SSD-Tensorflow:TypeError: Can not convert a tuple into a Tensor or Operation

来源:互联网 发布:蜜缘快约软件 编辑:程序博客网 时间:2024/06/02 07:05

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_v3EVAL_DIR=logs/CHECKPOINT_PATH=./checkpoints/VGG_VOC0712_SSD_300x300_ft_iter_120000.ckptpython3 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



阅读全文
0 0