Add files

.gitattributes

@@ -1,3 +1,4 @@
+*jpg filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,163 @@
+gradio_cached_examples/
+yolo*.pt
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.991
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']

.style.yapf

@@ -0,0 +1,5 @@
+[style]
+based_on_style = pep8
+blank_line_before_nested_class_or_def = false
+spaces_before_comment = 2
+split_before_logical_operator = true

README.md

@@ -4,7 +4,7 @@ emoji: 💻
 colorFrom: indigo
 colorTo: purple
 sdk: gradio
-sdk_version: 3.17.0
+sdk_version: 3.18.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -0,0 +1,122 @@
+#!/usr/bin/env python
+
+import pathlib
+
+import gradio as gr
+import numpy as np
+import PIL.Image
+import torch
+from sahi.prediction import ObjectPrediction
+from sahi.utils.cv import visualize_object_predictions
+from transformers import AutoImageProcessor, DetaForObjectDetection
+from ultralytics import YOLO
+
+DESCRIPTION = '# Compare DETA and YOLOv8'
+
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+
+MODEL_ID = 'jozhang97/deta-swin-large'
+image_processor = AutoImageProcessor.from_pretrained(MODEL_ID)
+model_deta = DetaForObjectDetection.from_pretrained(MODEL_ID)
+model_deta.to(device)
+
+model_yolo = YOLO('yolov8x.pt')
+
+
+@torch.inference_mode()
+def run_deta(image_path: str, threshold: float) -> np.ndarray:
+    image = PIL.Image.open(image_path)
+    inputs = image_processor(images=image, return_tensors='pt').to(device)
+    outputs = model_deta(**inputs)
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = image_processor.post_process_object_detection(
+        outputs, threshold=threshold, target_sizes=target_sizes)[0]
+
+    boxes = results['boxes'].cpu().numpy()
+    scores = results['scores'].cpu().numpy()
+    cat_ids = results['labels'].cpu().numpy().tolist()
+    preds = []
+    for box, score, cat_id in zip(boxes, scores, cat_ids):
+        box = np.round(box).astype(int)
+        cat_label = model_deta.config.id2label[cat_id]
+        pred = ObjectPrediction(bbox=box,
+                                category_id=cat_id,
+                                category_name=cat_label,
+                                score=score)
+        preds.append(pred)
+    res = visualize_object_predictions(np.asarray(image), preds)['image']
+    return res
+
+
+def run_yolov8(image_path: str, threshold: float) -> np.ndarray:
+    image = PIL.Image.open(image_path)
+    results = model_yolo(image, imgsz=640, conf=threshold)
+    boxes = results[0].boxes.cpu().numpy().data
+    preds = []
+    for box in boxes:
+        score = box[4]
+        cat_id = int(box[5])
+        box = np.round(box[:4]).astype(int)
+        cat_label = model_yolo.model.names[cat_id]
+        pred = ObjectPrediction(bbox=box,
+                                category_id=cat_id,
+                                category_name=cat_label,
+                                score=score)
+        preds.append(pred)
+    res = visualize_object_predictions(np.asarray(image), preds)['image']
+    return res
+
+
+def run(image_path: str, threshold_deta: float,
+        threshold_yolo: float) -> tuple[np.ndarray, np.ndarray]:
+    return run_deta(image_path,
+                    threshold_deta), run_yolov8(image_path, threshold_yolo)
+
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        with gr.Column():
+            image = gr.Image(label='Input image', type='filepath')
+            threshold_deta = gr.Slider(label='Score threshold for DETA',
+                                       minimum=0,
+                                       maximum=1,
+                                       value=0.1,
+                                       step=0.01)
+            threshold_yolo = gr.Slider(label='Score threshold for YOLOv8',
+                                       minimum=0,
+                                       maximum=1,
+                                       value=0.5,
+                                       step=0.01)
+            run_button = gr.Button('Run')
+        with gr.Column():
+            result_deta = gr.Image(label='Result (DETA)', type='numpy')
+            result_yolo = gr.Image(label='Result (YOLOv8)', type='numpy')
+
+    with gr.Row():
+        paths = sorted(pathlib.Path('images').glob('*.jpg'))
+        gr.Examples(examples=[[path.as_posix(), 0.1, 0.5] for path in paths],
+                    inputs=[
+                        image,
+                        threshold_deta,
+                        threshold_yolo,
+                    ],
+                    outputs=[
+                        result_deta,
+                        result_yolo,
+                    ],
+                    fn=run,
+                    cache_examples=True)
+
+    run_button.click(fn=run,
+                     inputs=[
+                         image,
+                         threshold_deta,
+                         threshold_yolo,
+                     ],
+                     outputs=[
+                         result_deta,
+                         result_yolo,
+                     ])
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,7 @@
+git+https://github.com/huggingface/transformers@59d5ede
+numpy==1.24.1
+Pillow==9.4.0
+sahi==0.11.11
+torch==1.13.1
+torchvision==0.14.1
+ultralytics==8.0.28

style.css

@@ -0,0 +1,3 @@
+h1 {
+  text-align: center;
+}