cannot unpack non-iterable Sequential objectを解決したい

Question

前提・実現したいこと

Pythonにて鋳物の画像を用いた画像判別機を作ろうとしています。
model.fitの場面に以下のエラーメッセージが発生しました。
解決方法を探っています。
お判りになる方いらっしゃいましたら、
メッセージ頂けると幸いです。

発生している問題・エラーメッセージ

TypeError                                 Traceback (most recent call last)
<ipython-input-16-27f12ae95326> in <module>
     22     return predictions, history
     23 
---> 24 predictions, history = OKDEF()

TypeError: cannot unpack non-iterable Sequential object

該当のソースコード

import os, cv2, random
import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
from matplotlib import ticker
import seaborn as sns
%matplotlib inline 

import tensorflow
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Input, Dropout, Flatten, Convolution2D, MaxPooling2D, Dense, Activation
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.callbacks import ModelCheckpoint, Callback, EarlyStopping
import np_utils

TRAIN_DIR = './archive/casting_data/casting_data/train/'
TEST_DIR = './archive/casting_data/casting_data/test/'


ROWS = 64
COLS = 64
CHANNELS = 3

train_images = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR)] # use this for full dataset
train_ok =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cast_ok' in i]
train_def =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cast_def' in i]

test_images =  [TEST_DIR+i for i in os.listdir(TEST_DIR)]

# slice datasets for memory efficiency on Kaggle Kernels, delete if using full dataset
train_images = train_ok + train_def
random.shuffle(train_images)
test_images =  test_images

def read_image(file_path):
    img = cv2.imread(file_path, cv2.IMREAD_COLOR) #cv2.IMREAD_GRAYSCALE
    return cv2.resize(img, (ROWS, COLS), interpolation=cv2.INTER_CUBIC)


def prep_data(images):
    count = len(images)
    data = np.ndarray((count, CHANNELS, ROWS, COLS), dtype=np.uint8)

    for i, image_file in enumerate(images):
        image = read_image(image_file)
        data[i] = image.T #transpose mxn > nxm
        if i%250 == 0: print('Processed {} of {}'.format(i, count))
    
    return data

train = prep_data(train_images)
test = prep_data(test_images)

print("Train shape: {}".format(train.shape))
print("Test shape: {}".format(test.shape))

labels = []
for i in train_images:
    if 'cast_ok_' in i:
        labels.append(1)
    else:
        labels.append(0)

sns.countplot(labels)
plt.title('OK and def')

labels = np.array(labels)

DEF_avg = np.array([DEF[0].T for i, DEF in enumerate(train) if labels[i]==1]).mean(axis=0)
plt.imshow(DEF_avg)
plt.title('Average DEF')

OK_avg = np.array([OK[0].T for i, OK in enumerate(train) if labels[i]==0]).mean(axis=0)
plt.imshow(OK_avg)
plt.title('Average OK')

optimizer = RMSprop(lr=1e-4)
objective = 'binary_crossentropy'


def OKDEF():
    
    model = Sequential()

    model.add(Convolution2D(32, (3, 3), input_shape=(3, ROWS, COLS), activation='relu', padding="same"))
    model.add(Convolution2D(32, (3, 3), activation='relu', padding="same"))
    model.add(MaxPooling2D(data_format="channels_first", pool_size=(2, 2)))
    
    model.add(Convolution2D(64, (3, 3), activation='relu', padding="same"))
    model.add(Convolution2D(64, (3, 3), activation='relu', padding="same"))
    model.add(MaxPooling2D(data_format="channels_first", pool_size=(2, 2)))
    
    model.add(Convolution2D(128, (3, 3), activation='relu', padding="same"))
    model.add(Convolution2D(128, (3, 3), activation='relu', padding="same"))
    model.add(MaxPooling2D(data_format="channels_first", pool_size=(2, 2)))
    
    model.add(Convolution2D(256, (3, 3), activation='relu', padding="same"))
    model.add(Convolution2D(256, (3, 3), activation='relu', padding="same"))
    model.add(MaxPooling2D(data_format="channels_first", pool_size=(2, 2)))
    
    model.add(Flatten())
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))
    
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))

    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])
    return model


model = OKDEF()

train = tensorflow.transpose(train, [0, 2, 3, 1])
test = tensorflow.transpose(test,[0, 2, 3, 1])

epochs = 10
batch_size = 16

class LossHistory(Callback):
    def on_train_begin(self, logs={}):
        self.losses = []
        self.val_losses = []
        
    def on_epoch_end(self, batch, logs={}):
        self.losses.append(logs.get('loss'))
        self.val_losses.append(logs.get('val_loss'))

early_stopping = EarlyStopping(monitor='val_loss', patience=3, verbose=1, mode='auto')        
        
def run_OKDEF():
    
    history = LossHistory()
    model.fit(train, labels, batch_size=batch_size, epochs=epochs,
              validation_split=0.25, verbose=0, shuffle=True, callbacks=[history, early_stopping])
    
    predictions = model.predict(test, verbose=0)
    return predictions, history

predictions, history = OKDEF()

試したこと

NHWCへの変換
errorでの検索

補足情報（FW/ツールのバージョンなど）

Python 3.8.8
TensorFlow 2.3.0

Answer 1

提示ソース内容はほぼ理解していませんが
predictions, history = OKDEF()の部分はpredictions, history = run_OKDEF()が正しいと思います。

Comments

[K2ohei]

run_OKDEF()に直して実行を行いました。
すると
Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 64 but received input with shape [None, 64, 64, 3]
というエラーがさらに出てきました。
調べはしましたが、良い解決策が見つかっていません。

Answer 2

---> 24 predictions, history = OKDEF()

TypeError: cannot unpack non-iterable Sequential object

返り値を2つの変数で受けているのに、(たぶん)1つしか返ってきていないというエラーです。

ちらっとしか見ていませんが、ここは、

predictions, history = run_OKDEF()

の間違えではないかと思います。

Comments

[K2ohei]

run_OKDEF()に直して実行を行いました。
すると
Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 64 but received input with shape [None, 64, 64, 3]
というエラーがさらに出てきました。
shapeがNoneになっているのも不思議なところです。

Answer 3

In retro games, there are various options for randomly choosing records from a database table, each having pros and cons. One method may be better suited than the others depending on the particular requirements of the application.