官方的教程
tensorrt的安装:Installation Guide :: NVIDIA Deep Learning TensorRT Documentation
视频教程:TensorRT 教程 | 基于 8.6.1 版本 | 第一部分_哔哩哔哩_bilibili
代码教程:trt-samples-for-hackathon-cn/cookbook at master · NVIDIA/trt-samples-for-hackathon-cn (github.com)
Tensorrt的安装
官方的教程:
安装指南 :: NVIDIA Deep Learning TensorRT Documentation --- Installation Guide :: NVIDIA Deep Learning TensorRT Documentation
Tensorrt的安装方法主要有:
1、使用 pip install 进行安装;
2、下载 tar、zip、deb 文件进行安装;
3、使用docker容器进行安装:TensorRT Container Release Notes
Windows系统
首先选择和本机nVidia驱动、cuda版本、cudnn版本匹配的Tensorrt版本。
我使用的:cuda版本:11.4;cudnn版本:11.4
建议下载 zip 进行Tensorrt的安装,参考的教程:
windows安装tensorrt - 知乎 (zhihu.com)
Ubuntu系统
首先选择和本机nVidia驱动、cuda版本、cudnn版本匹配的Tensorrt版本。
我使用的:cuda版本:11.7;cudnn版本:8.9.0
1、使用 pip 进行安装:
pip install tensorrt==8.6.1
我这边安装失败
2、下载 deb 文件进行安装
os="ubuntuxx04"
tag="8.x.x-cuda-x.x"
sudo dpkg -i nv-tensorrt-local-repo-${os}-${tag}_1.0-1_amd64.deb
sudo cp /var/nv-tensorrt-local-repo-${os}-${tag}/*-keyring.gpg /usr/share/keyrings/
sudo apt-get update sudo apt-get install tensorrt
我这边同样没安装成功
3、使用 tar 文件进行安装(推荐)
推荐使用这种方法进行安装,成功率较高
下载对应的版本:developer.nvidia.com/tensorrt-download
下载后
tar -xzvf TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-11.8.tar.gz # 解压文件
# 将lib添加到环境变量里面
vim ~/.bashrc
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:./TensorRT-8.6.1.6/lib
source ~/.bashrc
# 或 直接将 TensorRT-8.6.1.6/lib 添加到 cuda/lib64 里面
cp -r ./lib/* /usr/local/cuda/lib64/
# 安装python的包
cd TensorRT-8.6.1.6/python
pip install tensorrt-xxx-none-linux_x86_64.whl
下载成功后验证:
# 验证是否安装成功:
python
>>>import tensorrt
>>>print(tensorrt.__version__)
>>>assert tensorrt.Builder(tensorrt.Logger())
如果没有报错说明安装成功
使用方法
我这边的使用的流程是:pytorch -> onnx -> tensorrt
选择resnet18进行转换
pytorch转onnx
安装onnx,onnxruntime安装一个就行
pip install onnx
pip install onnxruntime
pip install onnxruntime-gpu # gpu版本
将pytorch模型转成onnx模型
import torch
import torchvision
model = torchvision.models.resnet18(pretrained=False)
device = 'cuda' if torch.cuda.is_available else 'cpu'
dummy_input = torch.randn(1, 3, 224, 224, device=device)
model.to(device)
model.eval()
output = model(dummy_input)
print("pytorch result:", torch.argmax(output))
import torch.onnx
torch.onnx.export(model, dummy_input, './model.onnx', input_names=["input"], output_names=["output"], do_constant_folding=True, verbose=True, keep_initializers_as_inputs=True, opset_version=14, dynamic_axes={"input": {0: "nBatchSize"}, "output": {0: "nBatchSize"}})
# 一般情况
# torch.onnx.export(model, torch.randn(1, c, nHeight, nWidth, device="cuda"), './model.onnx', input_names=["x"], output_names=["y", "z"], do_constant_folding=True, verbose=True, keep_initializers_as_inputs=True, opset_version=14, dynamic_axes={"x": {0: "nBatchSize"}, "z": {0: "nBatchSize"}})
import onnx
import numpy as np
import onnxruntime as ort
model_onnx_path = './model.onnx'
# 验证模型的合法性
onnx_model = onnx.load(model_onnx_path)
onnx.checker.check_model(onnx_model)
# 创建ONNX运行时会话
ort_session = ort.InferenceSession(model_onnx_path, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
# 准备输入数据
input_data = {
'input': dummy_input.cpu().numpy()
}
# 运行推理
y_pred_onnx = ort_session.run(None, input_data)
print("onnx result:", np.argmax(y_pred_onnx[0]))
onnx转tensorrt
Window使用zip安装后使用 TensorrtRT-8.6.1.6/bin/trtexec.exe 文件生成 tensorrt 模型文件
Ubuntu使用tar安装后使用 TensorrtRT-8.6.1.6/bin/trtexec 文件生成 tensorrt 模型文件
./trtexec --onnx=model.onnx --saveEngine=model.trt --fp16 --workspace=16 --shapes=input:2x3x224x224
其中的参数:
--fp16:是否使用fp16
--shapes:输入的大小。tensorrt支持 动态batch 设置,感兴趣可以尝试
tensorrt的使用
nVidia的官方使用方法:
trt-samples-for-hackathon-cn/cookbook at master · NVIDIA/trt-samples-for-hackathon-cn (github.com)
打印转换后的tensorrt的模型的信息
import tensorrt as trt
# 加载TensorRT引擎
logger = trt.Logger(trt.Logger.INFO)
with open('./model.trt', "rb") as f, trt.Runtime(logger) as runtime:
engine = runtime.deserialize_cuda_engine(f.read())
for idx in range(engine.num_bindings):
name = engine.get_tensor_name(idx)
is_input = engine.get_tensor_mode(name)
op_type = engine.get_tensor_dtype(name)
shape = engine.get_tensor_shape(name)
