Getting error 'FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 10, current size 0)'

[cclough]

When I run main.py I get:

OutOfRangeError (see above for traceback): FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 10, current size 0) [[Node: create_inputs/batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](create_inputs/batch/fifo_queue, create_inputs/batch/n)]]

I've downloaded VOC and have the path in main.py set to:
flags.DEFINE_string('data_dir', './VOCdevkit/VOC2012', 'data directory')

I've also set the following in main.py:
flags.DEFINE_string('encoder_name', 'res101', 'name of pre-trained model, res101, res50 or deeplab') flags.DEFINE_string('pretrain_file', './resnet_v1_101.ckpt', 'pre-trained model filename corresponding to encoder_name')

Apologies if I'm doing something obvious wrong.

[zhengyang-wang]

I think you may need to check the directory with "./dataset/train.txt" again. For example, is the training image in "./VOCdevkit/VOC2012/JPEGImages/"? The error information means the program cannot find the input.
Thanks for reporting your problem.