编译ONNX模型Compile ONNX Models
编译ONNX模型Compile ONNX Models
本文是一篇介绍如何使用Relay部署ONNX模型的说明。
首先，必须安装ONNX包。
一个快速的解决方案是安装protobuf编译器，然后
pip install onnx –user
或者参考官方网站： https://github.com/onnx/onnx
import onnx
import numpy as np
import tvm
from tvm import te
import tvm.relay as relay
from tvm.contrib.download import download_testdata
Load pretrained ONNX model
这里使用的示例超分辨率模型与onnx说明中的模型完全相同
http://pytorch.org/tutorials/advanced/super_resolution_with_caffe2.html
跳过pytorch模型构造部分，下载保存的onnx模型
model_url = "".join(
[
"https://gist.github.com/zhreshold/",
"bcda4716699ac97ea44f791c24310193/raw/",
"93672b029103648953c4e5ad3ac3aadf346a4cdc/",
"super_resolution_0.2.onnx",
]
)
model_path = download_testdata(model_url, "super_resolution.onnx", module="onnx")
# now you have super_resolution.onnx on disk
onnx_model = onnx.load(model_path)
Out:
File /workspace/.tvm_test_data/onnx/super_resolution.onnx exists, skip.
Load a test image
Load a test image
A single cat dominates the examples!
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))
img_ycbcr = img.convert("YCbCr") # convert to YCbCr
img_y, img_cb, img_cr = img_ycbcr.split()
x = np.array(img_y)[np.newaxis, np.newaxis, :, :]
Out:
File /workspace/.tvm_test_data/data/cat.png exists, skip.
Compile the model with relay
target = "llvm"
input_name = "1"
shape_dict = {input_name: x.shape}
mod, params = relay.frontend.from_onnx(onnx_model, shape_dict)
with tvm.transform.PassContext(opt_level=1):
intrp = relay.build_module.create_executor("graph", mod, tvm.cpu(0), target)
Out:
/workspace/docs/../python/tvm/relay/frontend/onnx.py:2737: UserWarning: Mismatched attribute type in ' : kernel_shape'
==> Context: Bad node spec: input: "1" input: "2" output: "11" op_type: "Conv" attribute { name: "kernel_shape" ints: 5 ints: 5 } attribute { name: "strides" ints: 1 ints: 1 } attribute { name: "pads" ints: 2 ints: 2 ints: 2 ints: 2 } attribute { name: "dilations" ints: 1 ints: 1 } attribute { name: "group" i: 1 }
warnings.warn(str(e))
Execute on TVM
dtype = "float32"
tvm_output = intrp.evaluate()(tvm.nd.array(x.astype(dtype)), **params).asnumpy()
Display results
We put input and output image neck to neck
from matplotlib import pyplot as plt
out_y = Image.fromarray(np.uint8((tvm_output[0, 0]).clip(0, 255)), mode="L")
out_cb = img_cb.resize(out_y.size, Image.BICUBIC)
out_cr = img_cr.resize(out_y.size, Image.BICUBIC)
result = Image.merge("YCbCr", [out_y, out_cb, out_cr]).convert("RGB")
canvas = np.full((672, 672 * 2, 3), 255)
canvas[0:224, 0:224, :] = np.asarray(img)
canvas[:, 672:, :] = np.asarray(result)
plt.imshow(canvas.astype(np.uint8))
plt.show()
Notes
默认情况下，ONNX以动态形状定义模型。ONNX导入器在导入时保留这种动态性，编译器在编译时尝试将模型转换为静态形状。如果失败，模型中可能仍有动态操作。目前并非所有TVM内核都支持动态形状，请在discuss.tvm.apache.org上提交问题讨论，如果使用动态内核遇到错误。.
https://tvm.apache.org/docs/tutorials/frontend/from_onnx.html#sphx-glr-tutorials-frontend-from-onnx-py
Download Python source code: from_onnx.py
Download Jupyter notebook: from_onnx.ipynb
