OutOfRangeError: PaddingFIFOQueue '_2_get_batch/batch/padding_fifo_queue' is closed and has insufficient elements about fpn_tensorflow

[Kongsea]

I think it was caused by the inconsistency of the tfrecord data and the data reader.
Please check it first.

[niuniu111]

Have you tried the effect of the VGg network?

[Kongsea]

I have not tried it.
Maybe you can have a try.

[niuniu111]

I made a mistake when I tried, showing this mistake：ValueError: Shape of a new variable (vgg_16/fc8/weights) must be fully defined, but instead was (1, 1, 4096, ?)，I think it's my training model and I don't know where to download it.

[Kongsea]

How about defining the inputs fully?
Such as:
inputs = tf.placeholder(tf.float32, [FLAGS.batch_size, 224, 224, 3], name='inputs')

[TVXQ20031226]

I made a mistake when I tried, showing this mistake：ValueError: Shape of a new variable (vgg_16/fc8/weights) must be fully defined, but instead was (1, 1, 4096, ?)，I think it's my training model and I don't know where to download it.

have you solved this problem?? I met this issue too!! thanks in advance~~@niuniu111