princeton-vl / px2graph

Training code for "Pixels to Graphs by Associative Embedding"
BSD 3-Clause "New" or "Revised" License
133 stars 22 forks source link

OutOfRangeError (see above for traceback): FIFOQueue '_2_fifo_queue_2' is closed #11

Closed srikar2097 closed 4 years ago

srikar2097 commented 4 years ago

Hi Alejandro, First off, thanks for sharing your code. However there seems to be some issue with it. I cloned your repo as is, put the data in required data/ dir but when I run it, i get the following stacktrace.

python main.py -e="test" --sg_task=SG --gpu_choice="2" --batchsize=4 --num_data_threads=1

Any Idea why this could be happening?

OutOfRangeError (see above for traceback): FIFOQueue '_2_fifo_queue_2' is closed and has insufficient elements (requested 4, current size 0)
     [[Node: fifo_queue_2_DequeueMany = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT, DT_INT32, DT_INT32, DT_INT32, DT_FLOAT, DT_INT32, DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](fifo_queue_2, fifo_queue_2_DequeueMany/n)]]
     [[Node: gradients/cond_5/concat_1_grad/Gather_4/_735 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_5915_gradients/cond_5/concat_1_grad/Gather_4", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

Using the following setup: tensorflow version: 1.3.0 munkres-tensorflow compiled as per instructions. python: 3.6