Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/MID_ASSY[[:space:]]SAMPLE[[:space:]]COLOR.jpeg filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.9
+
+WORKDIR /content
+
+RUN mkdir /content/cache/
+
+RUN export TRANSFORMERS_CACHE=/content/cache/
+
+COPY ./requirements.txt /content/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /content/requirements.txt
+RUN apt-get update
+RUN apt-get install -y ffmpeg
+
+COPY . .
+
+RUN adduser --disabled-password --gecos '' admin
+RUN adduser admin sudo
+RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+
+RUN chown -R admin:admin /content
+RUN chmod -R 777 /content
+USER admin
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

logs/2024-06-14.log

@@ -0,0 +1,62 @@
+2024-06-14 20:09:20,239 - uvicorn.access - INFO - 127.0.0.1:57016 - "GET / HTTP/1.1" 200
+2024-06-14 20:09:20,379 - uvicorn.access - INFO - 127.0.0.1:57016 - "GET /favicon.ico HTTP/1.1" 404
+2024-06-14 20:09:25,816 - uvicorn.access - INFO - 127.0.0.1:57024 - "GET /docs HTTP/1.1" 200
+2024-06-14 20:09:26,030 - uvicorn.access - INFO - 127.0.0.1:57024 - "GET /openapi.json HTTP/1.1" 200
+2024-06-14 20:09:32,525 - root - INFO - Received process-image request for file: 35f8f42f-450d-4045-93f2-2eac807a4785.jpg
+2024-06-14 20:09:34,328 - ultralytics - INFO - Loading models\best-data-v5.onnx for ONNX Runtime inference...
+2024-06-14 20:09:34,712 - ultralytics - INFO - 
+2024-06-14 20:09:35,824 - ultralytics - INFO - 0: 640x640 19 Bolts, 22 Metal-Mounts, 229.2ms
+2024-06-14 20:09:35,824 - ultralytics - INFO - Speed: 14.2ms preprocess, 229.2ms inference, 21.1ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:35,824 - ultralytics - INFO - 
+2024-06-14 20:09:36,060 - ultralytics - INFO - 0: 640x640 5 Bolts, 1 Metal-Mount, 222.5ms
+2024-06-14 20:09:36,060 - ultralytics - INFO - Speed: 6.9ms preprocess, 222.5ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:36,089 - ultralytics - INFO - 
+2024-06-14 20:09:36,290 - ultralytics - INFO - 0: 640x640 4 Bolts, 2 Velcros, 201.5ms
+2024-06-14 20:09:36,290 - ultralytics - INFO - Speed: 0.0ms preprocess, 201.5ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:36,298 - ultralytics - INFO - 
+2024-06-14 20:09:36,541 - ultralytics - INFO - 0: 640x640 1 Bolt, 3 Metal-Mounts, 1 Velcro, 243.1ms
+2024-06-14 20:09:36,541 - ultralytics - INFO - Speed: 0.0ms preprocess, 243.1ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:36,541 - ultralytics - INFO - 
+2024-06-14 20:09:36,742 - ultralytics - INFO - 0: 640x640 (no detections), 194.8ms
+2024-06-14 20:09:36,742 - ultralytics - INFO - Speed: 0.0ms preprocess, 194.8ms inference, 6.5ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:36,742 - ultralytics - INFO - 
+2024-06-14 20:09:36,978 - ultralytics - INFO - 0: 640x640 7 Bolts, 3 Metal-Mounts, 229.2ms
+2024-06-14 20:09:36,978 - ultralytics - INFO - Speed: 0.0ms preprocess, 229.2ms inference, 6.5ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:36,979 - ultralytics - INFO - 
+2024-06-14 20:09:37,187 - ultralytics - INFO - 0: 640x640 10 Bolts, 2 Metal-Mounts, 3 Velcros, 207.7ms
