From 43d213ba3609175d68686a9335a6eeaee2e07de1 Mon Sep 17 00:00:00 2001 From: Micaela Verucchi Date: Tue, 24 Nov 2020 12:44:36 +0100 Subject: [PATCH 1/2] Update README_seg.md --- README_seg.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README_seg.md b/README_seg.md index 6717f0d..567b607 100644 --- a/README_seg.md +++ b/README_seg.md @@ -23,7 +23,7 @@ To run the semantic segmentation demo follow these steps (example with shelfnet_ rm shelfnet_mapillary_fp32.rt # be sure to delete(or move) old tensorRT files export TKDNN_BATCHSIZE=4 # be sure you have batch size > than 1 if you want to run inference on images bigger than 1024 ./test_shelfnet_mapillary # run the yolo test (is slow) -./demo shelfnet_mapillary_fp32.rt ../demo/yolo_test.mp4 1 15 +./seg_demo shelfnet_mapillary_fp32.rt ../demo/yolo_test.mp4 1 15 ``` In general the demo program takes the following parameters: ``` @@ -53,4 +53,4 @@ N.b. By default it is used FP32 inference 1. Zhuang, Juntang, et al. "ShelfNet for fast semantic segmentation." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2019. -*. Mapillary Vistas has originally 66 classes, but we reduced them to 15 to improve the results on the categories of our interest. \ No newline at end of file +*. Mapillary Vistas has originally 66 classes, but we reduced them to 15 to improve the results on the categories of our interest. From 8fb5772ad9786594a8a8a669e5c83c7182118816 Mon Sep 17 00:00:00 2001 From: Micaela Verucchi Date: Tue, 24 Nov 2020 13:03:02 +0100 Subject: [PATCH 2/2] Update README_seg.md --- README_seg.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README_seg.md b/README_seg.md index 567b607..ee637d7 100644 --- a/README_seg.md +++ b/README_seg.md @@ -41,7 +41,7 @@ where N.b. By default it is used FP32 inference - +[![tkDNN ShelfNet18 on MASA](https://img.youtube.com/vi/oiMzOLjo47A/0.jpg)](https://www.youtube.com/watch?v=oiMzOLjo47A "tkDNN ShelfNet18 on MASA") ## Existing tests and supported networks