Hi,
I am getting output like below while running inference on LPRnet instead of numbers.
input: shape:(-1, 3, 48, 96) dtype:DataType.FLOAT
output: shape:(-1, 24) dtype:DataType.INT32
output: shape:(-1, 24) dtype:DataType.FLOAT
[array([35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35,
35, 35, 35, 35, 35, 35, 35], dtype=int32), array([0.9999987 , 0.99999976, 1. , 1. , 1. ,
0.9999999 , 0.9999999 , 0.9999999 , 0.9999999 , 0.99999976,
0.99999976, 0.99999976, 0.9999999 , 0.9999999 , 0.99999976,
0.99999976, 0.99999976, 0.99999976, 0.99999976, 0.99999976,
0.99999964, 0.9999993 , 0.9999987 , 0.99999964], dtype=float32)]
My Code-base is below :
import os
import time
import cv2
#import matplotlib.pyplot as plt
import numpy as np
import pycuda.autoinit
import pycuda.driver as cuda
import tensorrt as trt
from PIL import Image
import pdb
class HostDeviceMem(object):
def __init__(self, host_mem, device_mem):
self.host = host_mem
self.device = device_mem
def __str__(self):
return "Host:\n" + str(self.host) + "\nDevice:\n" + str(self.device)
def __repr__(self):
return self.__str__()
def load_engine(trt_runtime, engine_path):
with open(engine_path, "rb") as f:
engine_data = f.read()
engine = trt_runtime.deserialize_cuda_engine(engine_data)
return engine
# Allocates all buffers required for an engine, i.e. host/device inputs/outputs.
def allocate_buffers(engine, batch_size=-1):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
# pdb.set_trace()
size = trt.volume(engine.get_binding_shape(binding)) * batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
print(f"input: shape:{engine.get_binding_shape(binding)} dtype:{engine.get_binding_dtype(binding)}")
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
print(f"output: shape:{engine.get_binding_shape(binding)} dtype:{engine.get_binding_dtype(binding)}")
return inputs, outputs, bindings, stream
def do_inference(context, bindings, inputs, outputs, stream, batch_size=1):
# Transfer input data to the GPU.
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
# Run inference.
context.execute_async(
batch_size=batch_size, bindings=bindings, stream_handle=stream.handle
)
# Transfer predictions back from the GPU.
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
return [out.host for out in outputs]
# TensorRT logger singleton
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
TRT_LOGGER = trt.Logger(trt.Logger.WARNING)
trt_engine_path = "number_plate_classification_b8_fp16.engine"
trt_runtime = trt.Runtime(TRT_LOGGER)
# pdb.set_trace()
trt_engine = load_engine(trt_runtime, trt_engine_path)
# Execution context is needed for inference
context = trt_engine.create_execution_context()
# This allocates memory for network inputs/outputs on both CPU and GPU
inputs, outputs, bindings, stream = allocate_buffers(trt_engine)
# pdb.set_trace()
image = cv2.imread("1626673361593_cropped_batch_code_image_imgGB3_BATOO69_.jpg")
image = cv2.resize(image, (96, 48))/255.0
image = image.T
np.copyto(inputs[0].host, image.ravel())
input_shape = (1,3,48,96)
context.set_binding_shape(0, input_shape)
output = do_inference(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream)
print(output)
Please help me what should I add to get exact inference result.
Thanks.