+2024-06-14 20:09:37,187 - ultralytics - INFO - Speed: 0.0ms preprocess, 207.7ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:37,187 - ultralytics - INFO - 
+2024-06-14 20:09:37,389 - ultralytics - INFO - 0: 640x640 2 Bolts, 4 Metal-Mounts, 2 Velcros, 194.7ms
+2024-06-14 20:09:37,389 - ultralytics - INFO - Speed: 7.1ms preprocess, 194.7ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:37,396 - ultralytics - INFO - 
+2024-06-14 20:09:37,577 - ultralytics - INFO - 0: 640x640 (no detections), 180.8ms
+2024-06-14 20:09:37,577 - ultralytics - INFO - Speed: 0.0ms preprocess, 180.8ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:37,583 - ultralytics - INFO - 
+2024-06-14 20:09:37,785 - ultralytics - INFO - 0: 640x640 5 Bolts, 6 Metal-Mounts, 201.9ms
+2024-06-14 20:09:37,785 - ultralytics - INFO - Speed: 0.0ms preprocess, 201.9ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:37,785 - ultralytics - INFO - 
+2024-06-14 20:09:37,973 - ultralytics - INFO - 0: 640x640 6 Bolts, 9 Metal-Mounts, 180.9ms
+2024-06-14 20:09:37,973 - ultralytics - INFO - Speed: 0.7ms preprocess, 180.9ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:37,973 - ultralytics - INFO - 
+2024-06-14 20:09:38,147 - ultralytics - INFO - 0: 640x640 2 Bolts, 3 Metal-Mounts, 167.1ms
+2024-06-14 20:09:38,147 - ultralytics - INFO - Speed: 6.6ms preprocess, 167.1ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:38,153 - ultralytics - INFO - 
+2024-06-14 20:09:38,328 - ultralytics - INFO - 0: 640x640 (no detections), 173.2ms
+2024-06-14 20:09:38,328 - ultralytics - INFO - Speed: 0.7ms preprocess, 173.2ms inference, 0.5ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:38,328 - ultralytics - INFO - 
+2024-06-14 20:09:38,522 - ultralytics - INFO - 0: 640x640 1 Bolt, 1 Velcro, 188.2ms
+2024-06-14 20:09:38,522 - ultralytics - INFO - Speed: 6.2ms preprocess, 188.2ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:38,522 - ultralytics - INFO - 
+2024-06-14 20:09:38,731 - ultralytics - INFO - 0: 640x640 4 Metal-Mounts, 1 Velcro, 201.7ms
+2024-06-14 20:09:38,731 - ultralytics - INFO - Speed: 6.9ms preprocess, 201.7ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:38,731 - ultralytics - INFO - 
+2024-06-14 20:09:38,912 - ultralytics - INFO - 0: 640x640 1 Velcro, 173.7ms
+2024-06-14 20:09:38,912 - ultralytics - INFO - Speed: 7.1ms preprocess, 173.7ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:38,918 - ultralytics - INFO - 
+2024-06-14 20:09:39,128 - ultralytics - INFO - 0: 640x640 (no detections), 208.8ms
+2024-06-14 20:09:39,128 - ultralytics - INFO - Speed: 0.3ms preprocess, 208.8ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 640)
+2024-06-14 20:09:39,134 - root - INFO - Completed slicing and detection
+2024-06-14 20:09:39,134 - root - INFO - Summary info: 23 Metal-Mount, 31 Bolt, 8 Velcro
+2024-06-14 20:09:39,134 - root - INFO - Run time: 6.61 seconds
+2024-06-14 20:09:39,134 - root - INFO - Returning JSON results
+2024-06-14 20:09:39,134 - uvicorn.access - INFO - 127.0.0.1:57052 - "POST /process-image/?draw_boxes=false HTTP/1.1" 200

