IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[POT] Fix bug in classification sample (#19490)

Browse Source 
* Fix bug in classification sample

* fix readme
This commit is contained in:
Liubov Talamanova 2023-08-30 12:18:44 +01:00 committed by GitHub
parent d84fa07841
commit b790458da6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/pot/openvino/tools/pot/api/samples/classification/README.md
View File

@ -32,7 +32,7 @@ How to Run the Example
.. code-block:: sh
python3 ./classification_example.py -m <PATH_TO_IR_XML> -a <IMAGENET_ANNOTATION_FILE> -d <IMAGES_DIR>
python3 ./classification_sample.py -m <PATH_TO_IR_XML> -a <IMAGENET_ANNOTATION_FILE> -d <IMAGES_DIR>
Optional: you can specify .bin file of IR directly using the ``-w``, ``--weights`` options.

7
tools/pot/openvino/tools/pot/api/samples/classification/classification_sample.py
View File

@ -210,10 +210,9 @@ def optimize_model(args):
# Step 6: Execute the pipeline.
compressed_model = pipeline.run(model)
# Step 7 (Optional): Compress model weights quantized precision
# in order to reduce the size of final .bin file.
if not args.keep_uncompressed_weights:
compress_model_weights(compressed_model)
# Step 7: Compress model weights quantized precision
# in order to reduce the size of final .bin file.
compress_model_weights(compressed_model)
return compressed_model, pipeline