什么嗎？

Question

所以我正在嘗試訓練一個cnn model，但我真的不明白如何正確地做到這一點。 我還在學習這種東西，所以我真的迷路了。 我已經嘗試過用它做一些事情，但仍然無法理解它。 有人可以向我解釋如何正確地做到這一點。 當我嘗試將火車數據擬合到 model 時，會彈出此錯誤。

WARNING:tensorflow:Model was constructed with shape (None, 224, 224, 3) for input KerasTensor(type_spec=TensorSpec(shape=(None, 224, 224, 3), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'input_1'"), but it was called on an input with incompatible shape (None,).
Traceback (most recent call last):
  File "G:/Skripsi/Program/training.py", line 80, in <module>
    train.train()
  File "G:/Skripsi/Program/training.py", line 70, in train
    model.fit(self.x_train, self.y_train, epochs=2, verbose=1)
  File "G:\Skripsi\Program\venv\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "G:\Skripsi\Program\venv\lib\site-packages\tensorflow\python\framework\func_graph.py", line 1129, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\engine\training.py", line 878, in train_function  *
        return step_function(self, iterator)
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\engine\training.py", line 867, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\engine\training.py", line 860, in run_step  **
        outputs = model.train_step(data)
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\engine\training.py", line 808, in train_step
        y_pred = self(x, training=True)
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "G:\Skripsi\Program\venv\lib\site-packages\keras\engine\input_spec.py", line 227, in assert_input_compatibility
        raise ValueError(f'Input {input_index} of layer "{layer_name}" '
    ValueError: Exception encountered when calling layer "model" (type Functional).
        Input 0 of layer "conv2d" is incompatible with the layer: expected min_ndim=4, found ndim=1. Full shape received: (None,)
        Call arguments received:
      • inputs=tf.Tensor(shape=(None,), dtype=int32)
      • training=True
      • mask=None

這是我訓練 model 的代碼。

from sklearn.model_selection import train_test_split
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
from densenet201 import DenseNet201
import tensorflow as tf
import pandas as pd
import numpy as np
import cv2
import os

dataset_folder = "./datasets/train_datasets"


class TrainingPreprocessing:

    @staticmethod
    def preprocessing_train(path):
        images = cv2.imread(path, 3)
        images_resize = cv2.resize(src=images, dsize=(224, 224), interpolation=cv2.INTER_LINEAR)
        images_normalize = cv2.normalize(images_resize, None, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX,
                                         dtype=cv2.CV_32F)
        return images_normalize.reshape(224, 224, 3)


class Training:

    @staticmethod
    def load_data():
        """Loads and Preprocess dataset"""
        train_labels_encode = []
        train_labels = []
        train_data = []

        file_list = os.listdir(dataset_folder)
        for folder in file_list:
            file_list2 = os.listdir(str(dataset_folder) + '/' + str(folder))
            for images in file_list2:
                train_labels_encode.append(folder)
                train_labels.append(folder)
                train_data.append(np.array(TrainingPreprocessing.preprocessing_train(
                    str(dataset_folder) + '/' + str(folder) + '/' + str(images)
                )))

        labels = np.array(train_labels_decode)
        data = np.array(train_data)
        return labels, data

    def split_data(self):
        """Split the preprocessed dataset to train and test data"""
        x, y = self.load_data()
        self.x_train, self.x_test, self.y_train, self.y_test = train_test_split(x, y, test_size=0.20, random_state=0)
        print('Training data shape : ', self.x_train.shape, self.y_train.shape)

        print('Testing data shape : ', self.x_test.shape, self.y_test.shape)

    def train(self):
        """Compile dan fit DenseNet model"""
        input_shape = 224, 224, 3
        number_classes = 2
        model = DenseNet201.densenet(input_shape, number_classes)
        model.summary()

        model.compile(loss='binary_crossentropy', optimizer='Adam', metrics=["accuracy"])
        model.fit(self.x_train, self.y_train, epochs=2, verbose=1)
        model.save_weights('densenet201_best_model.h5', overwrite=True)

        loss, accuracy = model.evaluate(self.x_test, self.y_test)

        print("[INFO] accuracy: {:.2f}%".format(accuracy * 100))


train = Training()
train.split_data()
train.train()

這是cnn網絡的代碼

from tensorflow.keras.layers import AveragePooling2D, GlobalAveragePooling2D, MaxPool2D
from tensorflow.keras.layers import Input, Conv2D, BatchNormalization, Dense
from tensorflow.keras.layers import ReLU, concatenate, Dropout
from tensorflow.keras.models import Model
import tensorflow.keras.layers as layers
import tensorflow.keras.backend as K
import tensorflow as tf


class DenseNet201:

    def densenet(image_shape, number_classes, growth_rate=32):

        def batch_relu_conv(x, growth_rate, kernel=1, strides=1):
            x = BatchNormalization()(x)
            x = ReLU()(x)
            x = Conv2D(growth_rate, kernel, strides=strides, padding='same', kernel_initializer="he_uniform")(x)
            return x

        def dense_block(x, repetition):
            for _ in range(repetition):
     

       y = batch_relu_conv(x, 4 * growth_rate)
            y = batch_relu_conv(y, growth_rate, 3)
            x = concatenate([y, x])
        return x

    def transition_layer(x):
        x = batch_relu_conv(x, K.int_shape(x)[-1] // 2)
        x = AveragePooling2D(2, strides=2, padding='same')(x)
        return x

    inputs = Input(image_shape)
    x = Conv2D(64, 7, strides=2, padding='same', kernel_initializer="he_uniform")(inputs)
    x = MaxPool2D(3, strides=2, padding='same')(x)
    for repetition in [6, 12, 48, 32]:
        d = dense_block(x, repetition)
        x = transition_layer(d)
    x = GlobalAveragePooling2D ()(d)

    output = Dense(number_classes, activation='softmax')(x)

    model = Model(inputs, output)
    return model

提前感謝您提供的任何幫助！

Answer 1

輸入圖像的大小是多少？

在行輸入 = Input(image_shape) --> 它是否具有來自 TF 的 Model 所需的相同形狀？

錯誤表明輸入形狀是 (None,)，而不是 (None,224,224,3) -> 您可以檢查輸入的定義方式嗎？