diff --git a/models/intel/index.md b/models/intel/index.md index 11c4f11201d..a90e389b034 100644 --- a/models/intel/index.md +++ b/models/intel/index.md @@ -45,6 +45,9 @@ network to detect objects of the same type better. | [vehicle-detection-0200](./vehicle-detection-0200/description/vehicle-detection-0200.md) | 0.786 | 1.817 | | | X | | | | | [vehicle-detection-0201](./vehicle-detection-0201/description/vehicle-detection-0201.md) | 1.768 | 1.817 | | | X | | | | | [vehicle-detection-0202](./vehicle-detection-0202/description/vehicle-detection-0202.md) | 3.143 | 1.817 | | | X | | | | +| [vehicle-detection-0203](./vehicle-detection-0203/description/vehicle-detection-0203.md) | 112.34 | 24.11 | | | X | | | | +| [vehicle-detection-0204](./vehicle-detection-0204/description/vehicle-detection-0204.md) | 190.32 | 34.15 | | | X | | | | +| [vehicle-detection-0205](./vehicle-detection-0205/description/vehicle-detection-0205.md) | 212.22 | 36.56 | | | X | | | | | [person-vehicle-bike-detection-crossroad-0078](./person-vehicle-bike-detection-crossroad-0078/description/person-vehicle-bike-detection-crossroad-0078.md) | 3.964 | 1.178 | | X | X | X | | | | [person-vehicle-bike-detection-crossroad-1016](./person-vehicle-bike-detection-crossroad-1016/description/person-vehicle-bike-detection-crossroad-1016.md) | 3.560 | 2.887 | | X | X | X | | | | [person-vehicle-bike-detection-crossroad-yolov3-1020](./person-vehicle-bike-detection-crossroad-yolov3-1020/description/person-vehicle-bike-detection-crossroad-yolov3-1020.md) | 65.984 | 61.922 | | X | X | X | | | diff --git a/models/intel/vehicle-detection-0203/accuracy-check.yml b/models/intel/vehicle-detection-0203/accuracy-check.yml new file mode 100644 index 00000000000..9c7f44f36a1 --- /dev/null +++ b/models/intel/vehicle-detection-0203/accuracy-check.yml @@ -0,0 +1,22 @@ +models: + - name: vehicle-detection-0203 + + launchers: + - framework: dlsdk + adapter: + type: class_agnostic_detection + + datasets: + - name: crossroad_extra_untagged_vehicle_labels_from_1 + preprocessing: + - type: resize + dst_width: 1344 + dst_height: 800 + postprocessing: + - type: resize_prediction_boxes + rescale: True + - type: clip_boxes + apply_to: prediction + metrics: + - type: coco_orig_precision + include_boundaries: false diff --git a/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.md b/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.md new file mode 100644 index 00000000000..107108efa2f --- /dev/null +++ b/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.md @@ -0,0 +1,49 @@ +# vehicle-detection-0203 + +## Use Case and High-Level Description + +This is a vehicle detector that is based on ResNet18 +backbone with FPN and CascadeRCNN heads. + +## Example + +![](./vehicle-detection-0203.png) + +## Specification + +| Metric | Value | +|---------------------------------|-------------------------------------------| +| AP @ [ IoU=0.50:0.95 ] | 0.438 (internal test set) | +| GFlops | 112.34 | +| MParams | 24.11 | +| Source framework | PyTorch\* | + +Average Precision (AP) is defined as an area under +the [precision/recall](https://en.wikipedia.org/wiki/Precision_and_recall) +curve. + +## Performance + +## Inputs + +Name: `input`, shape: [1x3x800x1344] - An input image in the format [BxCxHxW], +where: + +- B - batch size +- C - number of channels +- H - image height +- W - image width + +Expected color order is BGR. + +## Outputs + +The net outputs blob with shape: [1, 1, N, 5], where N is the number of detected +bounding boxes. Each detection has the format + [`x_min`, `y_min`, `x_max`, `y_max`, `conf`], where: + - (`x_min`, `y_min`) - coordinates of the top left bounding box corner + - (`x_max`, `y_max`) - coordinates of the bottom right bounding box corner. + - `conf` - confidence