Skip to content
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.

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

Failed to load pretrained deeplab model for training #16

Open
EryiXie opened this issue Jan 21, 2019 · 1 comment
Open

Failed to load pretrained deeplab model for training #16

EryiXie opened this issue Jan 21, 2019 · 1 comment

Comments

@EryiXie
Copy link

EryiXie commented Jan 21, 2019

Hi author,

thanks for your impressive work. Anyhow I met an issue by run train_planenet.py with a pretrained deeplab model.
The model is downloaded from this page https://github.com/DrSleep/tensorflow-deeplab-resnet under the chapter "Caffe to TensorFlow conversion"

The error which I got looks like:
[[Node: save_1/RestoreV2_310 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_1/Const_0_0, save_1/RestoreV2_310/tensor_names, save_1/RestoreV2_310/shape_and_slices)]]
2019-01-21 16:31:31.072749: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Tensor name "crfrnn/compatibility_matrix" not found in checkpoint files /home/xie/python_nn_framework/PlaneNet-master/pretrainedModels/deeplab_resnet.ckpt

It would be great if anyone can figure out, why error like this appears or did I make a mistake somewhere somehow? Thanks.

@chenliu-wustl
Copy link
Collaborator

Sorry for the late response. I just fixed the bug. Please let me know if it still doesn't work.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants