请问在单batch校验时的显示:
Version: None
Graph input:
…ut_image: shape=[1, 3, 480, 640], dtype=FLOAT32
Graph output:
preds: shape=[1, 1, 480, 640], dtype=INT64
2026-03-02 18:57:16,261 INFO Modify argmax output element type from int32 to int64 to make sure this onnx model will be valid.
2026-03-02 18:57:16,301 INFO End to prepare the onnx model.
2026-03-02 18:57:16,334 INFO Saving model to: ./.hb_check/original_float_model.onnx.
2026-03-02 18:57:16,334 INFO Start to optimize the onnx model.
2026-03-02 18:57:16,608 INFO End to optimize the onnx model.
2026-03-02 18:57:16,609 WARNING BPU only support Reducemean whose axes size == 1, unsupport node name:/segment/S5_5/ReduceMean
2026-03-02 18:57:16,641 INFO Saving model to: ./.hb_check/optimized_float_model.onnx.
2026-03-02 18:57:16,641 INFO Start to calibrate the model.
2026-03-02 18:57:16,693 INFO There are 1 samples in the data set.
2026-03-02 18:57:16,693 INFO Run calibration model with fixed thresholds method.
2026-03-02 18:57:16,799 INFO End to calibrate the model.
2026-03-02 18:57:16,857 INFO Saving model to: ./.hb_check/calibrated_model.onnx.
2026-03-02 18:57:16,857 INFO Start to quantize the model.
2026-03-02 18:57:17,299 INFO End to quantize the model.
2026-03-02 18:57:17,318 INFO Saving model to: ./.hb_check/quantized_model.onnx.
2026-03-02 18:57:17,318 INFO Start to compile the model with march bayes-e.
2026-03-02 18:57:17,393 INFO Compile submodel: main_graph_subgraph_0
2026-03-02 18:57:17,401 INFO hbdk-cc parameters:[‘–input-layout’, ‘NHWC’, ‘–output-layout’, ‘NHWC’]
[==================================================] 100%
2026-03-02 18:57:17,623 INFO consumed time 0.195803
2026-03-02 18:57:17,687 INFO FPS=37.75, latency = 26492.3 us, DDR = 128804672 bytes (see ./.hb_check/main_graph_subgraph_0.html)
多batch校验时显示
...ut_image: shape=[4, 3, 480, 640], dtype=FLOAT32
Graph output:
preds: shape=[1, 4, 480, 640], dtype=INT64
2026-03-02 18:54:46,555 INFO Modify argmax output element type from int32 to int64 to make sure this onnx model will be valid.
2026-03-02 18:54:46,595 INFO End to prepare the onnx model.
2026-03-02 18:54:46,628 INFO Saving model to: ./.hb_check/original_float_model.onnx.
2026-03-02 18:54:46,628 INFO Start to optimize the onnx model.
2026-03-02 18:54:46,948 INFO End to optimize the onnx model.
2026-03-02 18:54:46,948 WARNING BPU only support Reducemean whose axes size == 1, unsupport node name:/segment/S5_5/ReduceMean
2026-03-02 18:54:46,979 INFO Saving model to: ./.hb_check/optimized_float_model.onnx.
2026-03-02 18:54:46,979 INFO Start to calibrate the model.
2026-03-02 18:54:47,043 INFO There are 1 samples in the data set.
2026-03-02 18:54:47,043 INFO Run calibration model with fixed thresholds method.
2026-03-02 18:54:47,144 INFO End to calibrate the model.
2026-03-02 18:54:47,195 INFO Saving model to: ./.hb_check/calibrated_model.onnx.
2026-03-02 18:54:47,195 INFO Start to quantize the model.
2026-03-02 18:54:47,634 INFO End to quantize the model.
2026-03-02 18:54:47,652 INFO Saving model to: ./.hb_check/quantized_model.onnx.
2026-03-02 18:54:47,652 INFO Start to compile the model with march bayes-e.
2026-03-02 18:54:47,726 INFO Compile submodel: main_graph_subgraph_0
2026-03-02 18:54:47,733 INFO hbdk-cc parameters:[‘–input-layout’, ‘NHWC’, ‘–output-layout’, ‘NHWC’]
[==================================================] 100%
2026-03-02 18:54:48,049 INFO consumed time 0.289453
2026-03-02 18:54:48,114 INFO FPS=36.85, latency = 108537.9 us, DDR = 134271024 bytes (see ./.hb_check/main_graph_subgraph_0.html)
FPS=37.75, latency = 26492.3 us和FPS=36.85, latency = 108537.9 us在batch=4时,FPS一样但延迟多了四倍,代表着多batch内部也是串行执行单batch的嘛?