SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update old existing feature extractor references (#24552)

Browse Source 
* Update old existing feature extractor references

* Typo

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* Address comments from review - update 'feature extractor'
Co-authored by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
This commit is contained in:
amyeroberts
2023-06-29 10:17:36 +01:00
committed by GitHub
parent 10c2ac7bc6
commit ae454f41d4
138 changed files with 762 additions and 743 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/models/vision_encoder_decoder/test_modeling_flax_vision_encoder_decoder.py
View File

@@ -48,7 +48,7 @@ if is_torch_available():
if is_vision_available():
from PIL import Image
from transformers import ViTFeatureExtractor
from transformers import ViTImageProcessor
@require_flax
@@ -462,12 +462,12 @@ class FlaxViT2GPT2ModelIntegrationTest(unittest.TestCase):
def test_inference_coco_en(self):
loc = "ydshieh/vit-gpt2-coco-en"
feature_extractor = ViTFeatureExtractor.from_pretrained(loc)
image_processor = ViTImageProcessor.from_pretrained(loc)
tokenizer = AutoTokenizer.from_pretrained(loc)
model = FlaxVisionEncoderDecoderModel.from_pretrained(loc)
img = prepare_img()
pixel_values = feature_extractor(images=img, return_tensors="np").pixel_values
pixel_values = image_processor(images=img, return_tensors="np").pixel_values
decoder_input_ids = np.array([[model.config.decoder_start_token_id]])
logits = model(pixel_values, decoder_input_ids)[0]

12
tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py
View File

@@ -45,7 +45,7 @@ if is_tf_available():
from transformers import (
AutoConfig,
AutoFeatureExtractor,
AutoImageProcessor,
AutoTokenizer,
TFAutoModel,
TFAutoModelForCausalLM,
@@ -64,7 +64,7 @@ if is_torch_available():
if is_vision_available():
from PIL import Image
from transformers import ViTFeatureExtractor
from transformers import ViTImageProcessor
@require_tf
@@ -828,11 +828,11 @@ class TFVisionEncoderDecoderModelSaveLoadTests(unittest.TestCase):
load_weight_prefix = TFVisionEncoderDecoderModel.load_weight_prefix
config = self.get_encoder_decoder_config()
feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")
decoder_tokenizer = AutoTokenizer.from_pretrained("gpt2")
img = prepare_img()
pixel_values = feature_extractor(images=img, return_tensors="tf").pixel_values
pixel_values = image_processor(images=img, return_tensors="tf").pixel_values
decoder_input_ids = decoder_tokenizer("Linda Davis", return_tensors="tf").input_ids
with tempfile.TemporaryDirectory() as tmp_dirname:
@@ -893,13 +893,13 @@ class TFViT2GPT2ModelIntegrationTest(unittest.TestCase):
def test_inference_coco_en(self):
loc = "ydshieh/vit-gpt2-coco-en"
feature_extractor = ViTFeatureExtractor.from_pretrained(loc)
image_processor = ViTImageProcessor.from_pretrained(loc)
tokenizer = AutoTokenizer.from_pretrained(loc)
model = TFVisionEncoderDecoderModel.from_pretrained(loc)
# We will verify our results on an image of cute cats
img = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
pixel_values = feature_extractor(images=img, return_tensors="tf").pixel_values
pixel_values = image_processor(images=img, return_tensors="tf").pixel_values
decoder_input_ids = tf.constant([[model.config.decoder_start_token_id]])

6
tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py
View File

@@ -62,7 +62,7 @@ if is_vision_available():
import PIL
from PIL import Image
from transformers import ViTFeatureExtractor
from transformers import ViTImageProcessor
@require_torch
@@ -749,7 +749,7 @@ class ViT2GPT2ModelIntegrationTest(unittest.TestCase):
def test_inference_coco_en(self):
loc = "ydshieh/vit-gpt2-coco-en"
feature_extractor = ViTFeatureExtractor.from_pretrained(loc)
image_processor = ViTImageProcessor.from_pretrained(loc)
tokenizer = AutoTokenizer.from_pretrained(loc)
model = VisionEncoderDecoderModel.from_pretrained(loc)
model.to(torch_device)
@@ -757,7 +757,7 @@ class ViT2GPT2ModelIntegrationTest(unittest.TestCase):
# We will verify our results on an image of cute cats
img = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
pixel_values = feature_extractor(images=img, return_tensors="pt").pixel_values.to(torch_device)
pixel_values = image_processor(images=img, return_tensors="pt").pixel_values.to(torch_device)
decoder_input_ids = torch.tensor([[model.config.decoder_start_token_id]]).to(torch_device)