Add several onnx models (#121)

Author: sovrasov

tests/python/accuracy/prepare_data.py

@@ -54,15 +54,20 @@ def prepare_data(data_dir="./data"):
     retrieve_otx_model(args.data_dir, "mlc_efficient_b0_voc")
     retrieve_otx_model(args.data_dir, "mlc_efficient_v2s_voc")
     retrieve_otx_model(args.data_dir, "det_mobilenetv2_atss_bccd")
+    retrieve_otx_model(args.data_dir, "det_mobilenetv2_atss_bccd_onnx", "onnx")
     retrieve_otx_model(args.data_dir, "cls_mobilenetv3_large_cars")
     retrieve_otx_model(args.data_dir, "cls_mobilenetv3_large_cars", "onnx")
     retrieve_otx_model(args.data_dir, "cls_efficient_b0_cars")
     retrieve_otx_model(args.data_dir, "cls_efficient_v2s_cars")
     retrieve_otx_model(args.data_dir, "Lite-hrnet-18")
     retrieve_otx_model(args.data_dir, "Lite-hrnet-18_mod2")
     retrieve_otx_model(args.data_dir, "Lite-hrnet-s_mod2")
+    retrieve_otx_model(args.data_dir, "Lite-hrnet-s_mod2", "onnx")
     retrieve_otx_model(args.data_dir, "Lite-hrnet-x-mod3")
     retrieve_otx_model(args.data_dir, "is_efficientnetb2b_maskrcnn_coco_reduced")
+    retrieve_otx_model(
+        args.data_dir, "is_efficientnetb2b_maskrcnn_coco_reduced_onnx", "onnx"
+    )
     retrieve_otx_model(args.data_dir, "is_resnet50_maskrcnn_coco_reduced")
     retrieve_otx_model(args.data_dir, "mobilenet_v3_large_hc_cf")
     retrieve_otx_model(args.data_dir, "classification_model_with_xai_head")

tests/python/accuracy/public_scope.json

@@ -39,6 +39,16 @@
             }
         ]
     },
+    {
+        "name": "otx_models/Lite-hrnet-s_mod2.onnx",
+        "type": "SegmentationModel",
+        "test_data": [
+            {
+                "image": "coco128/images/train2017/000000000074.jpg",
+                "reference": ["0: 0.563, 1: 0.437, [426,640,2], [0], [0]; object: 0.520, 26, object: 0.530, 42, object: 0.501, 4, object: 0.507, 27, object: 0.503, 8, object: 0.502, 6, object: 0.505, 18, object: 0.504, 13, object: 0.524, 87, object: 0.521, 89, object: 0.757, 2706, "]
+            }
+        ]
+    },
     {
         "name": "otx_models/Lite-hrnet-x-mod3.xml",
         "type": "SegmentationModel",
@@ -89,6 +99,16 @@
             }
         ]
     },
+    {
+        "name": "otx_models/det_mobilenetv2_atss_bccd_onnx.onnx",
+        "type": "DetectionModel",
+        "test_data": [
+            {
+                "image": "BloodImage_00007.jpg",
+                "reference": ["494, 159, 637, 308, 2 (WBC): 0.697; 28, 139, 135, 228, 1 (RBC): 0.628; 535, 375, 638, 479, 1 (RBC): 0.524; 513, 8, 633, 152, 1 (RBC): 0.430; 21, 291, 143, 399, 1 (RBC): 0.422; 196, 86, 410, 286, 1 (RBC): 0.422; [0]; [0]"]
+            }
+        ]
+    },
     {
         "name": "resnet-18-pytorch",
         "type": "ClassificationModel",
@@ -199,6 +219,16 @@
             }
         ]
     },
+    {
+        "name": "otx_models/is_efficientnetb2b_maskrcnn_coco_reduced_onnx.onnx",
+        "type": "MaskRCNNModel",
+        "test_data": [
+            {
+                "image": "coco128/images/train2017/000000000074.jpg",
+                "reference": ["458, 106, 495, 150, 1 (person): 0.818, 852, RotatedRect: 478.119 130.332 28.677 46.408 46.637; 0, 30, 178, 323, 2 (bicycle): 0.753, 26728, RotatedRect: 79.739 177.262 251.785 156.656 87.397; 0; [0]; person: 0.818, 139; bicycle: 0.753, 622; "]
+            }
+        ]
+    },
     {
         "name": "otx_models/is_resnet50_maskrcnn_coco_reduced.xml",
         "type": "MaskRCNNModel",