for the predicted class + +## Legal Information +[*] Other names and brands may be claimed as the property of others. diff --git a/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.png b/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.png new file mode 100644 index 00000000000..1288e9f8e55 Binary files /dev/null and b/models/intel/vehicle-detection-0203/description/vehicle-detection-0203.png differ diff --git a/models/intel/vehicle-detection-0204/accuracy-check.yml b/models/intel/vehicle-detection-0204/accuracy-check.yml new file mode 100644 index 00000000000..e4a7f3656ad --- /dev/null +++ b/models/intel/vehicle-detection-0204/accuracy-check.yml @@ -0,0 +1,21 @@ +models: + - name: vehicle-detection-0204 + + launchers: + - framework: dlsdk + adapter: + type: class_agnostic_detection + datasets: + - name: crossroad_extra_untagged_vehicle_labels_from_1 + preprocessing: + - type: resize + dst_width: 1344 + dst_height: 800 + postprocessing: + - type: resize_prediction_boxes + rescale: True + - type: clip_boxes + apply_to: prediction + metrics: + - type: coco_orig_precision + include_boundaries: false diff --git a/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.md b/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.md new file mode 100644 index 00000000000..414fefe6144 --- /dev/null +++ b/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.md @@ -0,0 +1,49 @@ +# vehicle-detection-0204 + +## Use Case and High-Level Description + +This is a vehicle detector that is based on ResNet34 +backbone with FPN and CascadeRCNN heads. + +## Example + +![](./vehicle-detection-0204.png) + +## Specification + +| Metric | Value | +|---------------------------------|-------------------------------------------| +| AP @ [ IoU=0.50:0.95 ] | 0.473 (internal test set) | +| GFlops | 190.32 | +| MParams | 34.15 | +| Source framework | PyTorch\* | + +Average Precision (AP) is defined as an area under +the [precision/recall](https://en.wikipedia.org/wiki/Precision_and_recall) +curve. + +## Performance + +## Inputs + +Name: `input`, shape: [1x3x800x1344] - An input image in the format [BxCxHxW], +where: + +- B - batch size +- C - number of channels +- H - image height +- W - image width + +Expected color order is BGR. + +## Outputs + +The net outputs blob with shape: [1, 1, N, 5], where N is the number of detected +bounding boxes. Each detection has the format + [`x_min`, `y_min`, `x_max`, `y_max`, `conf`], where: + - (`x_min`, `y_min`) - coordinates of the top left bounding box corner + - (`x_max`, `y_max`) - coordinates of the bottom right bounding box corner. + - `conf` - confidence for the predicted class + +## Legal Information +[*] Other names and brands may be claimed as the property of others. diff --git a/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.png b/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.png new file mode 100644 index 00000000000..1288e9f8e55 Binary files /dev/null and b/models/intel/vehicle-detection-0204/description/vehicle-detection-0204.png differ diff --git a/models/intel/vehicle-detection-0205/accuracy-check.yml b/models/intel/vehicle-detection-0205/accuracy-check.yml new file mode 100644 index 00000000000..5e3eb18a838 --- /dev/null +++ b/models/intel/vehicle-detection-0205/accuracy-check.yml @@ -0,0 +1,21 @@ +models: + - name: vehicle-detection-0205 + + launchers: + - framework: dlsdk + adapter: + type: class_agnostic_detection + datasets: + - name: crossroad_extra_untagged_vehicle_labels_from_1 + preprocessing: + - type: resize + dst_width: 1344 + dst_height: 800 + postprocessing: + - type: resize_prediction_boxes + rescale: True + - type: clip_boxes + apply_to: prediction + metrics: + - type: coco_orig_precision + include_boundaries: false diff --git