Open Calen-J opened 4 years ago
请问inference.py如何使用,我一直报错 (256,) 2020-04-14 18:48:01,906 maskrcnn_benchmark.utils.model_serialization INFO: rpn.head.conv.weight loaded from rpn.head.conv.weight of shape (256, 256, 3, 3) torch.Size([3, 800, 1123]) Traceback (most recent call last): File "tools/inference.py", line 233, in main() File "tools/inference.py", line 186, in main rboxes = prediction.get_field( "rboxes" ).cpu() File "/home2/Jc/gliding_vertex-master/maskrcnn_benchmark/structures/bounding_box.py", line 43, in get_field return self.extra_fields[field] KeyError: 'rboxes'
train和test都是用我自己的数据,没有问题,只有推断产生了这类问题
你好,我也遇到了这个问题,请问你的问题解决了吗?
我也遇到了同样的问题,请问你怎么解决的
您好,请问现在有方法解决吗,谢谢了
你好!可视化结果infrence.py中,只有框,没有类别信息。代码里输出结果prediction中,也只有4个参数:hbox、rbbox、ratio、scores。请问如何生成并显示类别信息
请问inference.py如何使用,我一直报错 (256,) 2020-04-14 18:48:01,906 maskrcnn_benchmark.utils.model_serialization INFO: rpn.head.conv.weight loaded from rpn.head.conv.weight of shape (256, 256, 3, 3) torch.Size([3, 800, 1123]) Traceback (most recent call last): File "tools/inference.py", line 233, in
main()
File "tools/inference.py", line 186, in main
rboxes = prediction.get_field( "rboxes" ).cpu()
File "/home2/Jc/gliding_vertex-master/maskrcnn_benchmark/structures/bounding_box.py", line 43, in get_field
return self.extra_fields[field]
KeyError: 'rboxes'