I am training a Neural Network model with pytorch.
Since this model is very complicated, I made use of the pytorch_xla package to use TPU. I finished training the model and now I want to save the weight so I will be able to use them from any envrionment.
I tried to save the data like so
file_name = "model_params"
torch.save(model.state_dict(), file_name)
and when I tried to load them (from environment which does not support TPU)
model.load_state_dict(torch.load(file name))
I got the following error
NotImplementedError: Could not run 'aten::empty_strided' with arguments from the 'XLA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'aten::empty_strided' is only available for these backends: [CPU, Meta, BackendSelect, Named, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, UNKNOWN_TENSOR_TYPE_ID, AutogradMLC, AutogradHPU, AutogradNestedTensor, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode].
Is there a way to do what I want?
Related
I want to segment pelvic in MRI from the SMIR dataset using the MONAILABEL plugin. I have read relatively a lot about this plugin. However, I can’t perform the segmentation well enough yet.
These are the steps I take to do so:
connecting the server using the anaconda prompt
enabling the plugin in Slicer and loading one image
labeling the pelvis manually using the paint button in the scribbles part and the updating
click “submit label”
and then repeating the process for some other images while the network is being trained.
After the training process, I actually could not see anything when opening the mask files.
I also encounter these two errors:
" AssertionError: Not a valid Label "
" TypeError: object of type ‘NoneType’ has no len() "
Is it the correct way of using MONAI or am I missing something?
Which aspects should I take into account before starting the process?
I would appreciate your help and suggestions.
Thank you
Is there any way to execute a post project transfer event when transferring a project to a PLC?
I want to automatically change the value of a variable using fx the PVI interface every time I do a transfer.
I am not entirely sure what the usecase is for this. However the easiest way for some kind of post transfer script would be to utilize the Runtime Utility Center (RUC).
In the RUC, you can define instruction lists for a B&R PLC with an online connection. This includes instructions for transferring projects and setting values of process variables (PVs).
For transferring the project with RUC, you need to create a RUC package. This can be done under Settings/Export to Runtime Utility Center. You could also do this from the command line. More details in the help under Project management/Project installation/ Performing project installation/Export RUC Guid: cfe34190-f436-4c14-b06d-3a4ca39be7e7
This will create a zip, which you can then use in your RUC. For transfer command there is a wizard which activates when you double click on the command Transfer to target under Project installation The result is a line in the instruction list, which might look like this:
Transfer "C:\path\to\your\zip\project.zip", "InstallMode=Consistent InstallRestriction=AllowUpdatesWithoutDataLoss KeepPVValues=1 ExecuteInitExit=1"
After transferring you can write your PV. Under Process variable functions in the RUC you can find the command Write process variable. Also here there is a wizard and the result looks like this:
WriteVariable "taskname\VariableName", "USINT", "2"
I am using AS 4.4.6. There might be slight differences when using a other version.
I've been following the Build your own image classifier using Transfer Learning tutorial found at this link.
At the end of the tutorial, it says you use your own data set, which I created by following the example in the tutorial. It successfully completed and created a folder ~/CNTK-Samples-2-3-1/Examples/Image/TransferLearning/Output, which is expected. Inside this output folder is predictions.txt, predOutput.txt, and TransferLearning.model.
My question is, how do I access TransferLearning.model? I'm not sure what to do with it and I can't find anything in the documentation allowing me to alter it or run it.
Once you successfully create your model, you can use it in Python environment (with CNTK) to classify your images. The code should look something like this:
#load the trained transfer learning model
trained_model = load_model(model_file)
#for every new image:
#get predictions for a single image
probs = eval_single_image(trained_model, img_file, image_width, image_height)
I want to make a network graph which shows the distribution of our documents in our folder structure.
I have the nodefile, edgefile and gephi graph file in this location:
https://1drv.ms/f/s!AuVfRBdVHkO7hgs5K9r9f7jBBAUH
What I do is:
Run the algorithm ForceAtlas2 with scaling 10-20, dissuade hub marked and prevent overlap marked, all other standard setting.
What I get is a graph with groups radial/spherical distributed. However, what I want is a tree directed network graph.
Anyone know how I can adjust Gephi to make this?
Thanks!
I just found a solution.
I tested the file format as shown on the Yed site "import excel file" page
http://yed.yworks.com/support/manual/import_excel.html
This gave me the Yed import dialog (took a life time to figure out that it's a pop up menu and not selectable through the standard menu)
Anyway, it worked and I've adjusted the test files with the data prepared for the Gehpi. This was pretty easy, I could used the source target ID's etc. Just copy paste.
I load it into Yed and used some directed and radial clustering algorithms on it. Works fine!
Below you can find the excel node/edge file used to import in Yed and the graph file you can open with Yed to see the final radial result.
https://1drv.ms/f/s!AuVfRBdVHkO7hg6DExK_eVkm5_mR
Only thing to figure out is how to combine the weight (which represents the number of documents) with the node size.
Unfortunately, as of version 0.9.0, Gephi no longer supports hierarchical graphs. Maybe try using a previous version?
Other alternatives involve more complex software, such as Graphviz, but you need a .dot file instead of your .csv. I looked all over, but could not find an easy-to-use csv to dot converter.
You could try looking at d3-hierarchy, a node.js program, but then again you need to use the not-so-user-friendly npm. If you look at the link, it looks like it can produce the kind of diagram you're looking for.
I trained a neural network model on Digits and it seemed to run fine there.
Then i exported the trained model files and copied them into a different system running the standard caffe web demo.
I hoped to just be able to plug those files in and have them run in Caffe but i am getting an error.
Specifically I copied my model into bvlc_reference_caffenet.caffemodel, the deploy.prototxt into deploy.prototxt, and the mean.binaryproto into the ilsvrc_2012_mean.npy file.
However when I try to run it , it appears to not like the format of the mean.binaryproto file as indicated by the error message:
IOError: Failed to interpret file '/home/vagrant/caffe/python/caffe/imagenet/ilsvrc_2012_mean.npy' as a pickle
what am I doing wrong here? Do I need to process the mean.binaryproto file from Digits somehow before I use it with caffe?
You need to convert the .binaryproto file to a numpy file.
There is a nice example here using caffe.io and caffe.proto.