Jump to content

k1w

Members
  • Content Count

    19
  • Joined

  • Last visited

  • Days Won

    6

k1w last won the day on March 19

k1w had the most liked content!

Community Reputation

6 Neutral

About k1w

  • Rank
    Member

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

  1. Thanks WilfriedB. I use SQL in my day job, so trying your suggestions out shouldn't be a problem. Much appreciated!
  2. Is there any way to monitor the progress of generating AI labels? I'm attempting to generate labels for a lot of unlabeled photos (now that the "search for unassigned" bug is fixed), but it seems like a bunch of photos are not getting labeled, even after several hours. It's difficult to tell whether they aren't getting queued, whether the queue is stalled, or whether they were not processed successfully. When I look at the cvis.txt log file, I see a lot of entries like: DEBUG 2020-03-19 13:03:35,751 CVis.OrchestratorActor [29] - NextTaskMessage INFO 2020-03-19 13:03:35,760 CVis.ImageTask [29] - not found media items for processing DEBUG 2020-03-19 13:03:35,762 CVis.OrchestratorActor [29] - WorkDoneMessage DEBUG 2020-03-19 13:04:20,775 CVis.OrchestratorActor [29] - NextTaskMessage INFO 2020-03-19 13:04:20,791 CVis.ImageTask [29] - not found media items for processing DEBUG 2020-03-19 13:04:20,796 CVis.OrchestratorActor [29] - WorkDoneMessage DEBUG 2020-03-19 13:05:05,808 CVis.OrchestratorActor [33] - NextTaskMessage INFO 2020-03-19 13:05:05,818 CVis.ImageTask [33] - not found media items for processing DEBUG 2020-03-19 13:05:05,821 CVis.OrchestratorActor [33] - WorkDoneMessage DEBUG 2020-03-19 13:05:50,825 CVis.OrchestratorActor [34] - NextTaskMessage INFO 2020-03-19 13:05:50,840 CVis.ImageTask [34] - not found media items for processing DEBUG 2020-03-19 13:05:50,843 CVis.OrchestratorActor [34] - WorkDoneMessage DEBUG 2020-03-19 13:06:35,848 CVis.OrchestratorActor [35] - NextTaskMessage INFO 2020-03-19 13:06:35,859 CVis.ImageTask [35] - not found media items for processing DEBUG 2020-03-19 13:06:35,862 CVis.OrchestratorActor [35] - WorkDoneMessage When I look at my Google Cloud Vision API metrics, I see 89 requests in the past hour, but none in the past several minutes, and that's after marking 2000 photos in Daminion for labeling. BTW, in the cvis.txt log, when it does find a file, it seems like it's logging the location of it's thumbnail, not the original photo location. Is there any way to easily determine a actual photo file that has been processed? Example is: DEBUG 2020-03-19 13:31:33,598 CVis.OrchestratorActor [63] - NextTaskMessage DEBUG 2020-03-19 13:31:33,606 CVis.ImageTask [63] - 2\4e\24e1df6a-5b7b-482d-84f9-b603eca9b9c5.dat: 42880, 17164 DEBUG 2020-03-19 13:31:33,610 CVis.ImageTask [63] - file exitst: E:\Users\Daminion\AppData\Roaming\Daminion Server\Thumbnails\2\4e\24e1df6a-5b7b-482d-84f9-b603eca9b9c5.dat INFO 2020-03-19 13:31:33,614 CVis.ImageTask [63] - start GetBuffer INFO 2020-03-19 13:31:33,624 CVis.ImageTask [63] - end GetBuffer: 42880 DEBUG 2020-03-19 13:31:33,627 CVis.ImageTask [63] - get image from file DEBUG 2020-03-19 13:31:33,651 CVis.ImageTask [63] - start DetectLabels DEBUG 2020-03-19 13:31:34,333 CVis.ImageTask [63] - end DetectLabels INFO 2020-03-19 13:31:34,337 CVis.ImageTask [63] - [ { "mid": "/m/0838f", "description": "Water", "score": 0.9684016, "topicality": 0.9684016 }, { "mid": "/m/06q40", "description": "Smoke", "score": 0.891961336, "topicality": 0.891961336 }, { "mid": "/m/015s2f", "description": "Water resources", "score": 0.870399833, "topicality": 0.870399833 }, { "mid": "/m/07pw27b", "description": "Atmospheric phenomenon", "score": 0.8569148, "topicality": 0.8569148 }, { "mid": "/m/08t9c_", "description": "Grass", "score": 0.821845353, "topicality": 0.821845353 }, { "mid": "/m/049_3v", "description": "Yard", "score": 0.77845, "topicality": 0.77845 }, { "mid": "/m/025s3q0", "description": "Landscape", "score": 0.7564218, "topicality": 0.7564218 }, { "mid": "/m/0hrcj2p", "description": "Backyard", "score": 0.7451672, "topicality": 0.7451672 }, { "mid": "/m/07j7r", "description": "Tree", "score": 0.686921835, "topicality": 0.686921835 }, { "mid": "/m/0gmc028", "description": "Spray", "score": 0.677393854, "topicality": 0.677393854 } ] DEBUG 2020-03-19 13:31:34,342 CVis.ImageTask [63] - start UpdateCloudVisionTable DEBUG 2020-03-19 13:31:34,346 CVis.ImageTask [63] - end UpdateCloudVisionTable DEBUG 2020-03-19 13:31:34,350 CVis.ImageTask [63] - process label: { "mid": "/m/0838f", "description": "Water", "score": 0.9684016, "topicality": 0.9684016 } DEBUG 2020-03-19 13:31:34,354 CVis.ImageTask [63] - labels tag value id: 25 DEBUG 2020-03-19 13:31:34,357 CVis.ImageTask [63] - process label: { "mid": "/m/06q40", "description": "Smoke", "score": 0.891961336, "topicality": 0.891961336 } DEBUG 2020-03-19 13:31:34,361 CVis.ImageTask [63] - labels tag value id: 1494 DEBUG 2020-03-19 13:31:34,366 CVis.ImageTask [63] - process label: { "mid": "/m/015s2f", "description": "Water