Be sure to review our Idea Submission Guidelines for more information!
Submission GuidelinesHello,
After used the new "Image Recognition Tool" a few days, I think you could improve it :
> by adding the dimensional constraints in front of each of the pre-trained models,
> by adding a true tool to divide the training data correctly (in order to have an equivalent number of images for each of the labels)
> at least, allow the tool to use black & white images (I wanted to test it on the MNIST, but the tool tells me that it necessarily needs RGB images) ?
Question : do you in the future allow the user to choose between CPU or GPU usage ?
In any case, thank you again for this new tool, it is certainly perfectible, but very simple to use, and I sincerely think that it will allow a greater number of people to understand the many use cases made possible thanks to image recognition.
Thank you again
Kévin VANCAPPEL (France ;-))
Thank you again.
Kévin VANCAPPEL
Add an option to read directly from a zip file.
It would be nice to have the ability to double click the top area of a container to either show or hide the container's objects. Only being able to show or hide containers using the arrow icon in the top right is quite cumbersome for large containers because it requires a lot of horizontal scrolling in order to change the desired view of the modules workflow.
For example, in the Properties tool (I say that generally because it could be in more than one place in that tool) all the user to enable to visibly see the path of the variable in the flow on the canvas. As shown in the mock-up image below (as crude as it is, I think you get the idea). This would allow you to trace the path forward and backwards in the flow, seeing where the variable entered and when it exited. This could be something you can turn on and off like the grid option.
Instead of being a module setting, showing counts should/could be a user setting.
When building an expression (e.g. [Store Type] in ("Supermarket", "C-Store", "Gas Station") ) when the user selects the field variable, provide all the unique values in that field so user can double-click and add them to the expression, without having to look and see what values are in the table, what data type (shows quotes if string) and manually type the values, which can lead to errors.
This functionality is currently available in GIS programs such as ArcGIS and Quantum GIS (QGIS).
Currently on the input tool I can only specify if the first row contains data. It would be great if I could simply specify which row the data starts on, ie. row 4 or row 500, and then specify which row, if at all, contains the headers.
The bak file that is automatically created (and re-created if deleted) really clutters up our folders.
Please allow us to either turn it off, or specify a different location to hold our back up files.
Thanks
Wouldn't it be nice to have more training examples available on YouTube?
It would helpful if you have a tool which will help us to filter out the data using CASS results column in a meaningful way. On the other day, I CASS'ed 2MM customers and ended up with 1500 combination of CASS result codes. I don't think we would have time to sit walk through all the 1500 combination to find out which I should call it as correct addresses and not the right ones. If you have one already that I didn't know of, please guide me.
Thanks
Arun
User | Likes Count |
---|---|
7 | |
7 | |
5 | |
3 | |
3 |