我试图提高模型的训练速度。我做了很多预处理和扩充(它们在CPU上运行),这使我的训练变慢了。因此,我尝试使用keras Sequence
来实现数据的加载和预处理。因此,我遵循了keras docs和这个stanford exmaple。到目前为止,这使我的训练慢了很多,我敢肯定我在某个地方有一个错误。因为使用4个workers
和use_multiprocessing=True
运行我的训练脚本,所以我得到以下日志:
Epoch 8/10
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
8/9 [=========================>....] - ETA: 2s - loss: 444.2380Using TensorFlow backend.
9/9 [==============================] - 26s 3s/step - loss: 447.4939 - val_loss: 308.3012
Using TensorFlow backend.
Epoch 9/10
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
8/9 [=========================>....] - ETA: 2s - loss: 421.9372Using TensorFlow backend.
9/9 [==============================] - 26s 3s/step - loss: 418.9702 - val_loss: 263.9197
似乎在我的代码中的某个地方,每个时期都为每个工作程序加载和加载了TensorFlow(由于验证集而设置为8个)。我认为这不是序列正常工作的方式吗?
DataGenerator:
class DataGenerator(Sequence):
def __init__(self, annotation_lines, batch_size, input_shape, anchors, num_classes, max_boxes=80):
self.annotations_lines = annotation_lines
self.batch_size = batch_size
self.input_shape = input_shape
self.anchors = anchors
self.num_classes = num_classes
self.max_boxes = max_boxes
def __len__(self):
return int(np.ceil(len(self.annotations_lines) / float(self.batch_size)))
def __getitem__(self, idx):
annotation_lines = self.annotations_lines[idx * self.batch_size:(idx + 1) * self.batch_size]
image_data = []
box_data = []
for annotation_line in annotation_lines:
image, box = get_random_data(annotation_line, self.input_shape, random=True, max_boxes=self.max_boxes)
image_data.append(image)
box_data.append(box)
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, self.input_shape, self.anchors, self.num_classes)
return [image_data, *y_true], np.zeros(self.batch_size)
我的训练脚本的一部分:
batch_size = batch_size_complete # note that more GPU memory is required after unfreezing the body
data_gen_train = DataGenerator(lines, batch_size, input_shape, anchors, num_classes)
data_gen_validation = DataGenerator(validation_lines, batch_size, input_shape, anchors, num_classes)
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
r = model.fit_generator(data_gen_train,
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_gen_validation,
validation_steps=max(1, num_val // batch_size),
epochs=epochs,
initial_epoch=initial_epoch,
callbacks=[logging, checkpoint, reduce_lr, early_stopping],
workers=workers,
use_multiprocessing=True)
model.save_weights(log_dir + 'trained_weights_final.h5')
答案 0 :(得分:0)
训练的速度取决于许多因素,例如批次大小,输入图像的大小,学习率,历元步骤和步骤验证。然后开始调查这些原因之一,并放入use_multiprocessing=False
,因为
培训期间编写的各种张量流后端不应该存在。
答案 1 :(得分:0)
我看到您很多时候都在使用“使用Tensorflow后端”,这似乎好像Keras在每个线程中一次又一次地初始化。
也许您应该简单地尝试use_multiprocessing=False
(您仍然可以有很多工作人员)