Skip to content

Fix monodepth2 issue #1472

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 4 commits into from
Oct 15, 2020
Merged

Fix monodepth2 issue #1472

merged 4 commits into from
Oct 15, 2020

Conversation

KuangHaofei
Copy link
Contributor

Fix two issues of monodepth2:

  1. posenet hybridiz issue: train monodepth2 error #1460
  2. lr decay issue: iters_per_epoch error #1462

@mli
Copy link
Member

mli commented Oct 14, 2020

Job PR-1472-2 is done.
Docs are uploaded to http://gluon-vision-staging.s3-website-us-west-2.amazonaws.com/PR-1472/2/index.html
Code coverage of this PR: pr.svg vs. Master: master.svg

bryanyzhu
bryanyzhu approved these changes Oct 14, 2020
View reviewed changes
Copy link
Collaborator

@bryanyzhu bryanyzhu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me. Thank you for resolving the issues.

@mli
Copy link
Member

mli commented Oct 15, 2020

Job PR-1472-3 is done.
Docs are uploaded to http://gluon-vision-staging.s3-website-us-west-2.amazonaws.com/PR-1472/3/index.html
Code coverage of this PR: pr.svg vs. Master: master.svg

@bryanyzhu bryanyzhu merged commit 0e97aaa into dmlc:master Oct 15, 2020
This was referenced Oct 15, 2020
Closed
Closed
@pandyadhatri
Copy link

XNetError Traceback (most recent call last)
in ()
20 # AutoGrad
21 with ag.record():
---> 22 output = [net(X) for X in data]
23 # loss = [loss_fn(yhat, y) for yhat, y in zip(output, label)]
24 loss_fn = gluon.loss.SoftmaxCrossEntropyLoss(sparse_label=False)

8 frames
/usr/local/lib/python3.7/dist-packages/mxnet/base.py in check_call(ret)
244 """
245 if ret != 0:
--> 246 raise get_last_ffi_error()
247
248

MXNetError: MXNetError: Shape inconsistent, Provided = [64,784], inferred shape=(64,4816896)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@zhreshold zhreshold zhreshold approved these changes

@bryanyzhu bryanyzhu bryanyzhu approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@KuangHaofei @mli @pandyadhatri @zhreshold @bryanyzhu