def run_eval(image_dir, anno_file, vis_dir, model, preprocess):
"""Run the evaluation on the test set and report mAP score
:param model: the model to test
:returns: float, the reported mAP score
"""
coco = COCO(anno_file)
cat_ids = coco.getCatIds(catNms=['person'])
img_ids = coco.getImgIds(catIds=cat_ids)
# img_ids = img_ids[81:82]
# img_paths = img_paths[81:82]
print("Total number of validation images {}".format(len(img_ids)))
# iterate all val images
outputs = []
print("Processing Images in validation set")
for i in range(len(img_ids)):
if i % 10 == 0 and i != 0:
print("Processed {} images".format(i))
img = coco.loadImgs(img_ids[i])[0]
file_name = img['file_name']
file_path = os.path.join(image_dir, file_name)
oriImg = cv2.imread(file_path)
# Get the shortest side of the image (either height or width)
shape_dst = np.min(oriImg.shape[0:2])
# Get results of original image
paf, heatmap, scale_img = get_outputs(oriImg, model, preprocess)
humans = paf_to_pose_cpp(heatmap, paf, cfg)
out = draw_humans(oriImg, humans)
vis_path = os.path.join(vis_dir, file_name)
cv2.imwrite(vis_path, out)
# subset indicated how many peoples foun in this image.
upsample_keypoints = (heatmap.shape[0]*cfg.MODEL.DOWNSAMPLE/scale_img, heatmap.shape[1]*cfg.MODEL.DOWNSAMPLE/scale_img)
append_result(img_ids[i], humans, upsample_keypoints, outputs)
# Eval and show the final result!
return eval_coco(outputs=outputs, annFile=anno_file, imgIds=img_ids)
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER)
args = parser.parse_args()
# update config file
update_config(cfg, args)
weight_name = '/home/tensorboy/Downloads/pose_model.pth'
model = get_model('vgg19')
model.load_state_dict(torch.load(weight_name))
model = torch.nn.DataParallel(model).cuda()
model.float()
model.eval()
test_image = './readme/ski.jpg'
oriImg = cv2.imread(test_image) # B,G,R order
shape_dst = np.min(oriImg.shape[0:2])
# Get results of original image
with torch.no_grad():
paf, heatmap, im_scale = get_outputs(oriImg, model, 'rtpose')
print(im_scale)
humans = paf_to_pose_cpp(heatmap, paf, cfg)
out = draw_humans(oriImg, humans)
cv2.imwrite('result.png', out)
# webcam image source
video_capture = cv2.VideoCapture(0)
imgnum=0
while True:
ret, frame = video_capture.read()
shape_dst = np.min(frame.shape[0:2])
with torch.no_grad():
paf, heatmap, im_scale = get_outputs(frame, model, 'rtpose')
humans = paf_to_pose_cpp(heatmap, paf, cfg)
out = draw_humans(frame, humans)
cv2.imshow('Video', out)
# skip the first image and write the rest of the stream
if (imgnum > 0):
cv2.imwrite('./LiveImages/image' + str(imgnum) + '.png',out)
# break loop with key press
if cv2.waitKey(1) & 0xFF == ord('q'):
break
imgnum+=1
# create the video
x,y,w,h=([int(s) for s in lines[-1].split()])
test_image = root_path+'images/'+filename+'.jpg'
oriImg = cv2.imread(test_image) # B,G,R order
shape_dst = np.min(oriImg.shape[0:2])
# Get results of image
with torch.no_grad():
paf, heatmap, im_scale = get_outputs(oriImg, model, 'rtpose')
# Get keypoints for each human
humans = paf_to_pose_cpp(heatmap, paf, cfg)
# Get keypoint coordinates for each hand
out,centers = draw_humans(oriImg, humans,x,y,w,h)
f=open("data.csv",'a+')
#TODO use some hueristic to select the hand automatically
while True:
l=[]
cv2.imshow('result.png',out)
# Press right key if obj in right hand
if cv2.waitKey(0) & 0xFF == 83:
for center,value in centers.items():
if(center==2 or center==3 or center==4):
print(''.join(re.sub(r"\(*\)*", "", str(value)))+",")
val=''.join(re.sub(r"\(*\)*", "", str(value)))+",";
l1=(val.split(','))
time.sleep(2)
type_, frame = device.get_next_frame()
if type_ is FrameType.Color: # FrameFormat.BGRX
rgb = frame.to_array().astype(np.uint8)[:,:,0:3]
# cv2.imshow('rgb', rgb[:,:,0:3])
oriImg = rgb
else:
continue
shape_dst = np.min(oriImg.shape[0:2])
with torch.no_grad():
paf, heatmap, imscale = get_outputs(
oriImg, model, 'rtpose')
humans = paf_to_pose_cpp(heatmap, paf, cfg)
out = draw_humans(oriImg, humans, imgcopy=True)
# print(type(out))
# Display the resulting frame
cv2.imshow('Video', out)
if cv2.waitKey(1) & 0xFF == ord('q'):
device.stop()
break
# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()
