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

updated the deepcopy method, using pythons native marshal command #2390

Closed
wants to merge 1 commit into from
Closed

updated the deepcopy method, using pythons native marshal command #2390

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
5 changes: 3 additions & 2 deletions prototype_source/fx_graph_mode_ptq_dynamic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@
from io import open
import time
import copy
import marshal

import torch
import torch.nn as nn
Expand Down Expand Up @@ -238,9 +239,9 @@ def evaluate(model_, data_source):
.set_object_type(nn.LSTM, default_dynamic_qconfig)
.set_object_type(nn.Linear, default_dynamic_qconfig)
)
# Deepcopying the original model because quantization api changes the model inplace and we want
# Deepcopying the original using native python method marshal model because quantization api changes the model inplace and we want
# to keep the original model for future comparison
model_to_quantize = copy.deepcopy(model)
model_to_quantize = marshal.loads(marshal.dumps(model))
Samsonboadi marked this conversation as resolved.
Show resolved Hide resolved
prepared_model = prepare_fx(model_to_quantize, qconfig_mapping, example_inputs)
print("prepared model:", prepared_model)
quantized_model = convert_fx(prepared_model)
Expand Down