File size: 4,351 Bytes
d07f178 f247b8c c006b6f f247b8c 16182c1 f247b8c 16182c1 1b7b95f c006b6f 1b7b95f c006b6f 1b7b95f f247b8c 1b7b95f 16182c1 f247b8c be592f0 f247b8c c006b6f d07f178 f247b8c 1b7b95f f247b8c c006b6f 688c453 c006b6f 688c453 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | import os
import gradio as gr
import numpy as np
import cv2
from PIL import Image, ImageOps
from insightface.app import FaceAnalysis
from hsemotion_onnx.facial_emotions import HSEmotionRecognizer
def exif_transpose(img):
if hasattr(ImageOps, 'exif_transpose'):
# Very recent versions of PIL can do exit transpose internally
return ImageOps.exif_transpose(img)
exif_orientation_tag = 274
# Check for EXIF data (only present on some files)
if hasattr(img, "_getexif") and isinstance(img._getexif(), dict) and exif_orientation_tag in img._getexif():
exif_data = img._getexif()
orientation = exif_data[exif_orientation_tag]
# Handle EXIF Orientation
if orientation == 1:
# Normal image - nothing to do!
pass
elif orientation == 2:
# Mirrored left to right
img = img.transpose(Image.FLIP_LEFT_RIGHT)
elif orientation == 3:
# Rotated 180 degrees
img = img.rotate(180)
elif orientation == 4:
# Mirrored top to bottom
img = img.rotate(180).transpose(Image.FLIP_LEFT_RIGHT)
elif orientation == 5:
# Mirrored along top-left diagonal
img = img.rotate(-90, expand=True).transpose(Image.FLIP_LEFT_RIGHT)
elif orientation == 6:
# Rotated 90 degrees
img = img.rotate(-90, expand=True)
elif orientation == 7:
# Mirrored along top-right diagonal
img = img.rotate(90, expand=True).transpose(Image.FLIP_LEFT_RIGHT)
elif orientation == 8:
# Rotated 270 degrees
img = img.rotate(90, expand=True)
return img
def resize(image, target_size):
# Get the dimensions of the input image
width, height = image.size
# Calculate the scaling factor needed to resize the image to the target size
scaling_factor = min(target_size[0] / width, target_size[1] / height)
target_height = int(scaling_factor * height)
target_width = int(scaling_factor * width)
# Resize the image
resized_image = image.resize((target_width, target_height), resample=Image.NEAREST)
return resized_image
def facial_emotion_recognition(img):
img = np.asarray(resize(exif_transpose(img), target_size))
faces = face_detector.get(img)
if len(faces) > 0:
highest_score_box = (0, 0, 0, 0) # x, y, w, h
highest_score = 0
for face in faces:
if face['det_score'] > highest_score:
highest_score = face['det_score']
x1, y1, x2, y2 = face['bbox'].astype(int)
x_margin = int((x2 - x1) * face_margin)
y_margin = int((y2 - y1) * face_margin)
x = max(0, x1 - x_margin)
y = max(0, y1 - y_margin)
w = min(x2 + x_margin, img.shape[1]) - x
h = min(y2 + y_margin, img.shape[0]) - y
highest_score_box = (x, y, w, h)
x, y, w, h = highest_score_box
emotion, _ = hse_emo_model.predict_emotions(img[y:y+h, x:x+w], logits=True)
cv2.rectangle(img, (x, y), (x+w, y+h), (0, 0, 255), 2)
cv2.putText(img, emotion, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, cv2.LINE_AA)
return img
face_margin = 0.1
target_size = (640, 640) # w, h
model_name = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'buffalo_sc')
face_detector = FaceAnalysis(name=model_name, allowed_modules=['detection'], providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
face_detector.prepare(ctx_id=0, det_size=(640, 640))
hse_emo_model = HSEmotionRecognizer(model_name='enet_b0_8_best_vgaf')
webcam = gr.Image(type='pil', source='webcam', label='Input Image')
webcam_output = gr.Image(image_mode='RGB', type='numpy', label='Output Image')
webcam_interface = gr.Interface(facial_emotion_recognition, inputs=webcam, outputs=webcam_output)
upload = gr.Image(type='pil', source='upload', label='Input Image')
upload_output = gr.Image(image_mode='RGB', type='numpy', label='Output Image')
upload_interface = gr.Interface(facial_emotion_recognition, inputs=upload, outputs=upload_output, examples='examples')
demo = gr.TabbedInterface(interface_list=[upload_interface, webcam_interface], tab_names=['Upload', 'Webcam'])
demo.launch()
|