ValueError：不能使用“filtered_detections/map/while/strided_slice_1”作为“filtered_detections/map/while/ones/packed”的输入
[英]ValueError: Cannot use 'filtered_detections/map/while/strided_slice_1' as input to 'filtered_detections/map/while/ones/packed'
问题描述
Training on custom dataset by using Keras retinanet ( https://github.com/fizyr/keras-retinanet ).
使用 Keras 视网膜网络（ https://github.com/fizyr/keras-retinanet ）对自定义数据集进行训练。 while running the retinanet-train command, i got the following error在运行retinanet-train 命令时，出现以下错误
File "c:\users\samjith.cp\anaconda3\lib\site-packages\tensorflow\python\ops\control_flow_util.py", line 350, in CheckInputFromValidContext
raise ValueError(error_msg + " See info log for more details.")
ValueError: Cannot use 'filtered_detections/map/while/strided_slice_1' as
input to 'filtered_detections/map/while/ones/packed'
because 'filtered_detections/map/while/strided_slice_1' is in a while loop.
See info log for more details.
how to solve this error?如何解决这个错误？
1 个解决方案
解决方案1
0 2020-06-02 14:44:59
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
我们是否需要通过 object 检测 model 的所有检测或基于置信度阈值的过滤检测以计算 mAP？ - Do we need to pass all the detections from a object detection model or filtered detections based on confidence threshold for calculation of mAP?
Tensorflow：带有while循环的strided_slice切片错误 - Tensorflow: strided_slice slicing error with while loop
ValueError：使用输入调光1索引超出范围； 输入的strided_slice只有1个暗角 - ValueError: Index out of range using input dim 1; input has only 1 dims for strided_slice
MTCNN 在第一次检测时不使用 GPU，但在后续检测中使用 - MTCNN does not use GPU on first detection but does on following detections
多个精灵碰撞检测 - Multiple sprite collision detections
使用Python查找错误检测的发生率 - Find Occurance of False Detections with Python
FiftyOne 使用重叠检测保存图像 - FiftyOne Save Image with Overlaid Detections
如何获得过滤后的数据框进行计算，同时将原始数据框保留在熊猫中？ - How to get the filtered dataframe for calculations while retaining the original one in pandas?
尝试向过滤流 twitter API 发出请求时出现未经授权的消息 - Unauthorized message while trying to make requests to Filtered stream twitter API
读取 JSON 时根据过滤值更改数据框架构 - Dataframe schema change based on filtered values while reading JSON
相关标签