-
Notifications
You must be signed in to change notification settings - Fork 2k
Loading Pretrained Models tutorial fails when running prediction #1559
Comments
Thanks for reporting. Trying to repro. |
I have a segv repro, now figuring out what's causing it. I'll document my steps here: For starters, these are the blobs + dimensions after loading the workspace.CreateNet(init_net, True)
for b in workspace.Blobs():
x = workspace.FetchBlob(b)
print("{}: {}".format(b, x.shape))
|
The segv happens here, where |
(@ryanrolds I think you must have run with |
Is that the default behavior? I'm encountering this issue with a build from master following directions on the site. |
Yep, it's all good, it's just why I wasn't seeing the enforce fire, but a hard segv. |
Any progress on this issue? |
RuntimeError Traceback (most recent call last) RuntimeError: [enforce fail at tensor.h:675] i < dims_.size(). 0 vs 0. Exceeding ndim limit Error from operator: |
@pietern have you solve this problem? |
Hi @danfouer and @ryanrolds - it looks like the SqueezeNet model in Amazon S3 (where the model downloader gets files from) was corrupt. I've just updated with the one in GitHub. Can you confirm doing the following
again and replacing the file allows you to run the tutorial? Thanks for your patience! |
Awesome. I will confirm ASAP, it may be this weekend. Thank you. |
Changing this line "results = p.run([img])" to "results = p.run({'data': img})" can solve the problem for the old model. |
Confirming that the new model resolved the issue. Thanks. |
hi! i have the last mobilenet_v2 and the error persist results = p.run({'data': img}) |
In caffe2/caffe2/blob/master/caffe2/python/tutorials/Loading_Pretrained_Models.ipynb fails with:
The text was updated successfully, but these errors were encountered: