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.

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

Tensorflow2ncnn cannot translate convolution layer with bias #126

Closed
Corea opened this issue Sep 1, 2017 · 2 comments
Closed

Tensorflow2ncnn cannot translate convolution layer with bias #126

Corea opened this issue Sep 1, 2017 · 2 comments

Comments

@Corea
Copy link
Contributor

Corea commented Sep 1, 2017

error was raised with this code.

shape = (1, 17, 30, 13)

images = tf.placeholder(tf.float32, shape=shape, name="input/image")
layer = slim.conv2d(images, num_outputs=8, kernel_size=3, stride=1, padding="SAME",
                    activation_fn=None,
                    biases_initializer=initializers.xavier_initializer())
output = tf.identity(layer, name="output/score")
@Corea Corea changed the title Tensorflow2ncnn cannot translate convolution with bias Tensorflow2ncnn cannot translate convolution layer with bias Sep 1, 2017
@Corea
Copy link
Contributor Author

Corea commented Sep 4, 2017

Need to handle when node.op() == "Identity" and layer type is MemoryData.

@Corea
Copy link
Contributor Author

Corea commented Sep 4, 2017

It might be fixed by 92eef2b..?

@nihui nihui closed this as completed Sep 27, 2017
@jiefly jiefly mentioned this issue May 13, 2020
Closed
restyled-io bot pushed a commit that referenced this issue May 18, 2021
@qaz734913414
Merge pull request #126 from Tencent/master
4152f3a 
20201208
@zhu-zhaofei zhu-zhaofei mentioned this issue Dec 19, 2021
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@nihui @Corea