SFSegNets
SFSegNets copied to clipboard
lxtGH
[ECCV-2020-oral]-Semantic Flow for Fast and Accurate Scene Parsing
Hi I would like to export a retrained model from onnx to tensorrt on resolution size: 2048x1024, 1024x512. However, gridsampler is not a supported op by onnx. Could you give...
Was it an error ? SFNet-ResNet101 is for me an excellent trade-off between speed and precision.
Executing the eval.py file using pre-trained model "res18_sfnet.pth", i get nan value for mIOU and also for the iou of all the classes. Although when looking at the output segmented...
Give the custom version of "torch.nn.functional.grid_sample", "torch.nn.AdaptiveAvgPool2d", "torch.linspace"... But still failed to convert onnx to tensorrt.
我使用python demo_folder.py --arch resnet50 --snapshot weigh --demo_folder input--save_dir output的时候提醒 FileNotFoundError: [Errno 2] No such file or directory: './data/mapillary\\config.json' 有什么办法可以不用这个吗，下载一整个文件实在太大了，如果没有的话可以分享一下config.json文件吗，谢谢你！
