mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-03 12:50:06 +06:00
203e27059b
* Standardize image-text-to-text-models-output add post_process_image_text_to_text to chameleon and cleanup Fix legacy kwarg behavior and deprecation warning add post_process_image_text_to_text to qwen2_vl and llava_onevision Add post_process_image_text_to_text to idefics3, mllama, pixtral processor * nit var name post_process_image_text_to_text udop * nit fix deprecation warnings * Add image-text-to-text pipeline * add support for image url in chat template for pipeline * Reformat to be fully compatible with chat templates * Add tests chat template * Fix imports and tests * Add pipeline tag * change logic handling of single prompt ans multiple images * add pipeline mapping to models * fix batched inference * fix tests * Add manual batching for preprocessing * Fix outputs with nested images * Add support for all common processing kwargs * Add default padding when multiple text inputs (batch size>1) * nit change version deprecation warning * Add support for text only inference * add chat_template warnings * Add pipeline tests and add copied from post process function * Fix batched pipeline tests * nit * Fix pipeline tests blip2 * remove unnecessary max_new_tokens * revert processing kosmos2 and remove unnecessary max_new_tokens * fix pipeline tests idefics * Force try loading processor if pipeline supports it * revert load_processor change * hardcode loading only processor * remove unnecessary try except * skip imagetexttotext tests for kosmos2 as tiny model causes problems * Make code clearer * Address review comments * remove preprocessing logic from pipeline * fix fuyu * add BC resize fuyu * Move post_process_image_text_to_text to ProcessorMixin * add guard in post_process * fix zero shot object detection pipeline * add support for generator input in pipeline * nit * change default image-text-to-text model to llava onevision * fix owlv2 size dict * Change legacy deprecation warning to only show when True
247 lines
9.9 KiB
Python
247 lines
9.9 KiB
Python
# Copyright 2021 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import unittest
|
|
|
|
from transformers import (
|
|
MODEL_FOR_ZERO_SHOT_OBJECT_DETECTION_MAPPING,
|
|
ZeroShotObjectDetectionPipeline,
|
|
is_vision_available,
|
|
pipeline,
|
|
)
|
|
from transformers.testing_utils import (
|
|
is_pipeline_test,
|
|
nested_simplify,
|
|
require_tf,
|
|
require_torch,
|
|
require_vision,
|
|
slow,
|
|
)
|
|
|
|
from .test_pipelines_common import ANY
|
|
|
|
|
|
if is_vision_available():
|
|
from PIL import Image
|
|
else:
|
|
|
|
class Image:
|
|
@staticmethod
|
|
def open(*args, **kwargs):
|
|
pass
|
|
|
|
|
|
@is_pipeline_test
|
|
@require_vision
|
|
@require_torch
|
|
class ZeroShotObjectDetectionPipelineTests(unittest.TestCase):
|
|
model_mapping = MODEL_FOR_ZERO_SHOT_OBJECT_DETECTION_MAPPING
|
|
|
|
def get_test_pipeline(
|
|
self,
|
|
model,
|
|
tokenizer=None,
|
|
image_processor=None,
|
|
feature_extractor=None,
|
|
processor=None,
|
|
torch_dtype="float32",
|
|
):
|
|
object_detector = ZeroShotObjectDetectionPipeline(
|
|
model=model,
|
|
processor=processor,
|
|
tokenizer=tokenizer,
|
|
image_processor=image_processor,
|
|
torch_dtype=torch_dtype,
|
|
)
|
|
|
|
examples = [
|
|
{
|
|
