def getimage():
try:
data = (request.data.decode()).split(",")[1]
body = base64.decodebytes(data.encode("utf-8"))
img = Image.open(BytesIO(body))
img = np.array(img)
RGB_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# cv2.imshow("name", RGB_img)
# cv2.waitKey(0)
# cv2.destroyAllWindows()
scene_class = label_img_scene.classify(RGB_img)
# make_response = jsonify({"scene": scene_class})
# make_response.headers.add(
# "Access-Control-Allow-Origin", "http://localhost:8001/"
# )
# make_response.headers.add(
# "Access-Control-Allow-Headers", "Content-Type,Authorization"
# )
# make_response.headers.add("Access-Control-Allow-Methods", "GET,PUT,POST,DELETE")
# make_response.headers.add("Access-Control-Allow-Credentials", "true")
# print(make_response)
return scene_class
except Exception as e:
print(e)
return "error"
logger.debug('+image processing+')
logger.debug('+postprocessing+')
start_time = time.time()
humans = e.inference(image, upsample_size=4.0)
img = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
logger.debug('+classification+')
# Getting only the skeletal structure (with white background) of the actual image
image = np.zeros(image.shape, dtype=np.uint8)
image.fill(255)
image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
# Classification
pose_class = label_img.classify(image)
scene_class = label_img_scene.classify(args.image)
end_time = time.time()
logger.debug('+displaying+')
cv2.putText(img, "Predicted Pose: %s" % (pose_class), (10, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
cv2.putText(img, "Predicted Scene: %s" % (scene_class), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
print('\n Overall Evaluation time (1-image): {:.3f}s\n'.format(end_time -
start_time))
cv2.imwrite('show1.png', img)
cv2.imshow('tf-human-action-classification result', img)
cv2.waitKey(0)
logger.debug('+finished+')
cv2.destroyAllWindows()
# =============================================================================
logger.debug('+image processing+')
logger.debug('+postprocessing+')
start_time = time.time()
humans = e.inference(image, upsample_size=4.0)
img = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
logger.debug('+classification+')
# Getting only the skeletal structure (with white background) of the actual image
image = np.zeros(image.shape, dtype=np.uint8)
image.fill(255)
image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
# Classification
pose_class = label_img.classify(image)
scene_class = label_img_scene.classify(address + args.image)
end_time = time.time()
logger.debug('+displaying+')
cv2.putText(img, "Predicted Pose: %s" % (pose_class), (10, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
cv2.putText(img, "Predicted Scene: %s" % (scene_class), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
print('\n Overall Evaluation time (1-image): {:.3f}s\n'.format(end_time -
start_time))
cv2.imwrite('show1.png', img)
cv2.imshow('tf-human-action-classification result', img)
cv2.waitKey(0)
logger.debug('+finished+')
cv2.destroyAllWindows()
# =============================================================================
logger.debug("+image processing+")
logger.debug("+postprocessing+")
start_time = time.time()
humans = e.inference(image, upsample_size=4.0)
img = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
logger.debug("+classification+")
# Getting only the skeletal structure (with white background) of the actual image
image = np.zeros(image.shape, dtype=np.uint8)
image.fill(255)
image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
# Classification
pose_class = label_img.classify(image)
scene_class = label_img_scene.classify(address + file)
end_time = time.time()
img_count += 1
total_time = total_time + (end_time - start_time)
logger.debug("+Completed image: {}+".format(img_count))
true_label_pose.append(pose_class)
true_label_scene.append(scene_class)
img_name.append(file)
outF = open("pose.txt", "w")
for line in true_label_pose:
outF.write(line)
outF.write("\n")
outF.close()
outF = open("scene.txt", "w")