(base) uu@uu-Matrimax-PC:~/pytorch-YOLOv4$ /home/uu/TensorRT-7.0.0.11/targets/x86_64-linux-gnu/bin/trtexec --onnx=yolov4_1_3_416_416_static.onnx --explicitBatch --saveEngine=yolov4_1_3_416_416_static_fp16.engine --workspace=4096 --fp16
&&&& RUNNING TensorRT.trtexec # /home/uu/TensorRT-7.0.0.11/targets/x86_64-linux-gnu/bin/trtexec --onnx=yolov4_1_3_416_416_static.onnx --explicitBatch --saveEngine=yolov4_1_3_416_416_static_fp16.engine --workspace=4096 --fp16
[11/22/2020-10:02:42] [I] === Model Options ===
[11/22/2020-10:02:42] [I] Format: ONNX
[11/22/2020-10:02:42] [I] Model: yolov4_1_3_416_416_static.onnx
[11/22/2020-10:02:42] [I] Output:
[11/22/2020-10:02:42] [I] === Build Options ===
[11/22/2020-10:02:42] [I] Max batch: explicit
[11/22/2020-10:02:42] [I] Workspace: 4096 MB
[11/22/2020-10:02:42] [I] minTiming: 1
[11/22/2020-10:02:42] [I] avgTiming: 8
[11/22/2020-10:02:42] [I] Precision: FP16
[11/22/2020-10:02:42] [I] Calibration:
[11/22/2020-10:02:42] [I] Safe mode: Disabled
[11/22/2020-10:02:42] [I] Save engine: yolov4_1_3_416_416_static_fp16.engine
[11/22/2020-10:02:42] [I] Load engine:
[11/22/2020-10:02:42] [I] Inputs format: fp32:CHW
[11/22/2020-10:02:42] [I] Outputs format: fp32:CHW
[11/22/2020-10:02:42] [I] Input build shapes: model
[11/22/2020-10:02:42] [I] === System Options ===
[11/22/2020-10:02:42] [I] Device: 0
[11/22/2020-10:02:42] [I] DLACore:
[11/22/2020-10:02:42] [I] Plugins:
[11/22/2020-10:02:42] [I] === Inference Options ===
[11/22/2020-10:02:42] [I] Batch: Explicit
[11/22/2020-10:02:42] [I] Iterations: 10
[11/22/2020-10:02:42] [I] Duration: 3s (+ 200ms warm up)
[11/22/2020-10:02:42] [I] Sleep time: 0ms
[11/22/2020-10:02:42] [I] Streams: 1
[11/22/2020-10:02:42] [I] ExposeDMA: Disabled
[11/22/2020-10:02:42] [I] Spin-wait: Disabled
[11/22/2020-10:02:42] [I] Multithreading: Disabled
[11/22/2020-10:02:42] [I] CUDA Graph: Disabled
[11/22/2020-10:02:42] [I] Skip inference: Disabled
[11/22/2020-10:02:42] [I] Inputs:
[11/22/2020-10:02:42] [I] === Reporting Options ===
[11/22/2020-10:02:42] [I] Verbose: Disabled
[11/22/2020-10:02:42] [I] Averages: 10 inferences
[11/22/2020-10:02:42] [I] Percentile: 99
[11/22/2020-10:02:42] [I] Dump output: Disabled
[11/22/2020-10:02:42] [I] Profile: Disabled
[11/22/2020-10:02:42] [I] Export timing to JSON file:
[11/22/2020-10:02:42] [I] Export output to JSON file:
[11/22/2020-10:02:42] [I] Export profile to JSON file:
[11/22/2020-10:02:42] [I]
Input filename: yolov4_1_3_416_416_static.onnx
ONNX IR version: 0.0.6
Opset version: 11
Producer name: pytorch
Producer version: 1.7
Domain:
Model version: 0
Doc string:
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [W] [TRT] onnx2trt_utils.cpp:198: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/22/2020-10:02:42] [E] [TRT] Layer: Where_491’s output can not be used as shape tensor.
[11/22/2020-10:02:42] [E] [TRT] Network validation failed.
[11/22/2020-10:02:42] [E] Engine creation failed
[11/22/2020-10:02:42] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec # /home/uu/TensorRT-7.0.0.11/targets/x86_64-linux-gnu/bin/trtexec --onnx=yolov4_1_3_416_416_static.onnx --explicitBatch --saveEngine=yolov4_1_3_416_416_static_fp16.engine --workspace=4096 --fp16
when I try to convet oonx to trt,the erro occured
please help help me!!!