[参考译文] PROCESSOR-SDK-J722S：运行 onnx 编译失败

*************** EP Error ***************
EP Error Unknown Provider Type: TIDLCompilationProvider when using ['TIDLCompilationProvider', 'CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
****************************************

import os
import tqdm
import cv2
import numpy as np
import onnxruntime as rt
import shutil
from scripts.utils import imagenet_class_to_name, download_model
import matplotlib.pyplot as plt
from pathlib import Path
from IPython.display import Markdown as md
from scripts.utils import loggerWritter
from scripts.utils import get_svg_path
import onnx

def preprocess(image_path):
    
    # read the image using openCV
    img = cv2.imread(image_path)
    
    # convert to RGB
    img = img[:,:,::-1]
    
    # Most of the onnx models are trained using
    # 224x224 images. The general rule of thumb
    # is to scale the input image while preserving
    # the original aspect ratio so that the
    # short edge is 256 pixels, and then
    # center-crop the scaled image to 224x224
    orig_height, orig_width, _ = img.shape
    short_edge = min(img.shape[:2])
    new_height = (orig_height * 256) // short_edge
    new_width = (orig_width * 256) // short_edge
    img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_CUBIC)

    startx = new_width//2 - (224//2)
    starty = new_height//2 - (224//2)
    img = img[starty:starty+224,startx:startx+224]
    
    # apply scaling and mean subtraction.
    # if your model is built with an input
    # normalization layer, then you might
    # need to skip this
    img = img.astype('float32')
    for mean, scale, ch in zip([128, 128, 128], [0.0078125, 0.0078125, 0.0078125], range(img.shape[2])):
            img[:,:,ch] = ((img.astype('float32')[:,:,ch] - mean) * scale)
    img = np.expand_dims(img,axis=0)
    img = np.transpose(img, (0, 3, 1, 2))
    
    return img
calib_images = [
'sample-images/elephant.bmp',
'sample-images/bus.bmp',
'sample-images/bicycle.bmp',
'sample-images/zebra.bmp',
]
output_dir = 'custom-artifacts/onnx/resnet18_opset9.onnx'
onnx_model_path = 'models/public/onnx/resnet18_opset9.onnx'
download_model(onnx_model_path)
onnx.shape_inference.infer_shapes_path(onnx_model_path, onnx_model_path)
#compilation options - knobs to tweak 
num_bits =8
accuracy =1

log_dir = Path("logs").mkdir(parents=True, exist_ok=True)

# stdout and stderr saved to a *.log file.  
with loggerWritter("logs/custon-model-onnx"):

# model compilation options
    compile_options = {
        'tidl_tools_path' : os.environ['TIDL_TOOLS_PATH'],
        'artifacts_folder' : output_dir,
        'tensor_bits' : num_bits,
        'accuracy_level' : accuracy,
        'advanced_options:calibration_frames' : len(calib_images), 
        'advanced_options:calibration_iterations' : 3, # used if accuracy_level = 1
        'advanced_options:add_data_convert_ops' : 1,
        'debug_level' : 1,
        #'deny_list' : "MaxPool" #Comma separated string of operator types as defined by ONNX runtime, ex "MaxPool, Concat"
    }
# create the output dir if not present
# clear the directory
os.makedirs(output_dir, exist_ok=True)
for root, dirs, files in os.walk(output_dir, topdown=False):
    [os.remove(os.path.join(root, f)) for f in files]
    [os.rmdir(os.path.join(root, d)) for d in dirs]

so = rt.SessionOptions()
EP_list = ['TIDLCompilationProvider','CPUExecutionProvider']
sess = rt.InferenceSession(onnx_model_path ,providers=EP_list, provider_options=[compile_options, {}], sess_options=so)

input_details = sess.get_inputs()
for num in tqdm.trange(len(calib_images)):
    output = list(sess.run(None, {input_details[0].name : preprocess(calib_images[num])}))[0]

##optional
#subgraph_link =get_svg_path(output_dir) 
#for sg in subgraph_link:
#    hl_text = os.path.join(*Path(sg).parts[4:])
#    sg_rel = os.path.join('../', sg)
#    display(md("[{}]({})".format(hl_text,sg_rel)))
#
#EP_list = ['TIDLExecutionProvider','CPUExecutionProvider']
#print("[ken debug] 5 ")
#sess = rt.InferenceSession(onnx_model_path ,providers=EP_list, provider_options=[compile_options, {}], sess_options=so)
##Running inference several times to get an stable performance output
#for i in range(5):
#    output = list(sess.run(None, {input_details[0].name : preprocess('sample-images/elephant.bmp')}))
#
#for idx, cls in enumerate(output[0].squeeze().argsort()[-5:][::-1]):
#    print('[%d] %s' % (idx, '/'.join(imagenet_class_to_name(cls))))
#    
#from scripts.utils import plot_TI_performance_data, plot_TI_DDRBW_data, get_benchmark_output
#stats = sess.get_TI_benchmark_data()
#fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(10,5))
#plot_TI_performance_data(stats, axis=ax)
#plt.show()
#print("[ken debug] 6 ")
#tt, st, rb, wb = get_benchmark_output(stats)
#print(f'Statistics : \n Inferences Per Second   : {1000.0/tt :7.2f} fps')
#print(f' Inference Time Per Image : {tt :7.2f} ms  \n DDR BW Per Image        : {rb+ wb : 7.2f} MB')