Create app.py

app.py

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: MIT
+
+import cv2
+import onnxruntime as ort
+import argparse
+import numpy as np
+from dependencies.box_utils import predict
+
+# ------------------------------------------------------------------------------------------------------------------------------------------------
+# Face detection using UltraFace-320 onnx model
+os.system("wget https://github.com/AK391/models/raw/main/vision/body_analysis/ultraface/models/version-RFB-320.onnx")
+face_detector_onnx = "version-RFB-320.onnx"
+
+# Start from ORT 1.10, ORT requires explicitly setting the providers parameter if you want to use execution providers
+# other than the default CPU provider (as opposed to the previous behavior of providers getting set/registered by default
+# based on the build flags) when instantiating InferenceSession.
+# For example, if NVIDIA GPU is available and ORT Python package is built with CUDA, then call API as following:
+# ort.InferenceSession(path/to/model, providers=['CUDAExecutionProvider'])
+face_detector = ort.InferenceSession(face_detector_onnx)
+
+# scale current rectangle to box
+def scale(box):
+    width = box[2] - box[0]
+    height = box[3] - box[1]
+    maximum = max(width, height)
+    dx = int((maximum - width)/2)
+    dy = int((maximum - height)/2)
+
+    bboxes = [box[0] - dx, box[1] - dy, box[2] + dx, box[3] + dy]
+    return bboxes
+
+# crop image
+def cropImage(image, box):
+    num = image[box[1]:box[3], box[0]:box[2]]
+    return num
+
+# face detection method
+def faceDetector(orig_image, threshold = 0.7):
+    image = cv2.cvtColor(orig_image, cv2.COLOR_BGR2RGB)
+    image = cv2.resize(image, (320, 240))
+    image_mean = np.array([127, 127, 127])
+    image = (image - image_mean) / 128
+    image = np.transpose(image, [2, 0, 1])
+    image = np.expand_dims(image, axis=0)
+    image = image.astype(np.float32)
+
+    input_name = face_detector.get_inputs()[0].name
+    confidences, boxes = face_detector.run(None, {input_name: image})
+    boxes, labels, probs = predict(orig_image.shape[1], orig_image.shape[0], confidences, boxes, threshold)
+    return boxes, labels, probs
+
+# ------------------------------------------------------------------------------------------------------------------------------------------------
+# Main void
+
+def inference(img):
+  color = (255, 128, 0)
+  
+  orig_image = cv2.imread(img)
+  boxes, labels, probs = faceDetector(orig_image)
+  
+  for i in range(boxes.shape[0]):
+      box = scale(boxes[i, :])
+      cv2.rectangle(orig_image, (box[0], box[1]), (box[2], box[3]), color, 4)
+      cv2.imwrite("out.png",orig_image)
+  return "out.png"
+  
+
+gr.Interface(inference,gr.inputs.Image(type="filepath"),gr.outputs.Image(type="file")).launch()
+