二値分類の学習が進まない

前提・実現したいこと

pythonで画像を用いた二値分類の学習をさせようとしています。(画像は100枚ずつ)
そこで、下記のコードを用いて実行したところ、loss　acc val_loss val_accがどうしても一定値になってしまい学習が進みません。
この原因としては何が考えられるか教えていただきたいです。

発生している問題・エラーメッセージ

192/192 [==============================] - 55s 286ms/step - loss: 6.1643 - acc: 0.4844 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 2/30
192/192 [==============================] - 49s 254ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 3/30
192/192 [==============================] - 48s 252ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 4/30
192/192 [==============================] - 50s 260ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 5/30
192/192 [==============================] - 85s 445ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 6/30
192/192 [==============================] - 106s 552ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 7/30
192/192 [==============================] - 78s 406ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 8/30
192/192 [==============================] - 85s 444ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 9/30
192/192 [==============================] - 79s 411ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 10/30
192/192 [==============================] - 98s 508ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 11/30
192/192 [==============================] - 80s 418ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 12/30
192/192 [==============================] - 51s 263ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 13/30
192/192 [==============================] - 55s 286ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 14/30
192/192 [==============================] - 72s 377ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792
Epoch 15/30
192/192 [==============================] - 67s 347ms/step - loss: 7.9751 - acc: 0.5052 - val_loss: 8.3948 - val_acc: 0.4792

エラーメッセージ


### 該当のソースコード

import numpy as np
import tensorflow as tf
import random as rn
import os
import keras
from keras import backend as K

from keras.preprocessing import image
from sklearn.model_selection import train_test_split

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D

os.environ['PYTHONHASHSEED'] = '0'
np.random.seed(0)
rn.seed(0)
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
tf.set_random_seed(0)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)

input_shape = (224, 224, 3)
batch_size = 32
epochs = 30
num_classes = 2
x = []
y = []
for f in os.listdir("sakura"):
x.append(image.img_to_array(image.load_img("sakura/"+f, target_size=input_shape[:2])))
y.append(0)
for f in os.listdir("cosmos"):
x.append(image.img_to_array(image.load_img("cosmos/"+f, target_size=input_shape[:2])))
y.append(1)
x = np.asarray(x)
x /= 255
y = np.asarray(y)
y = keras.utils.to_categorical(y, num_classes)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state= 3)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer="SGD",
metrics=['acc'])
history = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))