我在用这个模型进行评估的时候,遇见了上述这个问题,直接用github上的命令是有问题的,我的环境是python3, tensorflow 1.4,ubuntu16.04,结果就报错了:
TypeError: Can not convert a tuple into a Tensor or Operation
然后,自己对这个tensorflow编程不了解,沉寂了好长时间,我的命令是:
DATASET_DIR=tfrecords_test_v3 EVAL_DIR=logs/ CHECKPOINT_PATH=./checkpoints/VGG_VOC0712_SSD_300x300_ft_iter_120000.ckpt python3 eval_ssd_network.py \ --eval_dir=${EVAL_DIR} \ --dataset_dir=${DATASET_DIR} \ --dataset_name=pascalvoc_2007 \ --dataset_split_name=test \ --model_name=ssd_300_vgg \ --checkpoint_path=${CHECKPOINT_PATH} \ --batch_size=1
后面,有人在github上解决了这个问题,我在此分享给大家,打开eval_ssd_network.py文件,然后加入以下代码:
def flatten(x): result = [] for el in x: if isinstance(el, tuple): result.extend(flatten(el)) else: result.append(el) return result
# Waiting loop. slim.evaluation.evaluation_loop( master=FLAGS.master, checkpoint_dir=checkpoint_path, logdir=FLAGS.eval_dir, num_evals=num_batches, eval_op=flatten(list(names_to_updates.values())), #这里调用flatten variables_to_restore=variables_to_restore, eval_interval_secs=60, max_number_of_evaluations=np.inf, session_config=config, timeout=None)
# Standard evaluation loop. start = time.time() slim.evaluation.evaluate_once( master=FLAGS.master, checkpoint_path=checkpoint_path, logdir=FLAGS.eval_dir, num_evals=num_batches, eval_op=flatten(list(names_to_updates.values())), #这里也调用flatten variables_to_restore=variables_to_restore, session_config=config)
参考文献
[1].TypeError: Can not convert a tuple into a Tensor or Operation. https://github.com/balancap/SSD-Tensorflow/issues/154