def test(opt):
model = SSD(backbone=ResNet())
checkpoint = torch.load(opt.pretrained_model)
model.load_state_dict(checkpoint["model_state_dict"])
if torch.cuda.is_available():
model.cuda()
model.eval()
dboxes = generate_dboxes()
test_set = CocoDataset(opt.data_path, 2017, "val",
SSDTransformer(dboxes, (300, 300), val=True))
encoder = Encoder(dboxes)
if os.path.isdir(opt.output):
shutil.rmtree(opt.output)
os.makedirs(opt.output)
for img, img_id, img_size, _, _ in test_set:
if img is None:
continue
if torch.cuda.is_available():
img = img.cuda()
with torch.no_grad():
ploc, plabel = model(img.unsqueeze(dim=0))
result = encoder.decode_batch(ploc, plabel, opt.nms_threshold,
20)[0]
loc, label, prob = [r.cpu().numpy() for r in result]
best = np.argwhere(prob > opt.cls_threshold).squeeze(axis=1)
loc = loc[best]
label = label[best]
prob = prob[best]
if len(loc) > 0:
path = test_set.coco.loadImgs(img_id)[0]["file_name"]
output_img = cv2.imread(
os.path.join(opt.data_path, "val2017", path))
height, width, _ = output_img.shape
loc[:, 0::2] *= width
loc[:, 1::2] *= height
loc = loc.astype(np.int32)
for box, lb, pr in zip(loc, label, prob):
category = test_set.label_info[lb]
color = colors[lb]
xmin, ymin, xmax, ymax = box
cv2.rectangle(output_img, (xmin, ymin), (xmax, ymax),
color, 2)
text_size = cv2.getTextSize(category + " : %.2f" % pr,
cv2.FONT_HERSHEY_PLAIN, 1,
1)[0]
cv2.rectangle(
output_img, (xmin, ymin),
(xmin + text_size[0] + 3, ymin + text_size[1] + 4),
color, -1)
cv2.putText(output_img, category + " : %.2f" % pr,
(xmin, ymin + text_size[1] + 4),
cv2.FONT_HERSHEY_PLAIN, 1, (255, 255, 255), 1)
cv2.imwrite(
"{}/{}_prediction.jpg".format(opt.output, path[:-4]),
output_img)
def test(opt):
model = SSD(backbone=ResNet())
checkpoint = torch.load(opt.pretrained_model)
model.load_state_dict(checkpoint["model_state_dict"])
if torch.cuda.is_available():
model.cuda()
model.eval()
dboxes = generate_dboxes()
transformer = SSDTransformer(dboxes, (300, 300), val=True)
img = Image.open(opt.input).convert("RGB")
img, _, _, _ = transformer(img, None, torch.zeros(1,4), torch.zeros(1))
encoder = Encoder(dboxes)
if torch.cuda.is_available():
img = img.cuda()
with torch.no_grad():
ploc, plabel = model(img.unsqueeze(dim=0))
result = encoder.decode_batch(ploc, plabel, opt.nms_threshold, 20)[0]
loc, label, prob = [r.cpu().numpy() for r in result]
best = np.argwhere(prob > opt.cls_threshold).squeeze(axis=1)
loc = loc[best]
label = label[best]
prob = prob[best]
output_img = cv2.imread(opt.input)
if len(loc) > 0:
height, width, _ = output_img.shape
loc[:, 0::2] *= width
loc[:, 1::2] *= height
loc = loc.astype(np.int32)
for box, lb, pr in zip(loc, label, prob):
category = coco_classes[lb]
color = colors[lb]
xmin, ymin, xmax, ymax = box
cv2.rectangle(output_img, (xmin, ymin), (xmax, ymax), color, 2)
text_size = cv2.getTextSize(category + " : %.2f" % pr, cv2.FONT_HERSHEY_PLAIN, 1, 1)[0]
cv2.rectangle(output_img, (xmin, ymin), (xmin + text_size[0] + 3, ymin + text_size[1] + 4), color,
-1)
cv2.putText(
output_img, category + " : %.2f" % pr,
(xmin, ymin + text_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1,
(255, 255, 255), 1)