main.py

@@ -0,0 +1,173 @@
+import supervision as sv
+from ultralytics import YOLO
+import cv2
+import numpy as np
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse, Response
+import uvicorn
+import logging
+from datetime import datetime
+import os
+import time
+from collections import defaultdict
+
+# Ensure the logs directory exists
+if not os.path.exists("logs"):
+    os.makedirs("logs")
+
+app = FastAPI()
+
+# Load the exported ONNX model
+onnx_model = YOLO("models/best-data-v5.onnx", task="detect")
+
+# Define the logging configuration
+LOGGING_CONFIG = {
+    "version": 1,
+    "disable_existing_loggers": False,
+    "formatters": {
+        "default": {
+            "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+        },
+        "access": {
+            "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+        },
+    },
+    "handlers": {
+        "default": {
+            "formatter": "default",
+            "class": "logging.StreamHandler",
+            "stream": "ext://sys.stdout",
+        },
+        "file": {
+            "formatter": "default",
+            "class": "logging.FileHandler",
+            "filename": f"logs/{datetime.now().strftime('%Y-%m-%d')}.log",
+            "mode": "a",
+        },
+        "access": {
+            "formatter": "access",
+            "class": "logging.StreamHandler",
+            "stream": "ext://sys.stdout",
+        },
+    },
+    "loggers": {
+        "": {
+            "handlers": ["default", "file"],
+            "level": "INFO",
+        },
+        "uvicorn.access": {
+            "handlers": ["access", "file"],
+            "level": "INFO",
+            "propagate": False,
+        },
+        "ultralytics": {
+            "handlers": ["default", "file"],
+            "level": "INFO",
+            "propagate": False,
+        },
+    }
+}
+
+# Apply the logging configuration
+logging.config.dictConfig(LOGGING_CONFIG)
+
+
+def parse_detection(detections):
+    parsed_rows = []
+    for i in range(len(detections.xyxy)):
+        x_min = float(detections.xyxy[i][0])
+        y_min = float(detections.xyxy[i][1])
+        x_max = float(detections.xyxy[i][2])
+        y_max = float(detections.xyxy[i][3])
+
+        width = int(x_max - x_min)
+        height = int(y_max - y_min)
+
+        row = {
+            "top": int(y_min),
+            "left": int(x_min),
+            "width": width,
+            "height": height,
+            "class_id": ""
+            if detections.class_id is None
+            else int(detections.class_id[i]),
+            "confidence": ""
+            if detections.confidence is None
+            else float(detections.confidence[i]),
+            "tracker_id": ""
+            if detections.tracker_id is None
+            else int(detections.tracker_id[i]),
+        }
+
+        if hasattr(detections, "data"):
+            for key, value in detections.data.items():
+                row[key] = (
+                    str(value[i])
+                    if hasattr(value, "__getitem__") and value.ndim != 0
+                    else str(value)
+                )
+        parsed_rows.append(row)
+    return parsed_rows
+
+
+# Run inference
+def callback(image_slice: np.ndarray) -> sv.Detections:
+    # logging.info("Running callback for image slice")
+    results = onnx_model(image_slice)[0]
+    return sv.Detections.from_ultralytics(results)
+
+
+def infer(image):
+    start_time = time.time()
+    image_arr = np.frombuffer(image, np.uint8)
+    image = cv2.imdecode(image_arr, cv2.IMREAD_COLOR)
+    image = cv2.resize(image, (1920, 1920))
+    results = onnx_model(image)[0]
+    # detections = sv.Detections.from_ultralytics(results)
+
+    slicer = sv.InferenceSlicer(callback=callback, slice_wh=(640, 640))
+    detections = slicer(image=image)
+    logging.info("Completed slicing and detection")
+
+    parsed_rows = parse_detection(detections)
+    # Count the occurrences of each class
+    class_counts = defaultdict(int)
+    for detection in parsed_rows:
+        class_name = detection.get("class_name", "Unknown")
+        class_counts[class_name] += 1
+    summary_info = ", ".join(
+        [f"{count} {class_name}" for class_name, count in class_counts.items()]
+    )
+    logging.info(f"Summary info: {summary_info}")
+    logging.info(f"Run time: {time.time() - start_time:.2f} seconds")
+    # label_annotator = sv.LabelAnnotator(text_color=sv.Color.BLACK)
+    bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=4)
+
+    annotated_image = image.copy()
+    annotated_image = bounding_box_annotator.annotate(scene=annotated_image, detections=detections)
+    # annotated_image = label_annotator.annotate(scene=annotated_image, detections=detections)
+    # logging.info("Annotated image")
+    return annotated_image, parsed_rows
+
+
+@app.post("/process-image/")
+async def process_image(image: UploadFile = File(...), draw_boxes: bool = False):
+    filename = image.filename
+    logging.info(f"Received process-image request for file: {filename}")
+    image_data = await image.read()
+    annotated_image, results = infer(image_data)
+    if draw_boxes:
+        _, img_encoded = cv2.imencode('.jpg', annotated_image)
+        logging.info("Returning annotated image")
+        return Response(content=img_encoded.tobytes(), media_type="image/jpeg")
+    logging.info("Returning JSON results")
+    return JSONResponse(content=results)
+
+
+@app.get("/")
+def hello_world():
+    return 'Hello, World!'
+
+
+if __name__ == "__main__":
+    uvicorn.run("main:app", port=8001, reload=True)

models/best-data-v4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48e20c75d7c3b103a4843b0dc2be529ab4b66f25a2279f61a936ec0b360e6a4
+size 101965198

models/best-data-v4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73597941364c27868db2ffe233cb7b50ad78c953e47398333c3641cb429a6c5
+size 204643878

models/best-data-v5.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add3500eaa4f5289ed6c5c94206c6b51d3f9b3444294c63d611e4d28279723a6
+size 101965198

models/best-data-v5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ec334351280472b9d820ea888b2b6cf18dbee6912d25f1b7aa8eab09bd201e
+size 204643878

requirements.txt

@@ -0,0 +1,15 @@
+fastapi
+uvicorn
+flup
+a2wsgi
+python-multipart
+numpy
+imutils
+opencv-python
+pytesseract
+scikit-learn
+roboflow
+inference
+supervision
+ultralytics
+onnx