Collections: - Name: YOLACT Metadata: Training Data: COCO Training Techniques: - SGD with Momentum - Weight Decay Training Resources: 8x V100 GPUs Architecture: - FPN - ResNet Paper: URL: https://arxiv.org/abs/1904.02689 Title: 'YOLACT: Real-time Instance Segmentation' README: configs/yolact/README.md Code: URL: https://github.com/open-mmlab/mmdetection/blob/v2.5.0/mmdet/models/detectors/yolact.py#L9 Version: v2.5.0 Models: - Name: yolact_r50_1x8_coco In Collection: YOLACT Config: configs/yolact/yolact_r50_1xb8-55e_coco.py Metadata: Training Resources: 1x V100 GPU Batch Size: 8 Epochs: 55 inference time (ms/im): - value: 23.53 hardware: V100 backend: PyTorch batch size: 1 mode: FP32 resolution: (550, 550) Results: - Task: Instance Segmentation Dataset: COCO Metrics: mask AP: 29.0 Weights: https://download.openmmlab.com/mmdetection/v2.0/yolact/yolact_r50_1x8_coco/yolact_r50_1x8_coco_20200908-f38d58df.pth - Name: yolact_r50_8x8_coco In Collection: YOLACT Config: configs/yolact/yolact_r50_8xb8-55e_coco.py Metadata: Batch Size: 64 Epochs: 55 inference time (ms/im): - value: 23.53 hardware: V100 backend: PyTorch batch size: 1 mode: FP32 resolution: (550, 550) Results: - Task: Instance Segmentation Dataset: COCO Metrics: mask AP: 28.4 Weights: https://download.openmmlab.com/mmdetection/v2.0/yolact/yolact_r50_8x8_coco/yolact_r50_8x8_coco_20200908-ca34f5db.pth - Name: yolact_r101_1x8_coco In Collection: YOLACT Config: configs/yolact/yolact_r101_1xb8-55e_coco.py Metadata: Training Resources: 1x V100 GPU Batch Size: 8 Epochs: 55 inference time (ms/im): - value: 29.85 hardware: V100 backend: PyTorch batch size: 1 mode: FP32 resolution: (550, 550) Results: - Task: Instance Segmentation Dataset: COCO Metrics: mask AP: 30.4 Weights: https://download.openmmlab.com/mmdetection/v2.0/yolact/yolact_r101_1x8_coco/yolact_r101_1x8_coco_20200908-4cbe9101.pth