if opt.output is None:
output = "{}_prediction.jpg".format(opt.input[:-4])
else:
output = opt.output
cv2.imwrite(output, output_img)
draw.rectangle(xy=[l + 1. for l in box_location], outline=box_color)
# Text (class label)
text_size = font.getsize(box_label_name.upper())
text_location = [box_location[0] + 2., box_location[1] - text_size[1]]
textbox_location = [box_location[0], box_location[1] - text_size[1], box_location[0] + text_size[0] + 4.,box_location[1]]
draw.rectangle(xy=textbox_location, fill=box_color)
draw.text(xy=text_location, text=box_label_name.upper(), fill='white')
annotated_image.save(args.image_save_path+'p_'+args.test_image.split('/')[-1])
del draw
if __name__ == '__main__':
args = get_infer_argument()
set_cuda_dev(args.ngpu)
print('Arguments for inference : ', args)
# Load model checkpoint
model = SSD('test', args)
checkpoint = args.trained_model # '*.pth'
_, model, _ = load_checkpoint(model, args.trained_model_path+checkpoint)
model = model.cuda()
model.eval()
with torch.no_grad():
img_example = args.test_image # With absolute path (ex. /media/dataset/VOC2007/JPEGImages/000001.jpg)
original_image = Image.open(img_example, mode='r')
original_image = original_image.convert('RGB')
detect_image(original_image, args)
print('Detect image finished!')
def test(opt):
model = SSD(backbone=ResNet())
checkpoint = torch.load(opt.pretrained_model)
model.load_state_dict(checkpoint["model_state_dict"])
if torch.cuda.is_available():
model.cuda()
model.eval()
dboxes = generate_dboxes()
transformer = SSDTransformer(dboxes, (300, 300), val=True)
cap = cv2.VideoCapture(opt.input)
if opt.output is None:
output = "{}_prediction.mp4".format(opt.input[:-4])
else:
output = opt.output
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
out = cv2.VideoWriter(output, cv2.VideoWriter_fourcc(*"MJPG"),
int(cap.get(cv2.CAP_PROP_FPS)), (width, height))
encoder = Encoder(dboxes)
while cap.isOpened():
flag, frame = cap.read()
output_frame = np.copy(frame)
if flag:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
else:
break
frame = Image.fromarray(frame)
frame, _, _, _ = transformer(frame, None, torch.zeros(1, 4),
torch.zeros(1))
if torch.cuda.is_available():
frame = frame.cuda()
with torch.no_grad():
ploc, plabel = model(frame.unsqueeze(dim=0))
result = encoder.decode_batch(ploc, plabel, opt.nms_threshold,
20)[0]
loc, label, prob = [r.cpu().numpy() for r in result]
best = np.argwhere(prob > opt.cls_threshold).squeeze(axis=1)
loc = loc[best]
label = label[best]
prob = prob[best]
if len(loc) > 0:
loc[:, 0::2] *= width
loc[:, 1::2] *= height
loc = loc.astype(np.int32)
for box, lb, pr in zip(loc, label, prob):
category = coco_classes[lb]
color = colors[lb]
xmin, ymin, xmax, ymax = box
cv2.rectangle(output_frame, (xmin, ymin), (xmax, ymax),
color, 2)
text_size = cv2.getTextSize(category + " : %.2f" % pr,
cv2.FONT_HERSHEY_PLAIN, 1,
1)[0]
cv2.rectangle(
output_frame, (xmin, ymin),
(xmin + text_size[0] + 3, ymin + text_size[1] + 4),
color, -1)
cv2.putText(output_frame, category + " : %.2f" % pr,
(xmin, ymin + text_size[1] + 4),
cv2.FONT_HERSHEY_PLAIN, 1, (255, 255, 255), 1)
out.write(output_frame)
cap.release()
out.release()