a/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.md b/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.md new file mode 100644 index 00000000000..2817e4f83e6 --- /dev/null +++ b/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.md @@ -0,0 +1,49 @@ +# vehicle-detection-0205 + +## Use Case and High-Level Description + +This is a vehicle detector that is based on ResNet50 +backbone with FPN and CascadeRCNN heads. + +## Example + +![](./vehicle-detection-0205.png) + +## Specification + +| Metric | Value | +|---------------------------------|-------------------------------------------| +| AP @ [ IoU=0.50:0.95 ] | 0.476 | +| GFlops | 212.22 | +| MParams | 36.56 | +| Source framework | PyTorch\* | + +Average Precision (AP) is defined as an area under +the [precision/recall](https://en.wikipedia.org/wiki/Precision_and_recall) +curve. + +## Performance + +## Inputs + +Name: `input`, shape: [1x3x800x1344] - An input image in the format [BxCxHxW], +where: + +- B - batch size +- C - number of channels +- H - image height +- W - image width + +Expected color order is BGR. + +## Outputs + +The net outputs blob with shape: [1, 1, N, 5], where N is the number of detected +bounding boxes. Each detection has the format + [`x_min`, `y_min`, `x_max`, `y_max`, `conf`], where: + - (`x_min`, `y_min`) - coordinates of the top left bounding box corner + - (`x_max`, `y_max`) - coordinates of the bottom right bounding box corner. + - `conf` - confidence for the predicted class + +## Legal Information +[*] Other names and brands may be claimed as the property of others. diff --git a/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.png b/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.png new file mode 100644 index 00000000000..1288e9f8e55 Binary files /dev/null and b/models/intel/vehicle-detection-0205/description/vehicle-detection-0205.png differ diff --git a/tools/accuracy_checker/configs/vehicle-detection-0203.yml b/tools/accuracy_checker/configs/vehicle-detection-0203.yml new file mode 100644 index 00000000000..1d35b49a132 --- /dev/null +++ b/tools/accuracy_checker/configs/vehicle-detection-0203.yml @@ -0,0 +1 @@ +../../../models/intel/vehicle-detection-0203/accuracy-check.yml diff --git a/tools/accuracy_checker/configs/vehicle-detection-0204.yml b/tools/accuracy_checker/configs/vehicle-detection-0204.yml new file mode 100644 index 00000000000..dea30e124b7 --- /dev/null +++ b/tools/accuracy_checker/configs/vehicle-detection-0204.yml @@ -0,0 +1 @@ +../../../models/intel/vehicle-detection-0204/accuracy-check.yml diff --git a/tools/accuracy_checker/configs/vehicle-detection-0205.yml b/tools/accuracy_checker/configs/vehicle-detection-0205.yml new file mode 100644 index 00000000000..d39b94ab0c5 --- /dev/null +++ b/tools/accuracy_checker/configs/vehicle-detection-0205.yml @@ -0,0 +1 @@ +../../../models/intel/vehicle-detection-0205/accuracy-check.yml diff --git a/tools/accuracy_checker/dataset_definitions.yml b/tools/accuracy_checker/dataset_definitions.yml index ab305e46128..acf899848f0 100644 --- a/tools/accuracy_checker/dataset_definitions.yml +++ b/tools/accuracy_checker/dataset_definitions.yml @@ -414,6 +414,15 @@ datasets: annotation: crossroad_extra_untagged_vehicle.pickle dataset_meta: crossroad_extra_untagged_vehicle.json + - name: crossroad_extra_untagged_vehicle_labels_from_1 + data_source: crossroad_extra_untagged/val_data + annotation_conversion: + converter: mscoco_detection + annotation_file: crossroad_extra_untagged/val_coco_no_bg_vehicle.json + has_background: True + annotation: crossroad_extra_untagged_vehicle_labels_from_1.pickle + dataset_meta: crossroad_extra_untagged_vehicle_labels_from_1.json + - name: pedestrian_and_vehicle_dataset data_source: val2017 annotation_conversion: