• Global community
    • Language:
      • Deutsch
      • English
      • Español
      • Français
      • Português
  • 日本語コミュニティ
    Dedicated community for Japanese speakers
  • 한국 커뮤니티
    Dedicated community for Korean speakers
Exit
3

Lightroom 6 / CC2015 - Facial Recognition Terribly Slow, not using all of CPU or GPU, still keeps going when paused.

Explorer ,
Apr 24, 2015 Apr 24, 2015

Copy link to clipboard

Copied

This is actually a couple of issue but wondering if others are experiencing it and worked through it.

I am using a Dual Xeon CPU 3.2 ghz Mac Pro, Catalog on SSD, Images files on Mirrored Pair, Dedicated GPU (max I can install in my version of Mac Pro) and hardware acceleration enabled in Lightroom.

I watched the Lightroom 6 Facial Recognition tutorial which leaves out a lot of the bulk editing and says basically let it loose on your whole catalog.. NOT recommended.

I started out with a couple small portrait galleries that identified a couple hundred total people to seed facial recognition so it didn't suggest everyone is the first person I confirmed (which it will do otherwise). I have also optimized my catalog multiple times.

I have encountered the following serious performance issues and bugs with Facial Recognition.:

  • Lightroom Facial Recognition goes to a ridiculous crawl after about 2000 images to be confirmed. (i.e. 2000-2300 in a couple hours, 800-1200 in the next 12 hours)
  • Lightroom becomes largely unresponsive after having a fair number of images to be confirmed, even after pausing Address and Facial Recognition. So even selecting 4 rows of images can take 5 minutes with several long pauses.
  • Once I select and click confirm it takes up to 2 minutes to update the "to be confirmed" list again.
  • When I click on an individual at the top of the page, pause facial recognition and address lookup it still continues to "Look for similar faces" [BUG!!!!!!!!] even though all I want to do is just confirm some individuals more quickly in bulk with the images already identified.. not continue to look for more as a work around for the painfully slow responsiveness of the module.

The odd part is that with all of the performance issues Lightroom will not use more than 20-30% of my two Xeon CPUs, barely touches my GPU (<10% CPU, 30% memory), my and no more than 35% of my memory. Computer Temps are also barely above startup temperatures and 15-25 degrees cooler than when I run other applications which will consume my entire CPU and memory if I let it. I have explored Lightroom's settings but seen nothing further I can configure to speed it all up.  I have also attempted the operation on images on the SSD, my drobo (known to be slow), an independent fast disk I have, and a pair of raided disks and have the same issues.

I will also note that all of my other applications seem to continue to operate just fine.. the slowness seems to be contained to the Lightroom application itself.

Lightroom version: 6.0 [1014445]

Operating system: Mac OS 10 Version: 10.10 [3]

Application architecture: x64

Logical processor count: 8

Processor speed: 3.2 GHz

Built-in memory: 18,432.0 MB

Real memory available to Lightroom: 18,432.0 MB

Real memory used by Lightroom: 5,537.5 MB (30.0%)

Virtual memory used by Lightroom: 32,240.6 MB

Memory cache size: 4,342.0 MB

Maximum thread count used by Camera Raw: 8

Camera Raw SIMD optimization: SSE2

Displays: 1) 2048x1152

Graphics Processor Info:

NVIDIA GeForce GTX 285 OpenGL Engine

Check OpenGL support: Passed

Vendor: NVIDIA Corporation

Version: 3.3 NVIDIA-10.0.31 310.90.10.05b12

Renderer: NVIDIA GeForce GTX 285 OpenGL Engine

LanguageVersion: 3.30

Application folder: /Applications/Adobe Lightroom

Library Path: /Users/DryClean/Documents/Lightroom_Catalog/MyCat_LR6.lrcat

Settings Folder: /Users/DryClean/Library/Application Support/Adobe/Lightroom

Anyone have any suggestions?

Views

34.6K

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Similar issues here. When showing a few hundert unnamed people, the interactive face tagging is so slow that it is almost unusable. Usually several seconds waiting time between clicks, frequent "beach balls", and also a bug where I can not select some of the faces when using Conmmand-click.

The whole purpose of this feature is to speed up a time consuming and tedious process. An unresponsive interface does not help in any way. I hope an update will fix this.

I am running an 2011 iMac 27 inch with HDD (no SSD), 12 GB RAM.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Since writing the original post I can too confirm I am experiencing the "can't control-select/command-select" some images but can select others as well. I have had it happen when I have no images selected and just wanting to do one image or when I have dozens of other images selected.

I will also clarify the 2000-2300 images reference above, that is actually "unnamed people".. I haven't been watching the number of indexed images as closely since it doesn't display. 

