From ea36faa37e1866e7928158f40913c7f77082aee4 Mon Sep 17 00:00:00 2001 From: junting Date: Tue, 2 Jul 2019 17:54:55 +0800 Subject: [PATCH 1/5] Update README.md --- README.md | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/README.md b/README.md index bb8685c..d1ecc2d 100644 --- a/README.md +++ b/README.md @@ -122,6 +122,28 @@ Img2Vid Architecture - Cityscapes - Cityscapes dataset can be downloaded from the [official website](https://www.cityscapes-dataset.com/) (registration required). - We apply Deeplab-V3 [github-repo](https://github.com/tensorflow/models/tree/master/research/deeplab) to get the corresponding semantic maps. + - We organize the dataset following as below: + ``` + seg2vid + ├── authors + ├── figs + ├── gifs + ├── logos + ├── pretrained_models + ├── src + ├── data + │ ├── cityscapes + │ │ ├── leftImg8bit_sequence + │ │ │ ├── train_512x256 + │ │ │ ├── val_512x256 + │ │ │ ├── val_pix2pixHD + │ │ │ ├── train_semantic_segmask + │ │ │ ├── val_semantic_segmask + │ │ ├── gtFine + │ │ │ ├── train + │ │ │ ├── val + ``` + - KTH - We use the [KTH human action dataset](http://www.nada.kth.se/cvap/actions/) dataset, and we follow the data processing in [svg](https://github.com/edenton/svg). - UCF-101 From 8c321f5d27de82225d09453afecd17c889f8971d Mon Sep 17 00:00:00 2001 From: junting Date: Tue, 2 Jul 2019 17:58:26 +0800 Subject: [PATCH 2/5] Update README.md --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index d1ecc2d..30965fb 100644 --- a/README.md +++ b/README.md @@ -150,9 +150,13 @@ Img2Vid Architecture - UCF-101 dataset can be downloader from the [official website](https://www.crcv.ucf.edu/research/data-sets/human-actions/ucf101/) ### Testing -- To do. +``` + python -u test_refine_w_mask_two_path.py --suffix refine_w_mask_two_path --dataset cityscapes_two_path +``` ### Training -- To do. +``` + python -u train_refine_multigpu_w_mask_two_path.py --batch_size 8 --dataset cityscapes_two_path +``` ## Software frameworks Our paper presents two convolutional neural networks, one correspends to the Generator (Saliency Prediction Network) and the another is the Discriminator for the adversarial training. To compute saliency maps only the Generator is needed. From 205bc9fc4d0035eff796a350fae0c73b2cfab85b Mon Sep 17 00:00:00 2001 From: junting Date: Tue, 2 Jul 2019 22:53:55 +0800 Subject: [PATCH 3/5] Update README.md --- README.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/README.md b/README.md index 30965fb..aba0763 100644 --- a/README.md +++ b/README.md @@ -135,13 +135,21 @@ Img2Vid Architecture │ ├── cityscapes │ │ ├── leftImg8bit_sequence │ │ │ ├── train_512x256 + │ │ │ │ ├── aachen + │ │ │ │ │ ├── aachen_000003_000019_leftImg8bit.png │ │ │ ├── val_512x256 │ │ │ ├── val_pix2pixHD + │ │ │ │ ├── frankfurt + │ │ │ │ │ ├── frankfurt_000000_000294_pix2pixHD.png │ │ │ ├── train_semantic_segmask │ │ │ ├── val_semantic_segmask + │ │ │ │ ├── frankfurt + │ │ │ │ │ ├── frankfurt_000000_000275_ssmask.png │ │ ├── gtFine │ │ │ ├── train │ │ │ ├── val + │ │ │ │ ├── frankfurt + │ │ │ │ │ ├── frankfurt_000000_000294_gtFine_instanceIds.png ``` - KTH From 28e17aff6060b50cf7c6e68ab9ac5e3d6073d2c2 Mon Sep 17 00:00:00 2001 From: junting Date: Tue, 2 Jul 2019 23:00:35 +0800 Subject: [PATCH 4/5] Update README.md --- README.md | 3 --- 1 file changed, 3 deletions(-) diff --git a/README.md b/README.md index aba0763..6806fa1 100644 --- a/README.md +++ b/README.md @@ -165,9 +165,6 @@ Img2Vid Architecture ``` python -u train_refine_multigpu_w_mask_two_path.py --batch_size 8 --dataset cityscapes_two_path ``` -## Software frameworks - -Our paper presents two convolutional neural networks, one correspends to the Generator (Saliency Prediction Network) and the another is the Discriminator for the adversarial training. To compute saliency maps only the Generator is needed. ### Seg2Vid on Pytorch From ffde5643a0ca68478e6a6e88aa27e4c91f10a3dc Mon Sep 17 00:00:00 2001 From: junting Date: Wed, 3 Jul 2019 10:08:59 +0800 Subject: [PATCH 5/5] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6806fa1..ccfb8c5 100644 --- a/README.md +++ b/README.md @@ -87,7 +87,7 @@ Img2Vid Architecture [Predicted Flow 1]:https://github.com/junting/seg2vid/blob/junting/gifs/flow/flow_1.gif [Predicted Flow 2]:https://github.com/junting/seg2vid/blob/junting/gifs/flow/flow_2.gif -### Cityscapes 24 frames (Prediction given the 1st frame ans its segmetation mask) +### Cityscapes 24 frames (Prediction given the 1st frame and its segmetation mask) | ![Long Video 1] | ![Long Video 2] | ![Long Video 3] | |:-:|:-:|:-:|