Description
I am trying to get the output of resnet50 and I am using the following code (python):
##########
inputs, outputs, bindings, stream = allocate_buffers(engine)
context = engine.create_execution_context()
for test_image in #####:
inputs[0].host = test_image
#inferencing andcheck timing
start_time = time.time()
trt_outputs = do_inference_v2(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream)
means_time[i] = time.time() - start_time
print(1/means_time.mean())
#########
But I am not getting the same results for frame per second on AGX.
I am getting 62 frames per second for Fp32 and 226 fps for int8.
Environment
TensorRT Version: 8
GPU Type: AGX
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version: linux 18
Python Version (if applicable): 3.7
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
Relevant Files
Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)
Steps To Reproduce
Please include:
- Exact steps/commands to build your repro
- Exact steps/commands to run your repro
- Full traceback of errors encountered