riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 18:51:14 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Make siglip examples clearer and error free (#33667)

Browse Source 
Update siglip.md

This was already partially fixed relative to the deployed docs. But the partial fix made it inconsistent. Additionally, giving the full text ("This is a photo of...") is likely not the desired output.
This commit is contained in:
John B Nelson 2024-09-27 01:33:55 -07:00 committed by GitHub
parent 7f9a9ca1e0
commit 55b7a0404e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/source/en/model_doc/siglip.md
View File

@ -85,7 +85,7 @@ If you want to do the pre- and postprocessing yourself, here's how to do that:
>>> candidate_labels = ["2 cats", "2 dogs"] >>> candidate_labels = ["2 cats", "2 dogs"]
# follows the pipeline prompt template to get same results # follows the pipeline prompt template to get same results
>>> candidate_labels = [f'This is a photo of {label}.' for label in candidate_labels] >>> texts = [f'This is a photo of {label}.' for label in candidate_labels]
>>> # important: we pass `padding=max_length` since the model was trained with this >>> # important: we pass `padding=max_length` since the model was trained with this
>>> inputs = processor(text=texts, images=image, padding="max_length", return_tensors="pt") >>> inputs = processor(text=texts, images=image, padding="max_length", return_tensors="pt")
@ -94,7 +94,7 @@ If you want to do the pre- and postprocessing yourself, here's how to do that:
>>> logits_per_image = outputs.logits_per_image >>> logits_per_image = outputs.logits_per_image
>>> probs = torch.sigmoid(logits_per_image) # these are the probabilities >>> probs = torch.sigmoid(logits_per_image) # these are the probabilities
>>> print(f"{probs[0][0]:.1%} that image 0 is '{texts[0]}'") >>> print(f"{probs[0][0]:.1%} that image 0 is '{candidate_labels[0]}'")
31.9% that image 0 is 'a photo of 2 cats' 31.9% that image 0 is 'a photo of 2 cats'
``` ```
@ -140,9 +140,9 @@ To load and run a model using Flash Attention 2, refer to the snippet below:
>>> candidate_labels = ["2 cats", "2 dogs"] >>> candidate_labels = ["2 cats", "2 dogs"]
# follows the pipeline prompt template to get same results # follows the pipeline prompt template to get same results
>>> candidate_labels = [f'This is a photo of {label}.' for label in candidate_labels] >>> texts = [f'This is a photo of {label}.' for label in candidate_labels]
# important: we pass `padding=max_length` since the model was trained with this # important: we pass `padding=max_length` since the model was trained with this
>>> inputs = processor(text=candidate_labels, images=image, padding="max_length", return_tensors="pt") >>> inputs = processor(text=texts, images=image, padding="max_length", return_tensors="pt")
>>> inputs.to(device) >>> inputs.to(device)
>>> with torch.no_grad(): >>> with torch.no_grad():
@ -240,4 +240,4 @@ Below is an expected speedup diagram that compares inference time between the na
## SiglipForImageClassification ## SiglipForImageClassification
[[autodoc]] SiglipForImageClassification [[autodoc]] SiglipForImageClassification
- forward - forward