Question/Issue:
Apologize if it is an easy question.
I am new and trying to train using N number of image files. The image files are named blobs.1.png, blobs.2.png, and so on. The CSV file has the following format.
file_name,this_feature
blobs.1.png,8
blobs.2.png,2
blobs.3.png,4
blobs.4.png,1
I have already uploaded the CSV file through CSV wizard. How do I automatically apply ‘this_feature’ as the label to the uploaded data? The objective is to create a model that will predict ‘this_feature’ as the output for an input image.
This is not time-series data. Whenever I upload new dataset, it asks me if it should infer the data from the filenames (not true), should keep the label empty, or provide a manual label. But it does not ask if it should consult the active csv configuration.
I am new to this. Please help.
Project ID:
899925
Context/Use case:
The context is to train a model to learn about a feature of images in a dataset.
Steps Taken:
See above.
Expected Outcome:
I will provide the CSV file and the uploaded dataset will be automatically labelled using the CSV file.
Actual Outcome:
Either wrong label (only the column header) or nothing.
Reproducibility:
- [ x] Always
- [ ] Sometimes
- [ ] Rarely
Environment:
- Platform: [e.g., Raspberry Pi, nRF9160 DK, etc.]
- Build Environment Details: [e.g., Arduino IDE 1.8.19 ESP32 Core for Arduino 2.0.4]
- OS Version: [e.g., Ubuntu 20.04, Windows 10]
- Edge Impulse Version (Firmware): [e.g., 1.2.3]
- To find out Edge Impulse Version:
- if you have pre-compiled firmware: run edge-impulse-run-impulse --raw and type AT+INFO. Look for Edge Impulse version in the output.
- if you have a library deployment: inside the unarchived deployment, open model-parameters/model_metadata.h and look for EI_STUDIO_VERSION_MAJOR, EI_STUDIO_VERSION_MINOR, EI_STUDIO_VERSION_PATCH
- Edge Impulse CLI Version: [e.g., 1.5.0]
- Project Version: [e.g., 1.0.0]
-
Custom Blocks / Impulse Configuration: [Describe custom blocks used or impulse configuration]
Logs/Attachments:
[Include any logs or screenshots that may help in diagnosing the issue]
Additional Information:
None.