Skip to content

models mmd 3x vfnet_x101 64x4d mdconv c3 c5_fpn_ms 2x_coco

Jump to bottom
github-actions[bot] edited this page Dec 20, 2023 · 10 revisions

mmd-3x-vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco

Overview

vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco model is from OpenMMLab's MMDetection library. This model is reported to obtain box AP of 50.8 for object-detection task on COCO dataset. To understand the naming style used, please refer to MMDetection's Config Name Style.

Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by ∼2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors.

The above abstract is from MMDetection website. Review the original-model-card to understand the data used to train the model, evaluation metrics, license, intended uses, limitations and bias before using the model.

Inference samples

Inference type Python sample (Notebook) CLI with YAML
Real time image-object-detection-online-endpoint.ipynb image-object-detection-online-endpoint.sh
Batch image-object-detection-batch-endpoint.ipynb image-object-detection-batch-endpoint.sh

Finetuning samples

Task Use case Dataset Python sample (Notebook) CLI with YAML
Image object detection Image object detection fridgeObjects fridgeobjects-object-detection.ipynb fridgeobjects-object-detection.sh

Model Evaluation

Task Use case Dataset Python sample (Notebook)
Image object detection Image object detection fridgeObjects image-object-detection.ipynb

Sample inputs and outputs (for real-time inference)

Sample input

{
  "input_data": {
    "columns": [
      "image"
    ],
    "index": [0, 1],
    "data": ["image1", "image2"]
  }
}

Note: "image1" and "image2" string should be in base64 format or publicly accessible urls.

Sample output

[
    {
        "boxes": [
            {
                "box": {
                    "topX": 0.1,
                    "topY": 0.2,
                    "bottomX": 0.8,
                    "bottomY": 0.7
                },
                "label": "carton",
                "score": 0.98
            }
        ]
    },
    {
        "boxes": [
            {
                "box": {
                    "topX": 0.2,
                    "topY": 0.3,
                    "bottomX": 0.6,
                    "bottomY": 0.5
                },
                "label": "can",
                "score": 0.97
            }
        ]
    }
]

Note: Please refer to object detection output data schema for more detail.

Model inference - visualization for a sample image

od visualization

Version: 9

Tags

Preview SharedComputeCapacityEnabled openmmlab_model_id : mmd-3x-vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco training_dataset : COCO license : apache-2.0 model_specific_defaults : ordereddict({'apply_deepspeed': 'false', 'apply_ort': 'false'}) task : object-detection inference_compute_allow_list : ['Standard_DS3_v2', 'Standard_D4a_v4', 'Standard_D4as_v4', 'Standard_DS4_v2', 'Standard_D8a_v4', 'Standard_D8as_v4', 'Standard_DS5_v2', 'Standard_D16a_v4', 'Standard_D16as_v4', 'Standard_D32a_v4', 'Standard_D32as_v4', 'Standard_D48a_v4', 'Standard_D48as_v4', 'Standard_D64a_v4', 'Standard_D64as_v4', 'Standard_D96a_v4', 'Standard_D96as_v4', 'Standard_FX4mds', 'Standard_F8s_v2', 'Standard_FX12mds', 'Standard_F16s_v2', 'Standard_F32s_v2', 'Standard_F48s_v2', 'Standard_F64s_v2', 'Standard_F72s_v2', 'Standard_FX24mds', 'Standard_FX36mds', 'Standard_FX48mds', 'Standard_E4s_v3', 'Standard_E8s_v3', 'Standard_E16s_v3', 'Standard_E32s_v3', 'Standard_E48s_v3', 'Standard_E64s_v3', 'Standard_NC4as_T4_v3', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v3', 'Standard_NC64as_T4_v3', 'Standard_NC24ads_A100_v4', 'Standard_NC48ads_A100_v4', 'Standard_NC96ads_A100_v4', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4', 'Standard_ND40rs_v2'] evaluation_compute_allow_list : ['Standard_NC4as_T4_v3', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v3', 'Standard_NC4as_T4_v3', 'Standard_NC24ads_A100_v4', 'Standard_NC48ads_A100_v4', 'Standard_NC96ads_A100_v4', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4', 'Standard_ND40rs_v2'] finetune_compute_allow_list : ['Standard_NC4as_T4_v3', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v3', 'Standard_NC64as_T4_v3', 'Standard_NC24ads_A100_v4', 'Standard_NC48ads_A100_v4', 'Standard_NC96ads_A100_v4', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4', 'Standard_ND40rs_v2']

View in Studio: https://ml.azure.com/registries/azureml/models/mmd-3x-vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco/version/9

License: apache-2.0

Properties

SHA: fff646d3dda72d8c794471bfaa75b4db0adb7610

evaluation-min-sku-spec: 4|1|28|176

evaluation-recommended-sku: Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

finetune-min-sku-spec: 4|1|28|176

finetune-recommended-sku: Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

finetuning-tasks: image-object-detection

inference-min-sku-spec: 4|0|14|28

inference-recommended-sku: Standard_DS3_v2, Standard_D4a_v4, Standard_D4as_v4, Standard_DS4_v2, Standard_D8a_v4, Standard_D8as_v4, Standard_DS5_v2, Standard_D16a_v4, Standard_D16as_v4, Standard_D32a_v4, Standard_D32as_v4, Standard_D48a_v4, Standard_D48as_v4, Standard_D64a_v4, Standard_D64as_v4, Standard_D96a_v4, Standard_D96as_v4, Standard_FX4mds, Standard_F8s_v2, Standard_FX12mds, Standard_F16s_v2, Standard_F32s_v2, Standard_F48s_v2, Standard_F64s_v2, Standard_F72s_v2, Standard_FX24mds, Standard_FX36mds, Standard_FX48mds, Standard_E4s_v3, Standard_E8s_v3, Standard_E16s_v3, Standard_E32s_v3, Standard_E48s_v3, Standard_E64s_v3, Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

Wiki menu

Clone this wiki locally