CNNを用いて画像の判別をする初歩的なAIを組んでいます。参照時にmodelでエラーを吐いたので助けてください

前提・実現したいこと

Python初心者です
Python3でKeras、Numpy、Tensorflowを使って画像の判別をするプログラムを組んでいたのですがテストデータとトレインデータを参照しモデルにする際にエラーが発生しました

発生している問題・エラーメッセージ

Using TensorFlow backend.
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-1-01647cf04319> in <module>
     87 y_test  = np_utils.to_categorical(y_test, nb_classes)
     88 
---> 89 model = model.fit(X_train,y_train,epochs=6,batch_size=1,validation_data=(X_test,y_test))
     90 
     91 score = model.model.evaluate(x=X_test,y=y_test)

~\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
   1173                 val_x, val_y,
   1174                 sample_weight=val_sample_weight,
-> 1175                 batch_size=batch_size)
   1176             if self._uses_dynamic_learning_phase():
   1177                 val_inputs = val_x + val_y + val_sample_weights + [0]

~\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    577             feed_input_shapes,
    578             check_batch_axis=False,  # Don't enforce the batch size.
--> 579             exception_prefix='input')
    580 
    581         if y is not None:

~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    133                         ': expected ' + names[i] + ' to have ' +
    134                         str(len(shape)) + ' dimensions, but got array '
--> 135                         'with shape ' + str(data_shape))
    136                 if not check_batch_axis:
    137                     data_shape = data_shape[1:]

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (0, 1)

該当のソースコード

Python
1from PIL import Image
2import os, glob
3import numpy as np
4import random, math
5
6train_dir = "/users/User/documents/train_pic"
7
8test_dir = "/users/User/documents/test_pic"
9
10categories = ["1","2","3","4","5","6"]
11
12nb_classes = len(categories)
13
14X = []
15
16Y = []
17
18def make_sample(files):
19    global X, Y
20    X = []
21    Y = []
22    for cat, fname in files:
23        add_sample(cat, fname)
24    return np.array(X), np.array(Y)
25
26def add_sample(cat, fname):
27    img = Image.open(fname)
28    img = img.convert("RGB")
29    img = img.resize((150, 150))
30    data = np.asarray(img)
31    X.append(data)
32    Y.append(cat)
33
34trainfiles = []
35
36testfiles = []
37
38for idx, cat in enumerate(categories):
39    image_dir = train_dir + "/" + cat
40    files = glob.glob(image_dir + "/*.jpeg")
41    for f in files:
42        trainfiles.append((idx, f))
43
44for idx, cat in enumerate(categories):
45    image_dir = test_dir + "/" + cat
46    files = glob.glob(image_dir + "/*.jpeg")
47    for f in files:
48        testfiles.append((idx, f))
49
50X_train, y_train = make_sample(trainfiles)
51X_test, y_test = make_sample(testfiles)
52xy = (X_train, X_test, y_train, y_test)
53
54np.save("/users/User/documents/cat.npy", xy)
55from keras import layers, models,optimizers
56
57from PIL import Image
58import os, glob
59import numpy as np
60import random, math
61import matplotlib.pyplot as plt
62from keras.utils import np_utils
63
64os.environ ['KMP_DUPLICATE_LIB_OK'] = 'True'
65
66model = models.Sequential()
67model.add(layers.Conv2D(32,(3,3),activation="relu",input_shape=(150,150,3)))
68model.add(layers.MaxPooling2D((2,2)))
69model.add(layers.Conv2D(64,(3,3),activation="relu"))
70model.add(layers.MaxPooling2D((2,2)))
71model.add(layers.Conv2D(128,(3,3),activation="relu"))
72model.add(layers.MaxPooling2D((2,2)))
73model.add(layers.Conv2D(128,(3,3),activation="relu"))
74model.add(layers.MaxPooling2D((2,2)))
75model.add(layers.Flatten())
76model.add(layers.Dense(512,activation="relu"))
77
78model.add(layers.Dense(6,activation="sigmoid")) 
79model.compile(loss='categorical_crossentropy',optimizer='adadelta',metrics=['accuracy'])
80
81X_train, X_test, y_train, y_test = np.load("/users/User/documents/cat.npy",allow_pickle = True)
82
83X_train = X_train.astype("float") / 255
84X_test  = X_test.astype("float")  / 255
85
86y_train = np_utils.to_categorical(y_train, nb_classes)
87y_test  = np_utils.to_categorical(y_test, nb_classes)
88
89model = model.fit(X_train,y_train,epochs=6,batch_size=1,validation_data=(X_test,y_test))
90
91score = model.model.evaluate(x=X_test,y=y_test)
92
93print('loss=', score[0])
94print('accuracy=', score[1])
95
96for i in range(5):
97    plt.subplot(2, 5, i+1)
98    plt.imshow(X_test[i], 'gray')
99
100pred = np.argmax(model.predict(X_test[0:5]), axis=1)
101print(pred)