"image": "./tests/fixtures/tests_samples/COCO/000000039769.png",
|
|
"candidate_labels": ["cat", "remote", "couch"],
|
|
}
|
|
]
|
|
return object_detector, examples
|
|
|
|
def run_pipeline_test(self, object_detector, examples):
|
|
outputs = object_detector(examples[0].get("image"), examples[0].get("candidate_labels"), threshold=0.0)
|
|
|
|
n = len(outputs)
|
|
self.assertGreater(n, 0)
|
|
self.assertEqual(
|
|
outputs,
|
|
[
|
|
{
|
|
"score": ANY(float),
|
|
"label": ANY(str),
|
|
"box": {"xmin": ANY(int), "ymin": ANY(int), "xmax": ANY(int), "ymax": ANY(int)},
|
|
}
|
|
for i in range(n)
|
|
],
|
|
)
|
|
|
|
@require_tf
|
|
@unittest.skip(reason="Zero Shot Object Detection not implemented in TF")
|
|
def test_small_model_tf(self):
|
|
pass
|
|
|
|
@require_torch
|
|
def test_small_model_pt(self):
|
|
object_detector = pipeline(
|
|
"zero-shot-object-detection", model="hf-internal-testing/tiny-random-owlvit-object-detection"
|
|
)
|
|
|
|
outputs = object_detector(
|
|
"./tests/fixtures/tests_samples/COCO/000000039769.png",
|
|
candidate_labels=["cat", "remote", "couch"],
|
|
threshold=0.64,
|
|
)
|
|
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
{"score": 0.7235, "label": "cat", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.7218, "label": "remote", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.7184, "label": "couch", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.6748, "label": "remote", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6656, "label": "cat", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6614, "label": "couch", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6456, "label": "remote", "box": {"xmin": 494, "ymin": 105, "xmax": 521, "ymax": 127}},
|
|
{"score": 0.642, "label": "remote", "box": {"xmin": 67, "ymin": 274, "xmax": 93, "ymax": 297}},
|
|
{"score": 0.6419, "label": "cat", "box": {"xmin": 494, "ymin": 105, "xmax": 521, "ymax": 127}},
|
|
],
|
|
)
|
|
|
|
outputs = object_detector(
|
|
[
|
|
{
|
|
"image": "./tests/fixtures/tests_samples/COCO/000000039769.png",
|
|
"candidate_labels": ["cat", "remote", "couch"],
|
|
}
|
|
],
|
|
threshold=0.64,
|
|
)
|
|
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
[
|
|
{"score": 0.7235, "label": "cat", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.7218, "label": "remote", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.7184, "label": "couch", "box": {"xmin": 204, "ymin": 167, "xmax": 232, "ymax": 190}},
|
|
{"score": 0.6748, "label": "remote", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6656, "label": "cat", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6614, "label": "couch", "box": {"xmin": 571, "ymin": 83, "xmax": 598, "ymax": 103}},
|
|
{"score": 0.6456, "label": "remote", "box": {"xmin": 494, "ymin": 105, "xmax": 521, "ymax": 127}},
|
|
{"score": 0.642, "label": "remote", "box": {"xmin": 67, "ymin": 274, "xmax": 93, "ymax": 297}},
|
|
{"score": 0.6419, "label": "cat", "box": {"xmin": 494, "ymin": 105, "xmax": 521, "ymax": 127}},
|
|
]
|
|
],
|
|
)
|
|
|
|
@require_torch
|
|
@slow
|
|
def test_large_model_pt(self):
|
|
object_detector = pipeline("zero-shot-object-detection")
|
|
|
|
outputs = object_detector(
|
|
"http://images.cocodataset.org/val2017/000000039769.jpg",
|
|
candidate_labels=["cat", "remote", "couch"],