But do know again last night it 12 hours I set it upon 15000 images (raw image count, not unnamed people) which almost all people had a fair profile already established this morning it still has 5000 to go.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Same issue. I have 62500 pictures in my catalog and it took about 2 days to analyze. Tagging people is painfully slow. I now have tagged about 2500 faces and 77000 are unnamed. Many of them will stay unnamed but LR does not have an ignore face feature like Picasa.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

swoga‌  You have a good point about excluding directories. I for example have some wedding photography sets I do not need Lightroom trying to identify every single wedding guest in a group shot, and even if I did want to include the directory and only cared about the wedding party I do not have a way to exclude everyone else. That may help but still doesn't address the core issue.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Jun 02, 2015 Jun 02, 2015

Copy link to clipboard

Copied

Still the same problem, It took also 2 days and notice that it miss close to 50% of the faces. I have notice that when I started to check individual picture. Many of the ppl where not even selected even there where a perfect head shot.

Hope in the next release they will fix the speed issue and the quality of the selection.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Another interface bug that I found: when editing the confirmed faces to screen out the ones that are wrong, LR regularly does not register an edit. I.e. I type in a new name for a face and confirm, but the tag does not change. This happens especially when I edit several faces in quick succession. So I have to make the edit, and then watch the interface to confirm that the wrong face really disappears.

Does anyone else see the same thing?

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Once you are in "slow mode" you have to wait for every action. Even selecting multiple images with ctrl+click (on win) takes sometimes more than 5 seconds. I speak from the white border that says: "yes, you have selected an image"

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 25, 2015 Apr 25, 2015

Copy link to clipboard

Copied

Same thing on Win7 with i7-4770K 3,5 GHz, 16GB Ram and GeForce GTX 970.

Slow, slower, slowest and no System load while tagging faces

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 26, 2015 Apr 26, 2015

Copy link to clipboard

Copied

Same here, insanely slow to do anything.

Just trying to rename one face takes a good 45 seconds or more before the UI updates with the name change.

Quad 4GHz

32GB Ram

550MB read/write SSD

Nvidia 680

Windows 8.1 Pro x64

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 27, 2015 Apr 27, 2015

Copy link to clipboard

Copied

I am reviewing 220K photos -- it's extremely painful.  So painful that my wife doesn't want me on the computer any more, since all I'm trying to do (for hours) is combat the swelling tide of thousands of photos.

And you name it -- tires, sand, grass -- it tries to name it -- not to mention pets!

I'm surprised at how poor it is in differentiating different people, tires, pets, etc. -- many of them it says are all the same person / pet -- ??

And the speed is unbelievably slow.

This is almost so painful I wish I'd never started it -- sad.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 27, 2015 Apr 27, 2015

Copy link to clipboard

Copied

I have about the same number of photos (~225k) and I am just letting it do a set of directories at a time now. The batch of 40000 pre-sorted, pre-keyworded (as I had everyone's name already in a keyword which it does not use) photos took from Friday evening till Monday morning for it just to go through. I decided until it has recognized all of the faces at this point I am not going to doing any more confirming, tagging, etc. Facial Recognition at this point is far from becoming part of my work flow if it is going to be this slow.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 28, 2015 Apr 28, 2015

Copy link to clipboard

Copied

And ditto here too. Great idea, poor implmentation. In it's current state this feature is totally unusable (other than a handful of small galleries). Trying to work with 1000's or 10's of thousands of images grinds the process to a crawl. Constanst screen reloads, lags, freezes etc. Needs major work. Rather fustrating as it's the main reason I upgraded from LR5 which itself was only purchased a few months back. I'm seriously condsidering a request for refund.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 28, 2015 Apr 28, 2015

Copy link to clipboard

Copied

Now I'm experiencing data loss.  The faces I've detected just got kicked out -- like 1,500 of them.

I called Adobe, waited on hold for a while, and some guy picked up, acting like I was bothering him (??).  When I started explaining my problem, he HUNG UP -- !!

This version is junk -- sorry, it is.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Apr 29, 2015 Apr 29, 2015

Copy link to clipboard

Copied

Yes same here - MacPro Late 2013 3.5GHz Hex Core, 16GB, catalog on SSD...

Face recognition is painfully slow, seems to run on a single core, and very slow to just go through select faces to be confirmed, which is peculiar as just selecting isn't supposed to be a CPU intensive operation.

Same performance observation when running over the whole catalog of 120k pictures, slows down.

Generally speaking I need to quit and restart lightroom to get back decent performance in all face recognition related operations.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Participant ,
Apr 29, 2015 Apr 29, 2015

Copy link to clipboard

Copied

Forget it if someone's oriented in profile or has sunglasses on. It offers you cartoons on magazine covers and billboards, patches of lawn, people of multiple races and genders, and never narrows the range of whacky suggestions no matter how many faces you confirm.

My wife was in the room when it asked me if an Emperor Palpatine PEZ dispenser was her (and she's an attractive woman!). She got pissed off at ME.

This feature is poorly conceived and executed and an uncharacteric misstep for an otherwise great program—enough so that it shakes my confidence in its future development.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 30, 2015 Apr 30, 2015

Copy link to clipboard

Copied

To be fair to Adobe, a good facial recognition program should identify all faces in a photograph even if it is a human like face on a Pez dispenser like you mentioned and ABSOLUTELY also do it if you have billboards, magazines, etc in the background. This is how it picks many faces out of a crowd.

