models mmd 3x rtmdet ins_x_8xb16 300e_coco - Azure/azureml-assets GitHub Wiki

mmd-3x-rtmdet-ins_x_8xb16-300e_coco

Overview

rtmdet-ins_x_8xb16-300e_coco model is from OpenMMLab's MMDetection library. In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks.

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.

Training Details

Training Data

The model developers used COCO dataset for training the model.

Training Procedure

Training Techniques:

  • AdamW
  • Flat Cosine Annealing

Training Memory (GB): 33.7

Epochs: 300

Training Resources: 8x A100 GPUs

Evaluation Results

mask AP: 44.6

License

apache-2.0

Inference samples

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

Finetuning samples

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

Model Evaluation

Task Use case Dataset Python sample (Notebook)
Image instance segmentation Image instance segmentation fridgeObjects image-instance-segmentation.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,
                "polygon": [
                    [ 0.576, 0.680,  …]
                ]
            }
        ]
    },
    {
        "boxes": [
            {
                "box": {
                    "topX": 0.2,
                    "topY": 0.3,
                    "bottomX": 0.6,
                    "bottomY": 0.5
                },
                "label": "can",
                "score": 0.97,
                "polygon": [
                    [ 0.58, 0.7,  …]
                ]
            }
        ]
    }
]

Note: Please refer to instance segmentation output data schema for more detail.

Model inference - visualization for a sample image

is visualization

Version: 4

Tags

SharedComputeCapacityEnabled openmmlab_model_id : mmd-3x-rtmdet-ins_x_8xb16-300e_coco training_dataset : COCO license : apache-2.0 model_specific_defaults : ordereddict({'apply_deepspeed': 'false', 'apply_ort': 'false'}) task : image-segmentation 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_NC64as_T4_v3', '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_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-rtmdet-ins_x_8xb16-300e_coco/version/4

License: apache-2.0

Properties

SharedComputeCapacityEnabled: True

SHA: 4d77feb7a8e5967686d9bf922d2bb61162de57d2

finetuning-tasks: image-instance-segmentation

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_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

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_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

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

⚠️ **GitHub.com Fallback** ⚠️