riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-04 05:10:06 +06:00
Code Issues Actions 20 Packages Projects Releases Wiki Activity

Fix doctest for Blip2ForConditionalGeneration (#26737)

Browse Source 
* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar 2023-10-12 10:01:07 +02:00 committed by GitHub
parent e1cec43415
commit 3bc65505fc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 24 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
src/transformers/models/blip_2/modeling_blip_2.py
View File

@ -1272,14 +1272,10 @@ class Blip2Model(Blip2PreTrainedModel):
>>> import torch >>> import torch
>>> from transformers import AutoTokenizer, Blip2Model >>> from transformers import AutoTokenizer, Blip2Model
>>> device = "cuda" if torch.cuda.is_available() else "cpu" >>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
>>> model.to(device) # doctest: +IGNORE_RESULT
>>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/blip2-opt-2.7b") >>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt").to(device) >>> inputs = tokenizer(["a photo of a cat"], padding=True, return_tensors="pt")
>>> text_features = model.get_text_features(**inputs) >>> text_features = model.get_text_features(**inputs)
```""" ```"""
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
@ -1333,16 +1329,12 @@ class Blip2Model(Blip2PreTrainedModel):
>>> import requests >>> import requests
>>> from transformers import AutoProcessor, Blip2Model >>> from transformers import AutoProcessor, Blip2Model
>>> device = "cuda" if torch.cuda.is_available() else "cpu" >>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
>>> model.to(device) # doctest: +IGNORE_RESULT
>>> processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b") >>> processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw) >>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, return_tensors="pt").to(device, torch.float16) >>> inputs = processor(images=image, return_tensors="pt")
>>> image_outputs = model.get_image_features(**inputs) >>> image_outputs = model.get_image_features(**inputs)
```""" ```"""
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
@ -1381,15 +1373,12 @@ class Blip2Model(Blip2PreTrainedModel):
>>> import requests >>> import requests
>>> from transformers import Blip2Processor, Blip2Model >>> from transformers import Blip2Processor, Blip2Model
>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") >>> processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16) >>> model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> model.to(device) # doctest: +IGNORE_RESULT
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw) >>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, return_tensors="pt").to(device, torch.float16) >>> inputs = processor(images=image, return_tensors="pt")
>>> qformer_outputs = model.get_qformer_features(**inputs) >>> qformer_outputs = model.get_qformer_features(**inputs)
```""" ```"""
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
@ -1654,34 +1643,7 @@ class Blip2ForConditionalGeneration(Blip2PreTrainedModel):
Examples: Examples:
Image captioning (without providing a text prompt): Prepare processor, model and image input
```python
>>> from PIL import Image
>>> import requests
>>> from transformers import Blip2Processor, Blip2ForConditionalGeneration
>>> import torch
>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
>>> model = Blip2ForConditionalGeneration.from_pretrained(
... "Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16
... )
>>> model.to(device) # doctest: +IGNORE_RESULT
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, return_tensors="pt").to(device, torch.float16)
>>> generated_ids = model.generate(**inputs)
>>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
>>> print(generated_text)
two cats laying on a couch
```
Visual question answering (prompt = question):
```python ```python
>>> from PIL import Image >>> from PIL import Image
@ -1698,7 +1660,22 @@ class Blip2ForConditionalGeneration(Blip2PreTrainedModel):
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw) >>> image = Image.open(requests.get(url, stream=True).raw)
```
Image captioning (without providing a text prompt):
```python
>>> inputs = processor(images=image, return_tensors="pt").to(device, torch.float16)
>>> generated_ids = model.generate(**inputs)
>>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
>>> print(generated_text)
two cats laying on a couch
```
Visual question answering (prompt = question):
```python
>>> prompt = "Question: how many cats are there? Answer:" >>> prompt = "Question: how many cats are there? Answer:"
>>> inputs = processor(images=image, text=prompt, return_tensors="pt").to(device="cuda", dtype=torch.float16) >>> inputs = processor(images=image, text=prompt, return_tensors="pt").to(device="cuda", dtype=torch.float16)
@ -1712,20 +1689,10 @@ class Blip2ForConditionalGeneration(Blip2PreTrainedModel):
This greatly reduces the amount of memory used by the model while maintaining the same performance. This greatly reduces the amount of memory used by the model while maintaining the same performance.
```python ```python
>>> from PIL import Image
>>> import requests
>>> from transformers import Blip2Processor, Blip2ForConditionalGeneration
>>> import torch
>>> processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xl")
>>> model = Blip2ForConditionalGeneration.from_pretrained( >>> model = Blip2ForConditionalGeneration.from_pretrained(
... "Salesforce/blip2-flan-t5-xl", load_in_8bit=True, device_map={"": 0}, torch_dtype=torch.bfloat16 ... "Salesforce/blip2-opt-2.7b", load_in_8bit=True, device_map={"": 0}, torch_dtype=torch.bfloat16
... ) # doctest: +IGNORE_RESULT ... ) # doctest: +IGNORE_RESULT
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> prompt = "Question: how many cats are there? Answer:"
>>> inputs = processor(images=image, text=prompt, return_tensors="pt").to(device="cuda", dtype=torch.bfloat16) >>> inputs = processor(images=image, text=prompt, return_tensors="pt").to(device="cuda", dtype=torch.bfloat16)
>>> generated_ids = model.generate(**inputs) >>> generated_ids = model.generate(**inputs)

1
utils/slow_documentation_tests.txt
View File

@ -1,4 +1,5 @@
docs/source/en/generation_strategies.md docs/source/en/generation_strategies.md
docs/source/en/model_doc/ctrl.md docs/source/en/model_doc/ctrl.md
docs/source/en/task_summary.md docs/source/en/task_summary.md
src/transformers/models/blip_2/modeling_blip_2.py
src/transformers/models/ctrl/modeling_ctrl.py src/transformers/models/ctrl/modeling_ctrl.py