resources", "score": 0.870399833, "topicality": 0.870399833 } DEBUG 2020-03-19 13:31:34,372 CVis.ImageTask [63] - labels tag value id: 420 DEBUG 2020-03-19 13:31:34,376 CVis.ImageTask [63] - process label: { "mid": "/m/07pw27b", "description": "Atmospheric phenomenon", "score": 0.8569148, "topicality": 0.8569148 } DEBUG 2020-03-19 13:31:34,381 CVis.ImageTask [63] - labels tag value id: 270 DEBUG 2020-03-19 13:31:34,387 CVis.ImageTask [63] - process label: { "mid": "/m/08t9c_", "description": "Grass", "score": 0.821845353, "topicality": 0.821845353 } DEBUG 2020-03-19 13:31:34,393 CVis.ImageTask [63] - labels tag value id: 115 DEBUG 2020-03-19 13:31:34,398 CVis.ImageTask [63] - process label: { "mid": "/m/049_3v", "description": "Yard", "score": 0.77845, "topicality": 0.77845 } DEBUG 2020-03-19 13:31:34,404 CVis.ImageTask [63] - labels tag value id: 2 DEBUG 2020-03-19 13:31:34,408 CVis.ImageTask [63] - process label: { "mid": "/m/025s3q0", "description": "Landscape", "score": 0.7564218, "topicality": 0.7564218 } DEBUG 2020-03-19 13:31:34,412 CVis.ImageTask [63] - labels tag value id: 116 DEBUG 2020-03-19 13:31:34,418 CVis.ImageTask [63] - process label: { "mid": "/m/0hrcj2p", "description": "Backyard", "score": 0.7451672, "topicality": 0.7451672 } DEBUG 2020-03-19 13:31:34,424 CVis.ImageTask [63] - labels tag value id: 106 DEBUG 2020-03-19 13:31:34,430 CVis.ImageTask [63] - process label: { "mid": "/m/07j7r", "description": "Tree", "score": 0.686921835, "topicality": 0.686921835 } DEBUG 2020-03-19 13:31:34,434 CVis.ImageTask [63] - labels tag value id: 55 DEBUG 2020-03-19 13:31:34,440 CVis.ImageTask [63] - process label: { "mid": "/m/0gmc028", "description": "Spray", "score": 0.677393854, "topicality": 0.677393854 } DEBUG 2020-03-19 13:31:34,444 CVis.ImageTask [63] - labels tag value id: 2925 DEBUG 2020-03-19 13:31:34,451 CVis.OrchestratorActor [63] - NextTaskMessage
  3. Appears to be working for me as well. Thank you!
  4. Thanks, rene. My hope was to find something that would detect them automatically (or at least a high percentage of them), without having to manually go through all 2000 images (since they are scattered throughout). Plan B would be to do as you say.
  5. Hi everyone, I've discovered that with a recent import of about 2000 scanned family photos, that a small percentage of them were upside down during scanning. Rather than go through them manually, I was hoping there was some way to automatically detect and mark photos are likely to be flipped. Does Daminion (or some other software utility) have some capacity to suggest photos that are upside down? Note that I am not asking about the EXIF orientation flag, but rather detecting based on the contents of the image itself that it is wrong, perhaps using some neural net/deep learning model. I've done some quick googling without finding quite what I am looking for, but hoped that perhaps the more experienced Daminion pros here may have found a solution. Thanks!
  6. Wonderful to hear, Daria! Thanks for the update. Will it handle being able to search for photos with empty tags, and thus also adding tags only to those that have not yet been processed? If you delete all tags from a photo, does that get considered as "empty" (untagged) and thus would be requested again if you attempt to generate tags for unprocessed files, or will it be treated as "no tags" (tags were generated, discarded as unwanted, so not processed again)? Or will the user have the ability to specify either state per photo? Looking forward to trying it out!
  7. Bumping this to see if there's been any progress made the issues with AI labels -- searching for empty, recovering deleted AI labels, etc.?
  8. Any update following the remote session with Wilfried?
  9. No change after completing optimization. Searching for "AI Labels is empty" matches 48449 out of 48449 items. Searching for "AI Labels is not empty" matches 16095 out of 48449 items.
  10. That is correct. 48449 total files of which 16k of them have AI labels (done by repeating batches of 1000 files at a time). I will try the optimization now and report back.
  11. Tried with the new 6.3 build that was announced today. Still seems to be a problem searching for empty AI labels:
  12. If "Unknown" is the same as Unassigned, then all 48k+ photos are listed as Unknown, even though 16k+ of them have AI Tags (as correctly detected by the "is not empty" search.
  13. Build 2030 still has problems with searching for "AI Tags" "is empty". It returns all files as matches. But it looks like "AI Tags" "is not empty" correctly finds files with AI tags.
  14. Is there any update on being able to search for only photos with no AI Tags?
  15. I was selecting a batch of 1000 files, generating AI tags, and then walking away, so I don't know exactly how long it took to complete. But on my Google console, ti's showing a peak over the past 7 days of just over 200, comparable current usage, and so overall looks a lot similar to what you posted.
×
×
  • Create New...