Add a tutorial to describe how to use ONNX in TensorLayer #775
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
luomai
requested changes
Aug 4, 2018
example/tutorial_work_with_onnx.py
Outdated
| y_ = tf.placeholder(tf.int64, shape=[batch_size]) | ||
|
|
||
| net = tl.layers.InputLayer(x, name='input') | ||
| ## Professional conv API for tensorflow expert |
example/tutorial_work_with_onnx.py
Outdated
|
|
||
| if __name__ == '__main__': | ||
|
|
||
| #sess = tf.InteractiveSession() |
example/tutorial_work_with_onnx.py
Outdated
| acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) | ||
| # y_op = tf.argmax(tf.nn.softmax(y), 1) | ||
|
|
||
| # You can add more penalty to the cost function as follow. |
example/tutorial_work_with_onnx.py
Outdated
| print(" test acc: %f" % (test_acc / n_batch)) | ||
|
|
||
|
|
||
| if __name__ == '__main__': |
There was a problem hiding this comment.
As we discussed, we shall have a main function that is classified into four stages:
- Load a pre-trained model
- Save pre-trained model into two files: ckpt and pb.
- Save the ckpt and pb as a onnx file
- load the onnx file
- use the onnx file (which can be currently commented out)
The main function should have this structure.
There was a problem hiding this comment.
ok, I will change the structure of the main function as we discussed
There was a problem hiding this comment.
Another advice for the function is that shall we supply the stage that train the model from scratch ?
luomai
changed the title
luomai
approved these changes
Aug 8, 2018
luomai
pushed a commit
that referenced
this pull request
Nov 21, 2018
* add tutorial of TensorLayer work with ONNX framework * modify the changelog * remove the unused code * remove the useless code * modify the code with yapf format * modify the structure of the tutotial * modify the format with yapf * add pip onnx-tf * modify the onnx tutorial structure * modify the format * fix the Trailing whitespace * add the contribution in changelog
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Checklist
Motivation and Context
Description
1.add tutorial of TensorLayer work with ONNX framework