哪位大侠能给看一下，这是错在哪里？

----------- Configuration Arguments -----------
ap_version: 11point
batch_size: 64
data_dir: data/pascalvoc
dataset: pascalvoc
enable_ce: False
epoc_num: 120
image_shape: 3,300,300
learning_rate: 0.001
mean_BGR: 127.5,127.5,127.5
model_save_dir: model
parallel: True
pretrained_model: pretrained/ssd_mobilenet_v1_coco/
use_gpu: True
------------------------------------------------
/usr/local/lib/python2.7/dist-packages/paddle/fluid/evaluator.py:71: Warning: The DetectionMAP is deprecated, because maintain a modified program inside evaluator cause bug easily, please use fluid.metrics.DetectionMAP instead.
% (self.__class__.__name__, self.__class__.__name__), Warning)
train on pascalvoc with 16552 images
test on pascalvoc with 4953 images
Epoc 0, batch 0, loss 42.7259063721, time 8.10623168945e-06
Epoc 0, batch 20, loss 7.97586536407, time 1.31518697739
Epoc 0, batch 40, loss 6.93747901917, time 1.24792098999
Epoc 0, batch 60, loss 6.71531248093, time 1.24015402794
Epoc 0, batch 80, loss 5.84000205994, time 1.24792313576
Epoc 0, batch 100, loss 6.04903888702, time 1.24645185471
Epoc 0, batch 120, loss 5.59432888031, time 1.27560687065
Epoc 0, batch 140, loss 5.22779273987, time 1.2607820034
Epoc 0, batch 160, loss 4.96114015579, time 1.25366401672
Epoc 0, batch 180, loss 4.66661167145, time 1.24980401993
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
/paddle/paddle/fluid/operators/math/cross_entropy.cu:29 Assertion `label[i] >= 0 && label[i] < D` failed.
F0917 11:31:21.934497 3499 exception_holder.h:34] Unknown exception caught
*** Check failure stack trace: ***
@ 0x7efca173fc3d google::LogMessage::Fail()
@ 0x7efca17436ec google::LogMessage::SendToLog()
@ 0x7efca173f763 google::LogMessage::Flush()
@ 0x7efca1744bfe google::LogMessageFatal::~LogMessageFatal()
@ 0x7efca23d98e2 paddle::framework::details::ExceptionHolder::Catch()
@ 0x7efca23d622d _ZZN6paddle9framework7details24ThreadedSSAGraphExecutor5RunOpEPNS0_13BlockingQueueIPNS1_13VarHandleBaseEEEPNS1_12OpHandleBaseEENKUlvE_clEv
@ 0x7efca22519e3 std::_Function_handler<>::_M_invoke()
@ 0x7efca1811a77 std::__future_base::_State_base::_M_do_set()
@ 0x7efcde9b8a99 __pthread_once_slow
@ 0x7efca23d4c62 _ZNSt13__future_base11_Task_stateISt5_BindIFZN6paddle9framework7details24ThreadedSSAGraphExecutor5RunOpEPNS3_13BlockingQueueIPNS4_13VarHandleBaseEEEPNS4_12OpHandleBaseEEUlvE_vEESaIiEFvvEE6_M_runEv
@ 0x7efca18135b4 _ZZN10ThreadPoolC1EmENKUlvE_clEv
@ 0x7efcd893fc80 (unknown)
@ 0x7efcde9b16ba start_thread
@ 0x7efcde6e741d clone
@ (nil) (unknown)
run_train.sh: 行 7: 3472 已放弃 CUDA_VISIBLE_DEVICES=0,1 python -u train.py --batch_size=64 --dataset='pascalvoc' --pretrained_model='pretrained/ssd_mobilenet_v1_coco/'