IronJustin
IronJustin
I got that error too. Waiting for help. OS: ubuntu 16.04.5 tensorflow: 1.7.0 cuda: 9.0 cudnn: 7.1
#147 solved the problem, you should put your checkpoint files under the EAST dir, and modify the running command: ``` python eval.py --test_data_path=images/ --gpu_list=0 --checkpoint_path=east_icdar2015_resnet_v1_50_rbox/ --output_dir=/tmp/ ```
@harshalcse check carefully, I removed some '/', as #147 mentioned.
@snowyseaons 求大佬更一下二维码谢谢
same problem here, can someone provide the new links?
any update or any official suggestion?
@vdantu [\mxnet-model-server\examples\model_service_template\mxnet_model_service.py line 96](https://github.com/awslabs/mxnet-model-server/blob/master/examples/model_service_template/mxnet_model_service.py#L96), the model will bind the input_shape, can we just comment this line to accept arbitrary size of image?
@vdantu sorry, I mean arbitrary w and h, not the batch dimension, since rebind will cost a lot, maybe fix the w and h size would be better. Thanks V~
Me too. But if you just want to test the model, ResNeXt101_fork is not necessary.
nice job, have you test it in public dataset?