mirror of
https://github.com/opencv/opencv.git
synced 2026-07-25 21:33:04 +04:00
Dmitry Matveev
fc5d412ba7
G-API: Integration branch for ONNX & Python-related changes #23597 # Changes overview ## 1. Expose ONNX backend's Normalization and Mean-value parameters in Python * Since Python G-API bindings rely on `Generic` infer to express Inference, the `Generic` specialization of `onnx::Params` was extended with new methods to control normalization (`/255`) and mean-value; these methods were exposed in the Python bindings * Found some questionable parts in the existing API which I'd like to review/discuss (see comments) UPD: 1. Thanks to @TolyaTalamanov normalization inconsistencies have been identified with `squeezenet1.0-9` ONNX model itself; tests using these model were updated to DISABLE normalization and NOT using mean/value. 2. Questionable parts were removed and tests still pass. ### Details (taken from @TolyaTalamanov's comment): `squeezenet1.0.*onnx` - doesn't require scaling to [0,1] and mean/std because the weights of the first convolution already scaled. ONNX documentation is broken. So the correct approach to use this models is: 1. ONNX: apply preprocessing from the documentation: https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py#L8-L44 but without normalization step: ``` # DON'T DO IT: # mean_vec = np.array([0.485, 0.456, 0.406]) # stddev_vec = np.array([0.229, 0.224, 0.225]) # norm_img_data = np.zeros(img_data.shape).astype('float32') # for i in range(img_data.shape[0]): # norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i] # # add batch channel # norm_img_data = norm_img_data.reshape(1, 3, 224, 224).astype('float32') # return norm_img_data # INSTEAD return img_data.reshape(1, 3, 224, 224) ``` 2. G-API: Convert image from BGR to RGB and then pass to `apply` as-is with configuring parameters: ``` net = cv.gapi.onnx.params('squeezenet', model_filename) net.cfgNormalize('data_0', False) ``` **Note**: Results might be difference because `G-API` doesn't apply central crop but just do resize to model resolution. --- `squeezenet1.1.*onnx` - requires scaling to [0,1] and mean/std - onnx documentation is correct. 1. ONNX: apply preprocessing from the documentation: https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py#L8-L44 2. G-API: Convert image from BGR to RGB and then pass to `apply` as-is with configuring parameters: ``` net = cv.gapi.onnx.params('squeezenet', model_filename) net.cfgNormalize('data_0', True) // default net.cfgMeanStd('data_0', [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ``` **Note**: Results might be difference because `G-API` doesn't apply central crop but just do resize to model resolution. ## 2. Expose Fluid & kernel package-related functionality in Python * `cv::gapi::combine()` * `cv::GKernelPackage::size()` (mainly for testing purposes) * `cv::gapi::imgproc::fluid::kernels()` Added a test for the above. ## 3. Fixed issues with Python stateful kernel handling Fixed error message when `outMeta()` of custom python operation fails. ## 4. Fixed various issues in Python tests 1. `test_gapi_streaming.py` - fixed behavior of Desync test to avoid sporadic issues 2. `test_gapi_infer_onnx.py` - fixed model lookup (it was still using the ONNX Zoo layout but was NOT using the proper env var we use to point to one). ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
#!/usr/bin/env python
|
|
|
|
import numpy as np
|
|
import cv2 as cv
|
|
import os
|
|
import sys
|
|
import unittest
|
|
|
|
from tests_common import NewOpenCVTests
|
|
|
|
|
|
try:
|
|
|
|
if sys.version_info[:2] < (3, 0):
|
|
raise unittest.SkipTest('Python 2.x is not supported')
|
|
|
|
CLASSIFICATION_MODEL_PATH = "vision/classification/squeezenet/model/squeezenet1.0-9.onnx"
|
|
|
|
class test_gapi_infer(NewOpenCVTests):
|
|
def find_dnn_file(self, filename):
|
|
return self.find_file(filename, [os.environ.get('OPENCV_GAPI_ONNX_MODEL_PATH')], False)
|
|
|
|
def test_onnx_classification(self):
|
|
model_path = self.find_dnn_file(CLASSIFICATION_MODEL_PATH)
|
|
if model_path is None:
|
|
raise unittest.SkipTest("Missing DNN test file")
|
|
|
|
in_mat = cv.imread(
|
|
self.find_file("cv/dpm/cat.png",
|
|
[os.environ.get('OPENCV_TEST_DATA_PATH')]))
|
|
|
|
g_in = cv.GMat()
|
|
g_infer_inputs = cv.GInferInputs()
|
|
g_infer_inputs.setInput("data_0", g_in)
|
|
g_infer_out = cv.gapi.infer("squeeze-net", g_infer_inputs)
|
|
g_out = g_infer_out.at("softmaxout_1")
|
|
|
|
comp = cv.GComputation(cv.GIn(g_in), cv.GOut(g_out))
|
|
|
|
net = cv.gapi.onnx.params("squeeze-net", model_path)
|
|
net.cfgNormalize("data_0", False)
|
|
try:
|
|
out_gapi = comp.apply(cv.gin(in_mat), cv.gapi.compile_args(cv.gapi.networks(net)))
|
|
except cv.error as err:
|
|
if err.args[0] == "G-API has been compiled without ONNX support":
|
|
raise unittest.SkipTest("G-API has been compiled without ONNX support")
|
|
else:
|
|
raise
|
|
|
|
self.assertEqual((1, 1000, 1, 1), out_gapi.shape)
|
|
|
|
|
|
except unittest.SkipTest as e:
|
|
|
|
message = str(e)
|
|
|
|
class TestSkip(unittest.TestCase):
|
|
def setUp(self):
|
|
self.skipTest('Skip tests: ' + message)
|
|
|
|
def test_skip():
|
|
pass
|
|
|
|
pass
|
|
|
|
|
|
if __name__ == '__main__':
|
|
NewOpenCVTests.bootstrap()
|