diff --git a/README.md b/README.md index 775a165..3ae4ab2 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,7 @@ NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 configuration -------------------------------------------------------------------------------------------------- ### YOLO-Pose: https://github.com/marcoslucianops/DeepStream-Yolo-Pose +### YOLO-Seg: https://github.com/marcoslucianops/DeepStream-Yolo-Seg -------------------------------------------------------------------------------------------------- ### Important: please export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to your model -------------------------------------------------------------------------------------------------- @@ -29,13 +30,14 @@ NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 configuration * INT8 calibration (PTQ) for Darknet and ONNX exported models * New output structure (fix wrong output on DeepStream < 6.2) - it need to export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to your model * **YOLO-Pose: https://github.com/marcoslucianops/DeepStream-Yolo-Pose** +* **YOLO-Seg: https://github.com/marcoslucianops/DeepStream-Yolo-Seg** ## ### Getting started * [Requirements](#requirements) -* [Suported models](#supported-models) +* [Supported models](#supported-models) * [Benchmarks](docs/benchmarks.md) * [dGPU installation](docs/dGPUInstalation.md) * [Basic usage](#basic-usage) @@ -156,7 +158,7 @@ NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 configuration ## -### Suported models +### Supported models * [Darknet](https://github.com/AlexeyAB/darknet) * [MobileNet-YOLO](https://github.com/dog-qiuqiu/MobileNet-Yolo) diff --git a/docs/DAMOYOLO.md b/docs/DAMOYOLO.md index e424fbc..3e73201 100644 --- a/docs/DAMOYOLO.md +++ b/docs/DAMOYOLO.md @@ -166,6 +166,7 @@ parse-bbox-func-name=NvDsInferParseYoloE **NOTE**: The **DAMO-YOLO** do not resize the input with padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=0 ... @@ -174,6 +175,7 @@ maintain-aspect-ratio=0 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/PPYOLOE.md b/docs/PPYOLOE.md index cd392a9..913468b 100644 --- a/docs/PPYOLOE.md +++ b/docs/PPYOLOE.md @@ -145,6 +145,7 @@ parse-bbox-func-name=NvDsInferParseYoloE **NOTE**: The **PP-YOLOE+ and PP-YOLOE legacy** do not resize the input with padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=0 ... @@ -153,6 +154,7 @@ maintain-aspect-ratio=0 **NOTE**: The **PP-YOLOE+** uses zero mean normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values. ``` +[property] ... net-scale-factor=0.0039215697906911373 ... @@ -163,6 +165,7 @@ net-scale-factor=0.0039215697906911373 Default: `mean = 0.485, 0.456, 0.406` and `std = 0.229, 0.224, 0.225` ``` +[property] ... net-scale-factor=0.0173520735727919486 offsets=123.675;116.28;103.53 @@ -172,6 +175,7 @@ offsets=123.675;116.28;103.53 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLONAS.md b/docs/YOLONAS.md index 840e8ed..29553b5 100644 --- a/docs/YOLONAS.md +++ b/docs/YOLONAS.md @@ -201,6 +201,7 @@ parse-bbox-func-name=NvDsInferParseYoloE **NOTE**: The **YOLO-NAS** resizes the input with left/top padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=0 @@ -210,6 +211,7 @@ symmetric-padding=0 **NOTE**: The **pre-trained YOLO-NAS** uses zero mean normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values. ``` +[property] ... net-scale-factor=0.0039215697906911373 ... @@ -218,6 +220,7 @@ net-scale-factor=0.0039215697906911373 **NOTE**: The **custom YOLO-NAS** uses no normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values. ``` +[property] ... net-scale-factor=1 ... @@ -226,6 +229,7 @@ net-scale-factor=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOR.md b/docs/YOLOR.md index 1809b45..77c8bcb 100644 --- a/docs/YOLOR.md +++ b/docs/YOLOR.md @@ -184,6 +184,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOR** resizes the input with center padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=1 @@ -193,6 +194,7 @@ symmetric-padding=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOX.md b/docs/YOLOX.md index 88e6404..43f65ee 100644 --- a/docs/YOLOX.md +++ b/docs/YOLOX.md @@ -150,6 +150,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOX and YOLOX legacy** resize the input with left/top padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=0 @@ -159,6 +160,7 @@ symmetric-padding=0 **NOTE**: The **YOLOX** uses no normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values. ``` +[property] ... net-scale-factor=1 ... @@ -169,6 +171,7 @@ net-scale-factor=1 Default: `mean = 0.485, 0.456, 0.406` and `std = 0.229, 0.224, 0.225` ``` +[property] ... net-scale-factor=0.0173520735727919486 offsets=123.675;116.28;103.53 @@ -178,6 +181,7 @@ offsets=123.675;116.28;103.53 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOv5.md b/docs/YOLOv5.md index 11fb196..e1fed34 100644 --- a/docs/YOLOv5.md +++ b/docs/YOLOv5.md @@ -176,6 +176,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOv5** resizes the input with center padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=1 @@ -185,6 +186,7 @@ symmetric-padding=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOv6.md b/docs/YOLOv6.md index df4a8f5..0c75cec 100644 --- a/docs/YOLOv6.md +++ b/docs/YOLOv6.md @@ -176,6 +176,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOv6** resizes the input with center padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=1 @@ -185,6 +186,7 @@ symmetric-padding=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOv7.md b/docs/YOLOv7.md index 3669952..5e7cda8 100644 --- a/docs/YOLOv7.md +++ b/docs/YOLOv7.md @@ -178,6 +178,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOv7** resizes the input with center padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=1 @@ -187,6 +188,7 @@ symmetric-padding=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ... diff --git a/docs/YOLOv8.md b/docs/YOLOv8.md index c5d23c6..68edd1d 100644 --- a/docs/YOLOv8.md +++ b/docs/YOLOv8.md @@ -169,6 +169,7 @@ parse-bbox-func-name=NvDsInferParseYolo **NOTE**: The **YOLOv8** resizes the input with center padding. To get better accuracy, use ``` +[property] ... maintain-aspect-ratio=1 symmetric-padding=1 @@ -178,6 +179,7 @@ symmetric-padding=1 **NOTE**: By default, the dynamic batch-size is set. To use implicit batch-size, uncomment the line ``` +[property] ... force-implicit-batch-dim=1 ...