Also Facial Recognition is a predictive analytic tool that requires training. If you let it go on your entire catalog without some 'training directories' first it will have a horrible ID rate. You need to train it first.  I have used other image recognition programs and they too need to be trained. Also keep in mind that Facial Recognition is step one in the evolution of this.. coming next are identification of "what is a bridge", "What is an car" , "what is a Bear", etc

My primary issue is the speed performance of the engine and it not utilizing the resources made available to it.This thread is not intended to be RANT about how you do not like the results of its matching.. please start another thread for that.

I posted this Blog Post on some tips about how to work around some of the performance issues as well as described how I initially trained it and though yes it does sometimes think a bunch of leaves or a car ornament is a face... but how I trained it on my 48,000 image set.. I only got about 100 instances of that if I recall right.. so not too bad considering.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Participant ,
Apr 30, 2015 Apr 30, 2015

Copy link to clipboard

Copied

I agree it should identify photographic faces on magazine covers and billboards, which is why I specified "cartoon" illustrations. It seems like it should be able to tell the difference between the primitive drawing of a queen on a playing card and a real person, but Adobe's own training video shows it mistaking a playing card for a person. Maybe I'm asking too much, though. I'd be happy if it compared faces across my entire library instead of just within folders, if the results narrowed the suggestions instead of expanding them, and if the spinning wheels would go away.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 30, 2015 Apr 30, 2015

Copy link to clipboard

Copied

It does use the training data from across your library, not just a specific folder. I can definitely confirm this as I used a couple specific folders / collections (say my 5 star images with pick flag) and then let it loose and it uses that data to id people and once trained it does decently well though think it could group the stacks together better.

My primary gripe is performance of Lightroom 6 when using Facial Recognition, the rest of quite reasonable once trained.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Participant ,
Apr 30, 2015 Apr 30, 2015

Copy link to clipboard

Copied

Christopher, your blog post is terrific! I arrived at basically the same set of workarounds and tips while working with the program over the last week.

Like you say, better speed would help a lot but the feature itself also doesn't seem that effective at actually identifying people and doesn't seem to use the timeline at all, sometimes identifying the same person as an 80 year old in a photo from 2008 and an infant in a photo from 2013. I understand you'd like to restrict this thread to performance issues but it seems these things must be connected: if Lightroom made fewer false positives and used more tools in its algorithm, including detecting when a shot is part of a burst of shots of the same person, and grouped rejected faces as well as confirmed faces, it would run faster. And in any case, having to correct trivial errors and then wait twenty seconds between clicks is a big bottleneck to productivity. Accuracy is connected to speed in that regard, too. Cheers.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
Apr 30, 2015 Apr 30, 2015

Copy link to clipboard

Copied

"Like you say, better speed would help a lot but the feature itself also doesn't seem that effective at actually identifying people and doesn't seem to use the timeline at all, sometimes identifying the same person as an 80 year old in a photo from 2008 and an infant in a photo from 2013. I know you'd like to restrict the thread to performance issues but it seems these things must be connected: if Lightroom made fewer false positives and used more tools in its algorithm, including detecting when a shot is part of a burst of shots of the same person, and grouped rejected faces as well as confirmed faces, it would run faster."

omg -- this is some pretty deep stuff -- much deeper than LR could ever do, that's for sure -- !!

imagine the feature actually working.

i mean, they've taken an "upgrade feature" and basically killed LR with it.  there's no way to shut off face recognition, and it slows down your usage to a crawl.

to me, it's almost like a bug living in the software -- and there's no way to get rid of it --

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
May 06, 2015 May 06, 2015

Copy link to clipboard

Copied

Face recognition can be paused.  Hover the cursor over your Identity Plate, top left corner of the corner of the screen.  Click the ID plate. Options appear to pause Face Recognition and Address Lookup. 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 06, 2015 May 06, 2015

Copy link to clipboard

Copied

alksaki2‌ While you can in theory "pause" facial recognition it doesn't truly pause it in all areas. Such as if you go into the People view it still continues to "Find Similar People" and if you are paused but are in the Facial recognition module and reject a suggestion it will continue crunching away and attempting to make alternative suggestions even causing continued lag. The "pause function" only seems to pause identifying faces in images that have not yet been indexed.

At @edgduke, stay out of the facial recognition module while it is indexing and stay in the Loupe mode. It may not appear that it is indexing (recognizing faces in images), but it is continuing to do so as long as you do not have it paused. It seems to speed it up quite a lot but still VERY slow only using a fraction of the hardware resources available to it, but at least it is not trying to dynamically update a grid view for 130,000+ unknown individuals with every new image it processes.  Someone pointed this out to me and it really helped me get through the last 25% of my 228k catalog faster. See my blog post where I also point out a few more tips as well as some more issues.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
May 06, 2015 May 06, 2015

Copy link to clipboard

Copied

crsouser‌ - fantastic recommendation -- thank you!!  who would have thought -- !!!

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Beginner ,
May 06, 2015 May 06, 2015

Copy link to clipboard

Copied

crouser, thanks for the tips.  I've been using LR6 for just a few days.  As you mentioned, I found that pausing the face search on the entire catalog helps performance while editing. I will go to your blog for your other helpful tips.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines