Add EfficientLoFTR model (#36355)
* initial commit * Apply suggestions from code review Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * fix: various typos, typehints, refactors from suggestions * fix: fine_matching method * Added EfficientLoFTRModel and AutoModelForKeypointMatching class * fix: got rid of compilation breaking instructions * docs: added todo for plot * fix: used correct hub repo * docs: added comments * fix: run modular * doc: added PyTorch badge * fix: model repo typo in config * fix: make modular * fix: removed mask values from outputs * feat: added plot_keypoint_matching to EfficientLoFTRImageProcessor * feat: added SuperGlueForKeypointMatching to AutoModelForKeypointMatching list * fix: reformat * refactor: renamed aggregation_sizes config parameter into q, kv aggregation kernel size and stride * doc: added q, kv aggregation kernel size and stride doc to config * refactor: converted efficientloftr implementation from modular to copied from mechanism * tests: overwrote batching_equivalence for "keypoints" specific tests * fix: changed EfficientLoFTRConfig import in test_modeling_rope_utils * fix: make fix-copies * fix: make style * fix: update rope function to make meta tests pass * fix: rename plot_keypoint_matching to visualize_output for clarity * refactor: optimize image pair processing by removing redundant target size calculations * feat: add EfficientLoFTRImageProcessor to image processor mapping * refactor: removed logger and updated attention forward * refactor: added auto_docstring and can_return_tuple decorators * refactor: update type imports * refactor: update type hints from List/Dict to list/dict for consistency * refactor: update MODEL_MAPPING_NAMES and __all__ to include LightGlue and AutoModelForKeypointMatching * fix: change type hint for size parameter in EfficientLoFTRImageProcessor to Optional[dict] * fix typing * fix some typing issues * nit * a few more typehint fixes * Remove output_attentions and output_hidden_states from modeling code * else -> elif to support efficientloftr * nit * tests: added EfficientLoFTR image processor tests * refactor: reorder functions * chore: update copyright year in EfficientLoFTR test file * Use default rope * Add docs * Update visualization method * fix doc order * remove 2d rope test * Update src/transformers/models/efficientloftr/modeling_efficientloftr.py * fix docs * Update src/transformers/models/efficientloftr/image_processing_efficientloftr.py * update gradient * refactor: removed unused codepath * Add motivation to keep postprocessing in modeling code * refactor: removed unnecessary variable declarations * docs: use load_image from image_utils * refactor: moved stage in and out channels computation to configuration * refactor: set an intermediate_size parameter to be more explicit * refactor: removed all mentions of attention masks as they are not used * refactor: moved position_embeddings to be computed once in the model instead of every layer * refactor: removed unnecessary hidden expansion parameter from config * refactor: removed completely hidden expansions * refactor: removed position embeddings slice function * tests: fixed broken tests because of previous commit * fix is_grayscale typehint * not refactoring * not renaming * move h/w to embeddings class * Precompute embeddings in init * fix: replaced cuda device in convert script to accelerate device * fix: replaced stevenbucaille repo to zju-community * Remove accelerator.device from conversion script * refactor: moved parameter computation in configuration instead of figuring it out when instantiating a Module * fix: removed unused attributes in configuration * fix: missing self * fix: refactoring and tests * fix: make style --------- Co-authored-by: steven <steven.bucaille@buawei.com> Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>
This commit is contained in:
StevenBucaille
@@ -0,0 +1,90 @@
|
||||
# Copyright 2025 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 tests.models.superglue.test_image_processing_superglue import (
|
||||
SuperGlueImageProcessingTest,
|
||||
SuperGlueImageProcessingTester,
|
||||
)
|
||||
from transformers.testing_utils import require_torch, require_vision
|
||||
from transformers.utils import is_torch_available, is_vision_available
|
||||
|
||||
|
||||
if is_torch_available():
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from transformers.models.efficientloftr.modeling_efficientloftr import KeypointMatchingOutput
|
||||
|
||||
if is_vision_available():
|
||||
from transformers import EfficientLoFTRImageProcessor
|
||||
|
||||
|
||||
def random_array(size):
|
||||
return np.random.randint(255, size=size)
|
||||
|
||||
|
||||
def random_tensor(size):
|
||||
return torch.rand(size)
|
||||
|
||||
|
||||
class EfficientLoFTRImageProcessingTester(SuperGlueImageProcessingTester):
|
||||
"""Tester for EfficientLoFTRImageProcessor"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
batch_size=6,
|
||||
num_channels=3,
|
||||
image_size=18,
|
||||
min_resolution=30,
|
||||
max_resolution=400,
|
||||
do_resize=True,
|
||||
size=None,
|
||||
do_grayscale=True,
|
||||
):
|
||||
super().__init__(
|
||||
parent, batch_size, num_channels, image_size, min_resolution, max_resolution, do_resize, size, do_grayscale
|
||||
)
|
||||
|
||||
def prepare_keypoint_matching_output(self, pixel_values):
|
||||
"""Prepare a fake output for the keypoint matching model with random matches between 50 keypoints per image."""
|
||||
max_number_keypoints = 50
|
||||
batch_size = len(pixel_values)
|
||||
keypoints = torch.zeros((batch_size, 2, max_number_keypoints, 2))
|
||||
matches = torch.full((batch_size, 2, max_number_keypoints), -1, dtype=torch.int)
|
||||
scores = torch.zeros((batch_size, 2, max_number_keypoints))
|
||||
for i in range(batch_size):
|
||||
random_number_keypoints0 = np.random.randint(10, max_number_keypoints)
|
||||
random_number_keypoints1 = np.random.randint(10, max_number_keypoints)
|
||||
random_number_matches = np.random.randint(5, min(random_number_keypoints0, random_number_keypoints1))
|
||||
keypoints[i, 0, :random_number_keypoints0] = torch.rand((random_number_keypoints0, 2))
|
||||
keypoints[i, 1, :random_number_keypoints1] = torch.rand((random_number_keypoints1, 2))
|
||||
random_matches_indices0 = torch.randperm(random_number_keypoints1, dtype=torch.int)[:random_number_matches]
|
||||
random_matches_indices1 = torch.randperm(random_number_keypoints0, dtype=torch.int)[:random_number_matches]
|
||||
matches[i, 0, random_matches_indices1] = random_matches_indices0
|
||||
matches[i, 1, random_matches_indices0] = random_matches_indices1
|
||||
scores[i, 0, random_matches_indices1] = torch.rand((random_number_matches,))
|
||||
scores[i, 1, random_matches_indices0] = torch.rand((random_number_matches,))
|
||||
return KeypointMatchingOutput(keypoints=keypoints, matches=matches, matching_scores=scores)
|
||||
|
||||
|
||||
@require_torch
|
||||
@require_vision
|
||||
class EfficientLoFTRImageProcessingTest(SuperGlueImageProcessingTest, unittest.TestCase):
|
||||
image_processing_class = EfficientLoFTRImageProcessor if is_vision_available() else None
|
||||
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
self.image_processor_tester = EfficientLoFTRImageProcessingTester(self)
|
||||
Reference in New Issue
Block a user