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

remove strip #3262

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
+2 −17
Open

remove strip #3262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 0 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,9 +201,6 @@ def transform_fn(data_item):
calibration_dataset = nncf.Dataset(val_dataset, transform_fn)
# Step 3: Run the quantization pipeline
quantized_model = nncf.quantize(model, calibration_dataset)
# Step 4: Remove auxiliary layers and operations added during the quantization process,
# resulting in a clean, fully quantized model ready for deployment.
stripped_model = nncf.strip(quantized_model)
```

</details>
Expand Down
6 changes: 1 addition & 5 deletions docs/usage/training_time_compression/quantization_aware_training/Usage.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,11 +60,7 @@ ov_quantized_model = ov.convert_model(quantized_model.cpu(), example_input=dummy
# To OpenVINO format
import openvino as ov

# Removes auxiliary layers and operations added during the quantization process,
# resulting in a clean, fully quantized model ready for deployment.
stripped_model = nncf.strip(quantized_model)

ov_quantized_model = ov.convert_model(stripped_model)
ov_quantized_model = ov.convert_model(quantized_model)
```

</details>
Expand Down
4 changes: 0 additions & 4 deletions examples/post_training_quantization/tensorflow/mobilenet_v2/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,10 +144,6 @@ def transform_fn(data_item):
calibration_dataset = nncf.Dataset(val_dataset, transform_fn)
tf_quantized_model = nncf.quantize(tf_model, calibration_dataset)

# Removes auxiliary layers and operations added during the quantization process,
# resulting in a clean, fully quantized model ready for deployment.
tf_quantized_model = nncf.strip(tf_quantized_model)

###############################################################################
# Benchmark performance, calculate compression rate and validate accuracy

Expand Down
6 changes: 1 addition & 5 deletions examples/quantization_aware_training/tensorflow/mobilenet_v2/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,15 +160,11 @@ def transform_fn(data_item):
# However, training for more than 1 epoch would further improve the quantized model's accuracy.
tf_quantized_model.fit(train_dataset, epochs=1, verbose=1)

# Removes auxiliary layers and operations added during the quantization process,
# resulting in a clean, fully quantized model ready for deployment.
stripped_model = nncf.strip(tf_quantized_model)

###############################################################################
# Benchmark performance, calculate compression rate and validate accuracy

ov_model = ov.convert_model(tf_model)
ov_quantized_model = ov.convert_model(stripped_model)
ov_quantized_model = ov.convert_model(tf_quantized_model)

fp32_ir_path = ROOT / "mobilenet_v2_fp32.xml"
ov.save_model(ov_model, fp32_ir_path, compress_to_fp16=False)
Expand Down