RK3399Pro入门教程（4）从Tensorflow.Keras到RKNN

IndexError: list index out of range

E Catch exception when building RKNN model!
E Traceback (most recent call last):
E   File "/home/zl/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
E     return fn(*args)
E   File "/home/zl/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
E     options, feed_dict, fetch_list, target_list, run_metadata)
E   File "/home/zl/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
E     run_metadata)
E tensorflow.python.framework.errors_impl.OutOfRangeError: FIFOQueue '_0_fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
E          [[{{node fifo_queue_Dequeue}} = QueueDequeueV2[component_types=[DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](fifo_queue)]]
E During handling of the above exception, another exception occurred:
E Traceback (most recent call last):
Ubuntu16.04 pc上运行上面的代码生成模型，然后转换的时候rknn.build的时候提示这个错误，请问是哪的事？

jefferyzhang 发表于 2020-11-10 17:46
建议加置顶帖官方RKNN群讨论

已加，多谢

jefferyzhang 发表于 2020-11-10 17:46
建议加置顶帖官方RKNN群讨论

请问能否提供下dataset.txt以及量化用的图片，我这边量化失败，应该是量化用的图片不对。可以的话，帮忙发到邮箱里面：454086991@qq.com
非常感谢！

jefferyzhang 发表于 2020-11-11 15:12
量化图片是你需要真实场景图片，量化过程就是个下采样过程

嗯，之前的量化图片是从mnist数据集里面取出来的jpg图片，量化总是失败，后来群里建议jpg改成npy，我试了下，可以转换模型了，但是转换之后，rknn.init_runtime()又崩溃了：
D [print_tensor:136]out(0): id[   8] vtl[1] const[0] shape[ 10               ] fmt[u8 ] qnt[ASM zp=157, scale=32.828148]
D [setup_node:368]Setup node id[3] uid[2] op[SOFTMAX]
D [print_tensor:136]in(0) : id[   8] vtl[1] const[0] shape[ 10               ] fmt[u8 ] qnt[ASM zp=157, scale=32.828148]
D [print_tensor:136]out(0): id[   0] vtl[0] const[0] shape[ 10, 1            ] fmt[f16] qnt[NONE]
D [optimize_node:312]Backward optimize neural network
D [optimize_node:319]Forward optimize neural network
D [rknn_optimize_internal_node:331]Optimize node uid[2] sub_uid[1] op[SOFTMAX_INTERNAL]
I [compute_node:261]Create vx node

Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)
这个信息发群里也没有人碰到过，提示信息只能看出好像是有地方内存溢出等，但是没法排查了。版主碰到过吗？或者有什么方式进一步排查下吗？
谢谢