diff --git a/configs/segmenter/README.md b/configs/segmenter/README.md index d72daa300..45041c64c 100644 --- a/configs/segmenter/README.md +++ b/configs/segmenter/README.md @@ -71,7 +71,7 @@ In our default setting, pretrained models and their corresponding [ViT-AugReg](h | Segmenter Linear | ViT-S_16 | 512x512 | 160000 | 1.78 | 28.07 | 45.75 | 46.82 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) | | Segmenter Mask | ViT-S_16 | 512x512 | 160000 | 2.03 | 24.80 | 46.19 | 47.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json) | | Segmenter Mask | ViT-B_16 | 512x512 | 160000 | 4.20 | 13.20 | 49.60 | 51.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json) | -| Segmenter Mask | ViT-L_16 | 640x640 | 160000 | 16.56 | 2.62 | 52.16 | 53.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json) | +| Segmenter Mask | ViT-L_16 | 640x640 | 160000 | 16.99 | 3.03 | 51.65 | 53.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513-4783a347.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513.log.json) | Note: diff --git a/configs/segmenter/segmenter.yml b/configs/segmenter/segmenter.yml index dc6e68d3d..af1df7d09 100644 --- a/configs/segmenter/segmenter.yml +++ b/configs/segmenter/segmenter.yml @@ -101,25 +101,25 @@ Models: mIoU(ms+flip): 51.07 Config: configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth -- Name: segmenter_vit-l_mask_8x1_512x512_160k_ade20k +- Name: segmenter_vit-l_mask_8x1_640x640_160k_ade20k In Collection: Segmenter Metadata: backbone: ViT-L_16 crop size: (640,640) lr schd: 160000 inference time (ms/im): - - value: 381.68 + - value: 330.03 hardware: V100 backend: PyTorch batch size: 1 mode: FP32 resolution: (640,640) - Training Memory (GB): 16.56 + Training Memory (GB): 16.99 Results: - Task: Semantic Segmentation Dataset: ADE20K Metrics: - mIoU: 52.16 - mIoU(ms+flip): 53.65 - Config: configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py - Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth + mIoU: 51.65 + mIoU(ms+flip): 53.58 + Config: configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py + Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513-4783a347.pth diff --git a/configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py b/configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py similarity index 91% rename from configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py rename to configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py index 718657093..4e6a0b185 100644 --- a/configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py +++ b/configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py @@ -1,6 +1,6 @@ _base_ = [ '../_base_/models/segmenter_vit-b16_mask.py', - '../_base_/datasets/ade20k.py', '../_base_/default_runtime.py', + '../_base_/datasets/ade20k_640x640.py', '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py' ] checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segmenter/vit_large_p16_384_20220308-d4efb41d.pth' # noqa @@ -29,7 +29,7 @@ crop_size = (640, 640) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', reduce_zero_label=True), - dict(type='Resize', img_scale=(2048, 640), ratio_range=(0.5, 2.0)), + dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), @@ -42,7 +42,7 @@ test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', - img_scale=(2048, 640), + img_scale=(2560, 640), # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75], flip=False, transforms=[