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
{"score": 0.2868, "label": "cat", "box": {"xmin": 324, "ymin": 20, "xmax": 640, "ymax": 373}},
|
|
{"score": 0.277, "label": "remote", "box": {"xmin": 40, "ymin": 72, "xmax": 177, "ymax": 115}},
|
|
{"score": 0.2537, "label": "cat", "box": {"xmin": 1, "ymin": 55, "xmax": 315, "ymax": 472}},
|
|
{"score": 0.1474, "label": "remote", "box": {"xmin": 335, "ymin": 74, "xmax": 371, "ymax": 187}},
|
|
{"score": 0.1208, "label": "couch", "box": {"xmin": 4, "ymin": 0, "xmax": 642, "ymax": 476}},
|
|
],
|
|
)
|
|
|
|
outputs = object_detector(
|
|
[
|
|
{
|
|
"image": "http://images.cocodataset.org/val2017/000000039769.jpg",
|
|
"candidate_labels": ["cat", "remote", "couch"],
|
|
},
|
|
{
|
|
"image": "http://images.cocodataset.org/val2017/000000039769.jpg",
|
|
"candidate_labels": ["cat", "remote", "couch"],
|
|
},
|
|
],
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
[
|
|
{"score": 0.2868, "label": "cat", "box": {"xmin": 324, "ymin": 20, "xmax": 640, "ymax": 373}},
|
|
{"score": 0.277, "label": "remote", "box": {"xmin": 40, "ymin": 72, "xmax": 177, "ymax": 115}},
|
|
{"score": 0.2537, "label": "cat", "box": {"xmin": 1, "ymin": 55, "xmax": 315, "ymax": 472}},
|
|
{"score": 0.1474, "label": "remote", "box": {"xmin": 335, "ymin": 74, "xmax": 371, "ymax": 187}},
|
|
{"score": 0.1208, "label": "couch", "box": {"xmin": 4, "ymin": 0, "xmax": 642, "ymax": 476}},
|
|
],
|
|
[
|
|
{"score": 0.2868, "label": "cat", "box": {"xmin": 324, "ymin": 20, "xmax": 640, "ymax": 373}},
|
|
{"score": 0.277, "label": "remote", "box": {"xmin": 40, "ymin": 72, "xmax": 177, "ymax": 115}},
|
|
{"score": 0.2537, "label": "cat", "box": {"xmin": 1, "ymin": 55, "xmax": 315, "ymax": 472}},
|
|
{"score": 0.1474, "label": "remote", "box": {"xmin": 335, "ymin": 74, "xmax": 371, "ymax": 187}},
|
|
{"score": 0.1208, "label": "couch", "box": {"xmin": 4, "ymin": 0, "xmax": 642, "ymax": 476}},
|
|
],
|
|
],
|
|
)
|
|
|
|
@require_tf
|
|
@unittest.skip(reason="Zero Shot Object Detection not implemented in TF")
|
|
def test_large_model_tf(self):
|
|
pass
|
|
|
|
@require_torch
|
|
@slow
|
|
def test_threshold(self):
|
|
threshold = 0.2
|
|
object_detector = pipeline("zero-shot-object-detection")
|
|
|
|
outputs = object_detector(
|
|
"http://images.cocodataset.org/val2017/000000039769.jpg",
|
|
candidate_labels=["cat", "remote", "couch"],
|
|
threshold=threshold,
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
{"score": 0.2868, "label": "cat", "box": {"xmin": 324, "ymin": 20, "xmax": 640, "ymax": 373}},
|
|
{"score": 0.277, "label": "remote", "box": {"xmin": 40, "ymin": 72, "xmax": 177, "ymax": 115}},
|
|
{"score": 0.2537, "label": "cat", "box": {"xmin": 1, "ymin": 55, "xmax": 315, "ymax": 472}},
|
|
],
|
|
)
|
|
|
|
@require_torch
|
|
@slow
|
|
def test_top_k(self):
|
|
top_k = 2
|
|
object_detector = pipeline("zero-shot-object-detection")
|
|
|
|
outputs = object_detector(
|
|
"http://images.cocodataset.org/val2017/000000039769.jpg",
|
|
candidate_labels=["cat", "remote", "couch"],
|
|
top_k=top_k,
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
{"score": 0.2868, "label": "cat", "box": {"xmin": 324, "ymin": 20, "xmax": 640, "ymax": 373}},
|
|
{"score": 0.277, "label": "remote", "box": {"xmin": 40, "ymin": 72, "xmax": 177, "ymax": 115}},
|
|
],
|
|
)
|