Fix YOLO-NAS / Small fixes

config_infer_primary_yolonas_custom.txt

@@ -0,0 +1,29 @@
+[property]
+gpu-id=0
+net-scale-factor=1
+model-color-format=0
+onnx-file=yolo_nas_s_coco.onnx
+model-engine-file=model_b1_gpu0_fp32.engine
+#int8-calib-file=calib.table
+labelfile-path=labels.txt
+batch-size=1
+network-mode=0
+num-detected-classes=80
+interval=0
+gie-unique-id=1
+process-mode=1
+network-type=0
+cluster-mode=2
+maintain-aspect-ratio=1
+symmetric-padding=0
+#force-implicit-batch-dim=1
+#workspace-size=1000
+parse-bbox-func-name=NvDsInferParseYoloE
+#parse-bbox-func-name=NvDsInferParseYoloECuda
+custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
+engine-create-func-name=NvDsInferYoloCudaEngineGet
+
+[class-attrs-all]
+nms-iou-threshold=0.45
+pre-cluster-threshold=0.25
+topk=300

docs/DAMOYOLO.md

@@ -82,7 +82,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 11 or lower. The default opset is 11.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 11 or lower. The default opset is 11.
 
 ```
 --opset 11

docs/PPYOLOE.md

@@ -59,7 +59,7 @@ python3 export_ppyoloe.py -w ppyoloe_plus_crn_s_80e_coco.pdparams -c configs/ppy
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
 
 ```
 --opset 12
@@ -134,7 +134,7 @@ parse-bbox-func-name=NvDsInferParseYoloE
 ...
 ```
 
-**NOTE**: If you use the **legacy** model, you should edit the `config_infer_primary_ppyoloe.txt` file.
+**NOTE**: If you are using the **legacy** model, you should edit the `config_infer_primary_ppyoloe.txt` file.
 
 **NOTE**: The **PP-YOLOE+ and PP-YOLOE legacy** do not resize the input with padding. To get better accuracy, use
 
@@ -182,7 +182,7 @@ force-implicit-batch-dim=1
 config-file=config_infer_primary_ppyoloe_plus.txt
 ```
 
-**NOTE**: If you use the **legacy** model, you should edit it to `config_infer_primary_ppyoloe.txt`.
+**NOTE**: If you are using the **legacy** model, you should edit it to `config_infer_primary_ppyoloe.txt`.
 
 ##
 

docs/YOLONAS.md

@@ -115,7 +115,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 14.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 14.
 
 ```
 --opset 12
@@ -190,6 +190,8 @@ parse-bbox-func-name=NvDsInferParseYoloE
 ...
 ```
 
+**NOTE**: If you are using a custom model, you should edit the `config_infer_primary_yolonas_custom.txt` file.
+
 **NOTE**: The **YOLO-NAS** resizes the input with left/top padding. To get better accuracy, use
 
 ```

docs/YOLOR.md

@@ -100,7 +100,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
 
 ```
 --opset 12

docs/YOLOX.md

@@ -64,7 +64,7 @@ python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --dynamic
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
 
 ```
 --opset 12
@@ -139,7 +139,7 @@ parse-bbox-func-name=NvDsInferParseYolo
 ...
 ```
 
-**NOTE**: If you use the **legacy** model, you should edit the `config_infer_primary_yolox_legacy.txt` file.
+**NOTE**: If you are using the **legacy** model, you should edit the `config_infer_primary_yolox_legacy.txt` file.
 
 **NOTE**: The **YOLOX and YOLOX legacy** resize the input with left/top padding. To get better accuracy, use
 
@@ -188,7 +188,7 @@ force-implicit-batch-dim=1
 config-file=config_infer_primary_yolox.txt
 ```
 
-**NOTE**: If you use the **legacy** model, you should edit it to `config_infer_primary_yolox_legacy.txt`.
+**NOTE**: If you are using the **legacy** model, you should edit it to `config_infer_primary_yolox_legacy.txt`.
 
 ##
 

docs/YOLOv5.md

@@ -92,7 +92,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 17.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 17.
 
 ```
 --opset 12

docs/YOLOv6.md

@@ -92,7 +92,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 13.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 13.
 
 ```
 --opset 12

docs/YOLOv7.md

@@ -94,7 +94,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
 
 ```
 --opset 12

docs/YOLOv8.md

@@ -85,7 +85,7 @@ or
 --batch 4
 ```
 
-**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 16.
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 16.
 
 ```
 --opset 12