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

Jump to bottom

Fixed the segmentation fault in CamemBERT and VIT #6

Merged
merged 2 commits into from
Oct 9, 2024
Merged

Fixed the segmentation fault in CamemBERT and VIT #6

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a72d3ac
fixed the segmentation fault in CamemBERT and VIT
Yiran-ASU Oct 9, 2024
b29b271
fixed the segmentation fault in CamemBERT and VIT
Yiran-ASU Oct 9, 2024
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
6 changes: 5 additions & 1 deletion experiments/CamemBERT/model/CamemBERT.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ def __init__(self, model_name: str):
self.layer3 = AutoModelForTokenClassification.from_pretrained(model_name).classifier

def forward(self, input):
x = input.reshape(1, 7, 768)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hmmm, I don't see how this works. Shouldn't it be input = instead of x =? And you already did example_input = example_input.reshape(1, 7*768) in line 50 but reshape it back here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh, my mistake

# Return only the logits.
x = self.layer1(input).last_hidden_state
x = self.layer2(x)
Expand All @@ -44,7 +45,10 @@ def forward(self, input):

print("Parsing sentence tokens.")
example_input = prepare_sentence_tokens(model_name, sentence)
print(example_input.shape)
print("example_input shape: ", example_input.shape)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add comment above this line to show what is the original shape?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sure


example_input = example_input.reshape(1, 7*768)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Plz try reshape(7*768)?

print("example_input shape after reshaping: ", example_input.shape)

print("Instantiating model.")
model = OnlyLogitsHuggingFaceModel(model_name)
Expand Down
4 changes: 4 additions & 0 deletions experiments/VIT/model/vit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ def __init__(self):
self.layer2 = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224').vit.layernorm
self.layer3 = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224').classifier
def forward(self,x):
x = x.reshape(1, 197, 768)
x = self.layer1(x).last_hidden_state
x = self.layer2(x)
x = self.layer3(x)
Expand All @@ -37,6 +38,9 @@ def forward(self,x):
model = prepare().eval()
example_input = model(inputs)
print(example_input.shape)
example_input = example_input.reshape(1, 197*768)
print("example_input shape after reshaping: ", example_input.shape)


vit_model = vit().eval()
output = vit_model(example_input)
Expand Down
Loading