- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Excuse me, I met a problem with accuracy_check. If anyone can help me, please reply! Thank you very much.
My yaml content is the following:
models:
- name: saved_model_int8
launchers:
- framework: dlsdk
device: CPU
model: out/FP32/saved_model.xml
weights: out/FP32/saved_model.bin
##adapter: classification
datasets:
- name: data
annotation: data.pickle
reader: pickle_reader
my command is :
#accuracy_check -c MA00_model_int8.yaml
but there is a problem, I don't know how to configure my yaml file.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello Lantianguhong,
Thank you for reaching out to us.
Annotation Converters demonstrate how pickle file is used. Did you have a chance to look at Deep Learning accuracy validation framework? This document shows an example of dataset definition. Also, Intel provides predefined configuration files that you can refer to configure .ymal file for your model.
Sincerely,
Zulkifli
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello Lantianguhong,
This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.
Sincerely,
Zulkifli
![](/skins/images/D2683F18326913BBA0436CB7114DD569/responsive_peak/images/icon_anonymous_message.png)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page