New model encoding version #749
Merged
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
… of the result array, change tests accordingly.
Codecov Report
@@ Coverage Diff @@
## master #749 +/- ##
==========================================
- Coverage 79.38% 78.82% -0.57%
==========================================
Files 48 49 +1
Lines 7476 7650 +174
==========================================
+ Hits 5935 6030 +95
- Misses 1541 1620 +79
Continue to review full report at Codecov.
|
DvirDukhan
reviewed
May 18, 2021
DvirDukhan
reviewed
May 18, 2021
tests/flow/test_serializations.py
Outdated
Comment on lines
174
to
177
| tf_model = load_file_content('graph.pb') | ||
| con.execute_command('AI.MODELSTORE', key_name, 'TF', 'CPU', 'TAG', "TF_GRAPH_V2", 'BATCHSIZE', 4, | ||
| 'MINBATCHSIZE', 2, 'MINBATCHTIMEOUT', 1000, 'INPUTS', 2, 'a', 'b', 'OUTPUTS', 1, 'mul', | ||
| 'BLOB', tf_model) |
There was a problem hiding this comment.
you don't need to do this
you just need to load the rdb
tests/flow/test_serializations.py
Outdated
Comment on lines
188
to
190
| torch_model = load_file_content('pt-minimal.pt') | ||
| con.execute_command('AI.MODELSTORE', key_name, 'TORCH', 'CPU', 'TAG', "PT_MINIMAL_V2", 'BATCHSIZE', 4, | ||
| 'MINBATCHSIZE', 2, 'MINBATCHTIMEOUT', 1000, 'BLOB', torch_model) |
There was a problem hiding this comment.
you don't need to do this
you just need to load the rdb
tests/flow/test_serializations.py
Outdated
Comment on lines
210
to
211
| onnx_model = load_file_content('linear_iris.onnx') | ||
| con.execute_command('AI.MODELSTORE', key_name, 'ONNX', 'CPU', 'TAG', "ONNX_LINEAR_IRIS_V2", 'BATCHSIZE', 4, |
There was a problem hiding this comment.
you don't need to do this
you just need to load the rdb
DvirDukhan
approved these changes
May 19, 2021
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.
Introduce a new version of RDB decoding, v2. The change is in RAI_ModelType, where we now load to RDB the
minbatchtimeoutof a model (in addition to the rest of the model fields). Model that were encoded using v1 will be decoded with the v1 "old" decode callback.AI.MODELGET (META)command now returns the value of the modelminbatchtimeoutfield at the end of the meta-data array.