i = (i + 1) % n
yield (np.array(X_train), np.array(Y_train))
def loss(y_true, y_pred):
crossloss = K.binary_crossentropy(y_true, y_pred)
# 这个乘除是为了求平均……相当于每个像素点的交叉熵。
loss = 4 * K.sum(crossloss) / HEIGHT / WIDTH
return loss
if __name__ == "__main__":
log_dir = "logs/"
# 获取model
model = convnet_segnet(n_classes=NCLASSES,
input_height=HEIGHT,
input_width=WIDTH)
# model.summary()
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
# 打开数据集的txt
with open(r"/SegNet_Conv2/dataset2/train.txt", "r") as f:
lines = f.readlines()
# 打乱行，这个txt主要用于帮助读取数据来训练
# 打乱的数据更有利于训练
from nets.segnet import convnet_segnet model = convnet_segnet(2, input_height=416, input_width=416) model.summary()