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
Alteryx currently shows 100% in the profiling of spatial fields in the results window, regardless of if there are rows with missing spatial features. I opened a ticket about this & was told it is expected behavior.
Therefore, I submit the idea that the profiling for spatial fields should give an accurate profile of the field, & if there are nulls in the field, it should identify that column isn't 100% OK and show the % of records that have null values, like the profiling does for every other column in workflows.
Thank you!
Hi,
I would like to see an option within the 'Find Nearest Tool' (and maybe other Tools like it) to exclude from results when a particular Target field equals a particular Universe field. This could be added right under the 'Ignore 0 Distance Matches' in config window. You could have drop-downs (like a filter tool) to pick the fields etc. Example of what I'm doing: One Address may have multiple accounts and it's in Target and Universe. Ignoring 0 Distance would drop all the other Accounts at the same address. I only want it to ignore the Universe Address if it has the same Account Number and the Target Account Number. That is a little deeper drill than just ignore 0 Distance but not too hard to add.
As it stands, I don't ignore 0 Distance. I have a formula after the 'Find Nearest' to drop Target Acct Nbr = Universe Acct Nbr. Then a 'Multi-Row Formula' tool to fix the find nearest order. This works, but I thought it might be nice to have it in the tool.
I love the new (relatively) ConsumerView Decoder Tool! I used to do it the hard way, and it was fragile.
However, one thing is still missing: the Mosaic fields (MOSAIC HOUSEHOLD and MOSAIC ZIP4) - these are output from the tool as nulls. So, not only do you not get it decoded, you have to join back to the input to get the fields back as they were.
First, at least please pass them through as they were.
But preferably, decode them to the Mosaic Segment/Group names.
I realize (or couldn't find) the source for the Mosaic segment definitions is not currently in a Calgary database, but the tool is in the Calgary group.
Utilisateur | Compte |
---|---|
6 | |
5 | |
3 | |
2 | |
2 |