# Workspace for loading Google vectors model using loadStaticModel **URL:** \ **Category:** DL4J\ **Created:** [March 2, 2020, 3:48pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203 "2020-03-02T15:48:29Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![ethiel](https://avatars.discourse-cdn.com/v4/letter/e/df788c/32.png) [@ethiel](https://community.konduit.ai/u/ethiel)\ **Post date:** [March 2, 2020, 3:48pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/1 "2020-03-02T15:48:29Z")
Hi, people. I’m trying to load the google vectors model into DL4j, to use it later for sentiment analysis. I’m able to do it but with a big cost in RAM memory. I read about workspaces and how the memory is hold off-heap, so I tried to load it using loadStaticModel inside a workspace,just to see if my RAM consumption was lower. However, I’m not able to do it if I set my available amount of RAM to a number less of 3.4 GB (the size of Google vectors model). So, does it mean the workspaces are only for certain operations?. It’s that a bug? . the code is quite simple: ``` final WorkspaceConfiguration mmap = WorkspaceConfiguration.builder() .initialSize(9500000000L) .policyLocation(LocationPolicy.MMAP) .policyAllocation(AllocationPolicy.STRICT) .policyReset(ResetPolicy.ENDOFBUFFER_REACHED) .tempFilePath("/Users/Downloads/temporalFile.temp") .build(); final File wordVectorsFile = new File("/sentiment/GoogleNews-vectors-negative3002.bin"); try (final MemoryWorkspace ws = Nd4j.getWorkspaceManager().getAndActivateWorkspace(mmap, "M2")) { final WordVectors wordVectors = WordVectorSerializer.loadStaticModel(wordVectorsFile); } ``` Any clues?. ---
**Author:** ![raver119](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@raver119](https://community.konduit.ai/u/raver119)\ **Post date:** [March 2, 2020, 3:53pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/2 "2020-03-02T15:53:44Z")
Workspace in this case will be used for vectors only. But, obviously, won’t be used for, say, Strings in it. But ye, i’d expect it to work. ---
**Author:** ![ethiel](https://avatars.discourse-cdn.com/v4/letter/e/df788c/32.png) [@ethiel](https://community.konduit.ai/u/ethiel)\ **Post date:** [March 2, 2020, 4:02pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/3 "2020-03-02T16:02:43Z")
Yes, I want to use it to load the vectors file only, outside JVM memory, and use it later. However, I can’t allocate vectors so process for loading the model fails. It shouldn’t be allocated to the workspace instead of RAM?. ---
**Author:** ![raver119](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@raver119](https://community.konduit.ai/u/raver119)\ **Post date:** [March 2, 2020, 4:04pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/4 "2020-03-02T16:04:31Z")
File an issue please, and I’ll take a look. I’d definitely expect it to work that way. ---
**Author:** ![ethiel](https://avatars.discourse-cdn.com/v4/letter/e/df788c/32.png) [@ethiel](https://community.konduit.ai/u/ethiel)\ **Post date:** [March 2, 2020, 7:06pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/5 "2020-03-02T19:06:06Z")
Done!. > > > \#### Issue Description > Workspace for loading Google vectors model using loadSta…ticModel does not load the model outside JVM memory. > > I’m trying to load the google vectors model into DL4j, to use it later. I’m able to do it but with a big cost in RAM memory. I read about workspaces and how the memory is hold off-heap, so I tried to load it using loadStaticModel inside a workspace, just to see if my RAM consumption was lower. However, I’m not able to do it if I set my available amount of RAM to a number less of 3.4 GB (the size of Google vectors model). > So, does it mean the workspaces are there only for certain operations?. > the code is quite simple: > > final WorkspaceConfiguration mmap = WorkspaceConfiguration.builder() > .initialSize(9500000000L) > .policyLocation(LocationPolicy.MMAP) > .policyAllocation(AllocationPolicy.STRICT) > .policyReset(ResetPolicy.ENDOFBUFFER\_REACHED) > .tempFilePath("/Users/Downloads/temporalFile.temp") > .build(); > final File wordVectorsFile = new File("/sentiment/GoogleNews-vectors-negative3002.bin"); > try (final MemoryWorkspace ws = Nd4j.getWorkspaceManager().getAndActivateWorkspace(mmap, "M2")) { > final WordVectors wordVectors = WordVectorSerializer.loadStaticModel(wordVectorsFile); > } > \- expected behavior: > The memory consumption is lower and Google vectors model is loaded > \- encountered behavior > The process fails because vectors couldn't be allocated. > > \#### Version Information > \* Deeplearning4j version: 1.0.0-beta6 > \* javacpp 1.5.2. > \* Platform information (OS, etc): macOS Mojave or Unix System. > > \#### Additional Information > This is the stack trace. Numbers are random. > Caused by: java.lang.OutOfMemoryError: Physical memory usage is too high: physicalBytes (2564) \> maxPhysicalBytes (1998) > > \#### Contributing > I'm willing to help for fixing this issue, of course. ---
**Author:** ![ethiel](https://avatars.discourse-cdn.com/v4/letter/e/df788c/32.png) [@ethiel](https://community.konduit.ai/u/ethiel)\ **Post date:** [March 2, 2020, 9:05pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/6 "2020-03-02T21:05:15Z")
This is a different question but related to solve the issue: How do I know that my workspace is actually storing my array? ---
**Author:** ![treo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/treo/32/47_2.png) [@treo](https://community.konduit.ai/u/treo)\ **Post date:** [March 3, 2020, 5:50pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/7 "2020-03-03T17:50:27Z")
Take a look inside the file and see what is inside. It should be the binary representation of the contents of the arrays inside that workspace. ---
**Author:** ![ethiel](https://avatars.discourse-cdn.com/v4/letter/e/df788c/32.png) [@ethiel](https://community.konduit.ai/u/ethiel)\ **Post date:** [March 3, 2020, 6:01pm UTC](https://community.konduit.ai/t/workspace-for-loading-google-vectors-model-using-loadstaticmodel/203/8 "2020-03-03T18:01:04Z")
Oh, thanks. I did it and indeed, the workspace is used.However, is not used as much as I think it should be used, but that’s a different issue.