-
Notifications
You must be signed in to change notification settings - Fork 1.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
AC: add inputs and LSTM inputs processing for OpenCV launcher #3444
base: master
Are you sure you want to change the base?
AC: add inputs and LSTM inputs processing for OpenCV launcher #3444
Conversation
Can one of the admins verify this patch? |
Jenkins please retry a build |
@@ -73,7 +73,8 @@ def parameters(cls): | |||
regex=BACKEND_REGEX, choices=OpenCVLauncher.OPENCV_BACKENDS.keys(), | |||
optional=True, default='IE', | |||
description="Backend name: {}".format(', '.join(OpenCVLauncher.OPENCV_BACKENDS.keys()))), | |||
'inputs': ListInputsField(optional=False, description="Inputs.") | |||
'inputs': ListInputsField(optional=False, description="Inputs."), | |||
'allow_reshape_input': BoolField(optional=True, default=False, description="Allows reshape input.") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this key means that instead of resizing data to fit model, model should be reshaped to data side. Does opencv support model reshaping or dynamic model inference?
for input_blobs in inputs: | ||
input_blobs.update(lstm_inputs_feed) | ||
for blob_name in input_blobs.keys(): | ||
input = input_blobs[blob_name].astype(np.float32) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
************* Module openvino.tools.accuracy_checker.launcher.opencv_launcher
openvino/tools/accuracy_checker/launcher/opencv_launcher.py:209: [W0622(redefined-builtin), OpenCVLauncher.predict_sequential] Redefining built-in 'input'
This PR allows to process input data correctly while running Accuracy Checker via OpenCV launcher