#detectron2-serve-model .el-tabs.el-tabs-cards .el-radio { display: flex; align-items: start; /*margin-bottom: 10px;*/ margin-left: 0; white-space: normal; } #detectron2-serve-model .el-tabs.el-tabs-cards .el-radio__label div { color: #7f858e; font-size: 13px; } .beautiful-table { border-collapse: collapse; } .beautiful-table tr:nth-child(2n) { background-color: #f6f8fa; } .beautiful-table td, .beautiful-table th { border: 1px solid #dfe2e5; padding: 6px 13px; text-align: center; line-height: 20px; } #detectron2-serve-model .el-tabs.el-tabs-cards { border-radius: 4px; box-shadow: none; } #detectron2-serve-model .el-tabs.el-tabs-cards .el-tabs__header { background-color: #f6fafd; } #detectron2-serve-model .el-tabs.el-tabs-cards .el-tabs__nav { float: none; display: flex; justify-content: space-between; } #detectron2-serve-model .el-tabs.el-tabs-cards .el-tabs__item { flex: 1; margin-bottom: -3px; padding: 9px 16px 13px; height: auto; line-height: normal; border-radius: 4px; }

Custom weights

load custom weights from Team Files

Pretrained models

weights pretrained on popular datasets

{{row["subtitle"]}}
{{model[column.key]}} {{model[column.key]}}

Detectron2 provides us Mask R-CNN Instance Segmentation
baselines based on 3 different backbone combinations

FPN: Use a ResNet+FPN backbone with standard conv and FC heads for mask and box prediction, respectively. It obtains the best speed/accuracy tradeoff, but the other two are still useful for research.
C4: Use a ResNet conv4 backbone with conv5 head. The original baseline in the Faster R-CNN paper.
DC5 (Dilated-C5): Use a ResNet conv5 backbone with dilations in conv5, and standard conv and FC heads for mask and box prediction, respectively. This is used by the Deformable ConvNet paper.

more about models
(find model using model id)

Categories

Types

Tags

interactive detection

Serve OWL-ViT

Apply OWL-ViT To Images Project