# imgplot = plt.imshow(Y)
# plt.show(block=False)
# plt.pause(3)
# plt.close()
#hello = y_to.flatten()
#print(hello[hello==3].shape)
#print("Number of classes",np.unique(hello))
#class_weights = class_weight.compute_class_weight('balanced',np.unique(hello),hello)
#class_weights.insert(3,0)
#print("class_weights",class_weights)
x_to = np.asarray(x_to)
y_to = np.asarray(y_to)
print(x_to.shape)
print(y_to.shape)
y_to[
y_to ==
4] = 1 #since label 4 was missing in Brats dataset , changing all labels 4 to 3.
#y_to = one_hot_encode(y_to)
y_to[y_to == 2] = 1
y_to[y_to == 1] = 1
y_to[y_to == 0] = 0
print(y_to.shape)
#y_to = y_to.reshape(240,240,1)
model.fit(x=x_to, y=y_to, batch_size=20, epochs=50)
model.save('2class.h5')
for j in range(100):
flair_small[i, :, :, j] = flair_small_[i, :, :, j+36]
print('Shape of flair_small: ' + str(flair_small.shape))
os.environ["CUDA_VISIBLE_DEVICES"] = "0, 1, 2, 3"
tfconfig = tf.ConfigProto()
tfconfig.gpu_options.allow_growth = True
tfconfig.allow_soft_placement = True
sess = tf.Session(config=tfconfig)
sess.run(tf.global_variables_initializer())
keras.backend.set_session(sess)
# history = model.fit(x=X_train_t1, y=X_train_t1, batch_size=32, epochs=100)
# history = model.fit(x=X_train_t1ce, y=X_train_t1ce, batch_size=32, epochs=100)
# history = model.fit(x=X_train_t2, y=X_train_t2, batch_size=32, epochs=100)
history = model.fit(x=flair_small, y=flair_small, batch_size=32, epochs=100)
print(history.history.keys())
plt.plot(history.history['loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train'], loc='upper right')
plt.show()
model.save("flair_model")