print('input id: ',idx, '\tis input: ', is_input, '\tbinding name: ', name, '\tshape: ', shape, '\ttype: ', op_type)
测试转换后的tensorrt模型,来自nVidia的 cookbook/08-Advance/MultiStream/main.py文章来源:https://www.toymoban.com/news/detail-852360.html
from time import time
import numpy as np
import tensorrt as trt
from cuda import cudart # 安装 pip install cuda-python
np.random.seed(31193)
nWarmUp = 10
nTest = 30
nB, nC, nH, nW = 1, 3, 224, 224
data = dummy_input.cpu().numpy()
def run1(engine):
input_name = engine.get_tensor_name(0)
output_name = engine.get_tensor_name(1)
output_type = engine.get_tensor_dtype(output_name)
output_shape = engine.get_tensor_shape(output_name)
context = engine.create_execution_context()
context.set_input_shape(input_name, [nB, nC, nH, nW])
_, stream = cudart.cudaStreamCreate()
inputH0 = np.ascontiguousarray(data.reshape(-1))
outputH0 = np.empty(output_shape, dtype=trt.nptype(output_type))
_, inputD0 = cudart.cudaMallocAsync(inputH0.nbytes, stream)
_, outputD0 = cudart.cudaMallocAsync(outputH0.nbytes, stream)
# do a complete inference
cudart.cudaMemcpyAsync(inputD0, inputH0.ctypes.data, inputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyHostToDevice, stream)
context.execute_async_v2([int(inputD0), int(outputD0)], stream)
cudart.cudaMemcpyAsync(outputH0.ctypes.data, outputD0, outputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyDeviceToHost, stream)
cudart.cudaStreamSynchronize(stream)
# Count time of memory copy from host to device
for i in range(nWarmUp):
cudart.cudaMemcpyAsync(inputD0, inputH0.ctypes.data, inputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyHostToDevice, stream)
trtTimeStart = time()
for i in range(nTest):
cudart.cudaMemcpyAsync(inputD0, inputH0.ctypes.data, inputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyHostToDevice, stream)
cudart.cudaStreamSynchronize(stream)
trtTimeEnd = time()
print("%6.3fms - 1 stream, DataCopyHtoD" % ((trtTimeEnd - trtTimeStart) / nTest * 1000))
# Count time of inference
for i in range(nWarmUp):
context.execute_async_v2([int(inputD0), int(outputD0)], stream)
trtTimeStart = time()
for i in range(nTest):
context.execute_async_v2([int(inputD0), int(outputD0)], stream)
cudart.cudaStreamSynchronize(stream)
trtTimeEnd = time()
print("%6.3fms - 1 stream, Inference" % ((trtTimeEnd - trtTimeStart) / nTest * 1000))
# Count time of memory copy from device to host
for i in range(nWarmUp):
cudart.cudaMemcpyAsync(outputH0.ctypes.data, outputD0, outputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyDeviceToHost, stream)
trtTimeStart = time()
for i in range(nTest):
cudart.cudaMemcpyAsync(outputH0.ctypes.data, outputD0, outputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyDeviceToHost, stream)
cudart.cudaStreamSynchronize(stream)
trtTimeEnd = time()
print("%6.3fms - 1 stream, DataCopyDtoH" % ((trtTimeEnd - trtTimeStart) / nTest * 1000))
# Count time of end to end
for i in range(nWarmUp):
context.execute_async_v2([int(inputD0), int(outputD0)], stream)
trtTimeStart = time()
for i in range(nTest):
cudart.cudaMemcpyAsync(inputD0, inputH0.ctypes.data, inputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyHostToDevice, stream)
context.execute_async_v2([int(inputD0), int(outputD0)], stream)
cudart.cudaMemcpyAsync(outputH0.ctypes.data, outputD0, outputH0.nbytes, cudart.cudaMemcpyKind.cudaMemcpyDeviceToHost, stream)
cudart.cudaStreamSynchronize(stream)
trtTimeEnd = time()
print("%6.3fms - 1 stream, DataCopy + Inference" % ((trtTimeEnd - trtTimeStart) / nTest * 1000))
cudart.cudaStreamDestroy(stream)
cudart.cudaFree(inputD0)
cudart.cudaFree(outputD0)
print("tensorrt result:", np.argmax(outputH0))
if __name__ == "__main__":
cudart.cudaDeviceSynchronize()
f = open("./model.trt", "rb") # 读取trt模型
runtime = trt.Runtime(trt.Logger(trt.Logger.WARNING)) # 创建一个Runtime(传入记录器Logger)
engine = runtime.deserialize_cuda_engine(f.read()) # 从文件中加载trt引擎
run1(engine) # do inference with single stream
print(dummy_input.shape, dummy_input.dtype)
文章来源地址https://www.toymoban.com/news/detail-852360.html
到了这里,关于Tensorrt安装及使用(python版本)的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!