编译 PyTorch 模型#

本文是使用 Relay 部署 PyTorch 模型的入门教程。

对于我们来说，首先应该安装 PyTorch。TorchVision 也是必需的，因为我们将使用它作为我们的模型动物园。

快速的解决方案是通过 pip 进行安装：

pip install torch==1.7.0
pip install torchvision==0.8.1

或者参考官方网站。

PyTorch 版本应该向后兼容，但应该与适当的 TorchVision 版本一起使用。

目前，TVM 支持 PyTorch 1.7 和 1.4。其他版本可能不稳定。

import numpy as np

# PyTorch imports
import torch
import torchvision

import set_env # 设置 TVM 环境
import tvm
from tvm import relay
from tvm.contrib.download import download_testdata

载入 PyTorch 预训练模型#

model_name = "resnet18"
model = getattr(torchvision.models, model_name)(pretrained=True)
model = model.eval()

# 我们通过跟踪获取 TorchScripted 模型
input_shape = [1, 3, 224, 224]
input_data = torch.randn(input_shape)
scripted_model = torch.jit.trace(model, input_data).eval()

加载测试图片#

from PIL import Image

img_url = "https://github.com/dmlc/mxnet.js/blob/main/data/cat.png?raw=true"
img_path = download_testdata(img_url, "cat.png", module="data")
img = Image.open(img_path).resize((224, 224))

# Preprocess the image and convert to tensor
from torchvision import transforms

my_preprocess = transforms.Compose(
    [
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ]
)
img = my_preprocess(img)
img = np.expand_dims(img, 0)

导入 Graph 到 Relay#

将 PyTorch 图转换为 Relay 图。input_name 可以是任意的。

input_name = "input0"
shape_list = [(input_name, img.shape)]
mod, params = relay.frontend.from_pytorch(scripted_model, shape_list)

Relay 构建#

使用给定的输入规范将 graph 编译为 llvm 目标：

target = tvm.target.Target("llvm", host="llvm")
dev = tvm.cpu(0)
with tvm.transform.PassContext(opt_level=3):
    lib = relay.build(mod, target=target, params=params)

One or more operators have not been tuned. Please tune your model for better performance. Use DEBUG logging level to see more details.

在 TVM 上执行可移植 Graph#

可以尝试在目标上部署编译后的模型。

from tvm.contrib import graph_executor

dtype = "float32"
m = graph_executor.GraphModule(lib["default"](dev))
# Set inputs
m.set_input(input_name, tvm.nd.array(img.astype(dtype)))
# Execute
m.run()
# Get outputs
tvm_output = m.get_output(0)

查找 synset 名称#

在 1000 类 synset 中查找预测 top 1 索引。

synset_url = "".join(
    [
        "https://raw.githubusercontent.com/Cadene/",
        "pretrained-models.pytorch/master/data/",
        "imagenet_synsets.txt",
    ]
)
synset_name = "imagenet_synsets.txt"
synset_path = download_testdata(synset_url, synset_name, module="data")
with open(synset_path) as f:
    synsets = f.readlines()

synsets = [x.strip() for x in synsets]
splits = [line.split(" ") for line in synsets]
key_to_classname = {spl[0]: " ".join(spl[1:]) for spl in splits}

class_url = "".join(
    [
        "https://raw.githubusercontent.com/Cadene/",
        "pretrained-models.pytorch/master/data/",
        "imagenet_classes.txt",
    ]
)
class_name = "imagenet_classes.txt"
class_path = download_testdata(class_url, class_name, module="data")
with open(class_path) as f:
    class_id_to_key = f.readlines()

class_id_to_key = [x.strip() for x in class_id_to_key]

# Get top-1 result for TVM
top1_tvm = np.argmax(tvm_output.numpy()[0])
tvm_class_key = class_id_to_key[top1_tvm]

# Convert input to PyTorch variable and get PyTorch result for comparison
with torch.no_grad():
    torch_img = torch.from_numpy(img)
    output = model(torch_img)

    # Get top-1 result for PyTorch
    top1_torch = np.argmax(output.numpy())
    torch_class_key = class_id_to_key[top1_torch]

print("Relay top-1 id: {}, class name: {}".format(top1_tvm, key_to_classname[tvm_class_key]))
print("Torch top-1 id: {}, class name: {}".format(top1_torch, key_to_classname[torch_class_key]))

Relay top-1 id: 281, class name: tabby, tabby cat
Torch top-1 id: 281, class name: tabby, tabby cat

TVM 文档

编译 PyTorch 模型

导航