aXeleRate/example_scripts/nvidia_jetson/classifier/inference.py

76 lines
2.6 KiB
Python

import tensorrt as trt
import pycuda.driver as cuda
import numpy as np
import pycuda.autoinit
def allocate_buffers(engine, batch_size, data_type):
"""
This is the function to allocate buffers for input and output in the device
Args:
engine : The path to the TensorRT engine.
batch_size : The batch size for execution time.
data_type: The type of the data for input and output, for example trt.float32.
Output:
h_input_1: Input in the host.
d_input_1: Input in the device.
h_output_1: Output in the host.
d_output_1: Output in the device.
stream: CUDA stream.
"""
# Determine dimensions and create page-locked memory buffers (which won't be swapped to disk) to hold host inputs/outputs.
h_input_1 = cuda.pagelocked_empty(batch_size * trt.volume(engine.get_binding_shape(0)), dtype=trt.nptype(data_type))
h_output = cuda.pagelocked_empty(batch_size * trt.volume(engine.get_binding_shape(1)), dtype=trt.nptype(data_type))
# Allocate device memory for inputs and outputs.
d_input_1 = cuda.mem_alloc(h_input_1.nbytes)
d_output = cuda.mem_alloc(h_output.nbytes)
# Create a stream in which to copy inputs/outputs and run inference.
stream = cuda.Stream()
return h_input_1, d_input_1, h_output, d_output, stream
def load_images_to_buffer(pics, pagelocked_buffer):
preprocessed = np.asarray(pics).ravel()
np.copyto(pagelocked_buffer, preprocessed)
def do_inference(context, engine, pics_1, h_input_1, d_input_1, h_output, d_output, stream, batch_size, height, width):
"""
This is the function to run the inference
Args:
engine : Path to the TensorRT engine
pics_1 : Input images to the model.
h_input_1: Input in the host
d_input_1: Input in the device
h_output_1: Output in the host
d_output_1: Output in the device
stream: CUDA stream
batch_size : Batch size for execution time
height: Height of the output image
width: Width of the output image
Output:
The list of output images
"""
load_images_to_buffer(pics_1, h_input_1)
# Transfer input data to the GPU.
cuda.memcpy_htod_async(d_input_1, h_input_1, stream)
# Run inference.
context.profiler = trt.Profiler()
context.execute(batch_size=1, bindings=[int(d_input_1), int(d_output)])
# Transfer predictions back from the GPU.
cuda.memcpy_dtoh_async(h_output, d_output, stream)
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return the host output.
return h_output