Go to the source code of this file.
Data Structures | |
| struct | _GstNvInferEval |
| GstNvInferEval: More... | |
| struct | _GstNvInferEvalClass |
Macros | |
| #define | GST_TYPE_NVINFEREVAL (gst_nv_infer_eval_get_type ()) |
| SECTION:element-nvinfereval. More... | |
| #define | GST_NVINFEREVAL(obj) (G_TYPE_CHECK_INSTANCE_CAST ((obj), GST_TYPE_NVINFEREVAL, GstNvInferEval)) |
| #define | GST_NVINFEREVAL_CLASS(klass) (G_TYPE_CHECK_CLASS_CAST ((klass), GST_TYPE_NVINFEREVAL, GstNvInferEvalClass)) |
| #define | GST_IS_NVINFEREVAL(obj) (G_TYPE_CHECK_INSTANCE_TYPE ((obj), GST_TYPE_NVINFEREVAL)) |
| #define | GST_IS_NVINFEREVAL_CLASS(klass) (G_TYPE_CHECK_CLASS_TYPE ((klass), GST_TYPE_NVINFEREVAL)) |
Typedefs | |
| typedef struct _GstNvInferEval | GstNvInferEval |
| typedef struct _GstNvInferEvalClass | GstNvInferEvalClass |
Functions | |
| GType | gst_nv_infer_eval_get_type (void) |
| #define GST_IS_NVINFEREVAL | ( | obj | ) | (G_TYPE_CHECK_INSTANCE_TYPE ((obj), GST_TYPE_NVINFEREVAL)) |
Definition at line 63 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| #define GST_IS_NVINFEREVAL_CLASS | ( | klass | ) | (G_TYPE_CHECK_CLASS_TYPE ((klass), GST_TYPE_NVINFEREVAL)) |
Definition at line 65 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| #define GST_NVINFEREVAL | ( | obj | ) | (G_TYPE_CHECK_INSTANCE_CAST ((obj), GST_TYPE_NVINFEREVAL, GstNvInferEval)) |
Definition at line 59 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| #define GST_NVINFEREVAL_CLASS | ( | klass | ) | (G_TYPE_CHECK_CLASS_CAST ((klass), GST_TYPE_NVINFEREVAL, GstNvInferEvalClass)) |
Definition at line 61 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| #define GST_TYPE_NVINFEREVAL (gst_nv_infer_eval_get_type ()) |
SECTION:element-nvinfereval.
A pass-through DeepStream GStreamer element that evaluates model accuracy live against ground-truth files. Buffers flow downstream UNCHANGED.
Two operating modes, auto-detected at READY->PAUSED by walking upstream through transparent elements (queue, queue2, identity, capsfilter):
Mode A — Single model nvinfer -> [queue?] -> nvinfereval -> sink No InferenceProvenanceMeta on frames. Evaluates one model vs GT. No promotion logic.
Mode B — Multi-model A/B evaluation + promotion nvmodelmux -> [queue?] -> nvinfereval -> sink InferenceProvenanceMeta present per frame (role / model_name / model_version). Any number of model_names may coexist — each gets its own isolated epoch counter, GT index, and accumulator. Promotion is triggered independently per model_name and targets only the streams carrying that pair.
Individual GObject properties set baseline values. If config-file is given, its sections overlay those values (config file wins for keys it defines). See configs/config_nvinfereval.txt for the full format.
Definition at line 58 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| typedef struct _GstNvInferEval GstNvInferEval |
Definition at line 68 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| typedef struct _GstNvInferEvalClass GstNvInferEvalClass |
Definition at line 69 of file sources/gst-plugins/gst-nvinfereval/gstnvinfereval.h.
| GType gst_nv_infer_eval_get_type | ( | void | ) |