Added separate file to see how code works without Gradio

.gitignore

@@ -0,0 +1,236 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,linux,visualstudiocode,windows
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,linux,visualstudiocode,windows
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/python,linux,visualstudiocode,windows

image_functions.py

@@ -0,0 +1,171 @@
+import io
+import matplotlib.pyplot as plt
+import requests, validators
+import torch
+import pathlib
+from PIL import Image
+from transformers import AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection
+from ultralyticsplus import YOLO, render_result
+
+import os
+
+# colors for visualization
+COLORS = [
+    [0.000, 0.447, 0.741],
+    [0.850, 0.325, 0.098],
+    [0.929, 0.694, 0.125],
+    [0.494, 0.184, 0.556],
+    [0.466, 0.674, 0.188],
+    [0.301, 0.745, 0.933]
+]
+
+YOLOV8_LABELS = ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor']
+
+def make_prediction(img, feature_extractor, model):
+    inputs = feature_extractor(img, return_tensors="pt")
+    outputs = model(**inputs)
+    img_size = torch.tensor([tuple(reversed(img.size))])
+    processed_outputs = feature_extractor.post_process(outputs, img_size)
+    return processed_outputs
+
+def fig2img(fig):
+    buf = io.BytesIO()
+    fig.savefig(buf)
+    buf.seek(0)
+    img = Image.open(buf)
+    return img
+
+
+def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
+    keep = output_dict["scores"] > threshold
+    boxes = output_dict["boxes"][keep].tolist()
+    scores = output_dict["scores"][keep].tolist()
+    labels = output_dict["labels"][keep].tolist()
+    if id2label is not None:
+        labels = [id2label[x] for x in labels]
+
+    # print("Labels " + str(labels))
+
+    plt.figure(figsize=(16, 10))
+    plt.imshow(pil_img)
+    ax = plt.gca()
+    colors = COLORS * 100
+    for score, (xmin, ymin, xmax, ymax), label, color in zip(scores, boxes, labels, colors):
+        ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3))
+        ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
+    plt.axis("off")
+    return fig2img(plt.gcf())
+
+def detect_objects(model_name,url_input,image_input,threshold):
+    
+
+    if 'yolov8' in model_name:
+        # Working on getting this to work, another approach
+        # https://docs.ultralytics.com/modes/predict/#key-features-of-predict-mode 
+
+        model = YOLO(model_name)
+        # set model parameters
+        model.overrides['conf'] = 0.15  # NMS confidence threshold
+        model.overrides['iou'] = 0.05  # NMS IoU threshold             https://www.google.com/search?client=firefox-b-1-d&q=intersection+over+union+meaning
+        model.overrides['agnostic_nms'] = False  # NMS class-agnostic
+        model.overrides['max_det'] = 1000  # maximum number of detections per image
+
+        results = model.predict(image_input)
+
+        render = render_result(model=model, image=image_input, result=results[0])
+
+        final_str = ""
+        final_str_abv = ""
+        final_str_else = ""
+
+        for result in results:
+            boxes = result.boxes.cpu().numpy()
+            for i, box in enumerate(boxes):
+                # r = box.xyxy[0].astype(int)
+                coordinates = box.xyxy[0].astype(int)
+                try:
+                    label = YOLOV8_LABELS[int(box.cls)]
+                except:
+                    label = "ERROR"
+                try:
+                    confi = float(box.conf)
+                except:
+                    confi = 0.0
+                # final_str_abv += str() + "__" + str(box.cls) + "__" + str(box.conf) + "__" + str(box) + "\n"
+                if confi >= threshold:
+                    final_str_abv += f"Detected `{label}` with confidence `{confi}` at location `{coordinates}`\n"
+                else:
+                    final_str_else += f"Detected `{label}` with confidence `{confi}` at location `{coordinates}`\n"
+
+        final_str = "{:*^50}\n".format("ABOVE THRESHOLD OR EQUAL") + final_str_abv + "\n{:*^50}\n".format("BELOW THRESHOLD")+final_str_else
+
+        return render, final_str
+    else:
+        
+        #Extract model and feature extractor
+        feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+        if 'detr' in model_name:
+        
+            model = DetrForObjectDetection.from_pretrained(model_name)
+
+        elif 'yolos' in model_name:
+        
+            model = YolosForObjectDetection.from_pretrained(model_name)
+    
+        tb_label = ""
+        if validators.url(url_input):
+            image = Image.open(requests.get(url_input, stream=True).raw)
+            tb_label = "Confidence Values URL"
+            
+        elif image_input:
+            image = image_input
+            tb_label = "Confidence Values Upload"
+        
+        #Make prediction
+        processed_output_list = make_prediction(image, feature_extractor, model)
+        # print("After make_prediction" + str(processed_output_list))
+        processed_outputs = processed_output_list[0]
+        
+        #Visualize prediction
+        viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label)
+        
+        # return [viz_img, processed_outputs]
+        # print(type(viz_img))
+    
+        final_str_abv = ""
+        final_str_else = ""
+        for score, label, box in sorted(zip(processed_outputs["scores"], processed_outputs["labels"], processed_outputs["boxes"]), key = lambda x: x[0].item(), reverse=True):
+            box = [round(i, 2) for i in box.tolist()]
+            if score.item() >= threshold:
+                final_str_abv += f"Detected `{model.config.id2label[label.item()]}` with confidence `{round(score.item(), 3)}` at location `{box}`\n"
+            else:
+                final_str_else += f"Detected `{model.config.id2label[label.item()]}` with confidence `{round(score.item(), 3)}` at location `{box}`\n"
+    
+        # https://docs.python.org/3/library/string.html#format-examples
+        final_str = "{:*^50}\n".format("ABOVE THRESHOLD OR EQUAL") + final_str_abv + "\n{:*^50}\n".format("BELOW THRESHOLD")+final_str_else
+            
+        return viz_img, final_str
+
+
+title = """<h1 id="title">Object Detection App with DETR and YOLOS</h1>"""
+
+description = """
+Links to HuggingFace Models:
+
+- [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50)  
+- [facebook/detr-resnet-101](https://huggingface.co/facebook/detr-resnet-101)  
+- [hustvl/yolos-small](https://huggingface.co/hustvl/yolos-small)
+- [hustvl/yolos-tiny](https://huggingface.co/hustvl/yolos-tiny)
+- [facebook/detr-resnet-101-dc5](https://huggingface.co/facebook/detr-resnet-101-dc5)
+- [hustvl/yolos-small-300](https://huggingface.co/hustvl/yolos-small-300)
+- [mshamrai/yolov8x-visdrone](https://huggingface.co/mshamrai/yolov8x-visdrone)
+
+"""
+
+models = ["facebook/detr-resnet-50","facebook/detr-resnet-101",'hustvl/yolos-small','hustvl/yolos-tiny','facebook/detr-resnet-101-dc5', 'hustvl/yolos-small-300', 'mshamrai/yolov8x-visdrone']
+urls = ["https://c8.alamy.com/comp/J2AB4K/the-new-york-stock-exchange-on-the-wall-street-in-new-york-J2AB4K.jpg"]
+
+
+TEST_IMAGE = Image.open(r"images/Test_Street_VisDrone.JPG")
+
+# image_functions.detect_objects('facebook/detr-resnet-50', "", image_functions.TEST_IMAGE, 0.7)