def video_prediction_function(frame_array,
iou_thres_nms=0.45,
conf_thres_nms=0.001):
n_frames = len(frame_array)
preds = []
for i in range(0, n_frames, batch_size):
frames = []
for frame in frame_array[i:min(i + batch_size, n_frames)]:
from utils.datasets import letterbox
img = letterbox(frame, new_shape=(imgsz, imgsz))[0]
img = np.array([img, img, img])
img = np.ascontiguousarray(img)
frames.append(img)
frames = np.array(frames)
# Convert img to torch
img = torch.from_numpy(frames).to(device)
img = (img.half() if device.type != "cpu" else img.float()
) # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
pred = model(img, augment=False)[0]
# Apply NMS
pred = non_max_suppression(pred,
iou_thres=iou_thres_nms,
conf_thres=conf_thres_nms)
_ = []
for j, det in enumerate(pred):
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
frame_array[i + j].shape)
det = det.cpu().numpy()
det[:, :4] = xyxy2xywhn(
det[:, :4],
w=frame_array[i + j].shape[1],
h=frame_array[i + j].shape[0],
)
_.append(det)
preds += _
return preds
def __getitem__(self, index):
index = self.indices[index] # linear, shuffled, or image_weights
hyp = self.hyp
mosaic = self.mosaic and random.random() < hyp['mosaic']
if mosaic:
# Load mosaic
img, labels = load_mosaic(self, index)
shapes = None
# MixUp augmentation
if random.random() < hyp['mixup']:
img, labels = mixup(
img, labels,
*load_mosaic(self, random.randint(0, self.n - 1)))
else:
# Load image
img, (h0, w0), (h, w) = load_image(self, index)
# Letterbox
shape = self.batch_shapes[self.batch[
index]] if self.rect else self.img_size # final letterboxed shape
img, ratio, pad = letterbox(img,
shape,
auto=False,
scaleup=self.augment)
shapes = (h0, w0), (
(h / h0, w / w0), pad) # for COCO mAP rescaling
labels = self.labels[index].copy()
if labels.size: # normalized xywh to pixel xyxy format
labels[:, 1:] = xywhn2xyxy(labels[:, 1:],
ratio[0] * w,
ratio[1] * h,
padw=pad[0],
padh=pad[1])
if self.augment:
img, labels = random_perspective(
img,
labels,
degrees=hyp['degrees'],
translate=hyp['translate'],
scale=hyp['scale'],
shear=hyp['shear'],
perspective=hyp['perspective'])
nl = len(labels) # number of labels
if nl:
labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5],
w=img.shape[1],
h=img.shape[0],
clip=True,
eps=1E-3)
if self.augment:
# Albumentations
img, labels = self.albumentations(img, labels)
# HSV color-space
augment_hsv(img,
hgain=hyp['hsv_h'],
sgain=hyp['hsv_s'],
vgain=hyp['hsv_v'])
# Flip up-down
if random.random() < hyp['flipud']:
img = np.flipud(img)
if nl:
labels[:, 2] = 1 - labels[:, 2]
# Flip left-right
if random.random() < hyp['fliplr']:
img = np.fliplr(img)
if nl:
labels[:, 1] = 1 - labels[:, 1]
# Cutouts
# if random.random() < 0.9:
# labels = cutout(img, labels)
labels_out = torch.zeros((nl, 6))
if nl:
labels_out[:, 1:] = torch.from_numpy(labels)
# Convert
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
def __getitem__(self, index):
index = self.indices[index] # linear, shuffled, or image_weights
hyp = self.hyp
mosaic = self.mosaic and random.random() < hyp['mosaic']
if mosaic:
# Load mosaic
img, labels = load_mosaic(self, index)
shapes = None
# MixUp https://arxiv.org/pdf/1710.09412.pdf
if random.random() < hyp['mixup']:
img2, labels2 = load_mosaic(self, random.randint(0, self.n - 1))
r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
img = (img * r + img2 * (1 - r)).astype(np.uint8)
labels = np.concatenate((labels, labels2), 0)
else:
# Load image
img, (h0, w0), (h, w) = load_image(self, index)
# Letterbox
shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
labels = self.labels[index].copy()
if labels.size: # normalized xywh to pixel xyxy format
labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
if self.augment:
# Augment imagespace
if not mosaic:
img, labels = random_perspective(img, labels,
degrees=hyp['degrees'],
translate=hyp['translate'],
scale=hyp['scale'],
shear=hyp['shear'],
perspective=hyp['perspective'])
# Augment colorspace
augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
# Apply cutouts
# if random.random() < 0.9:
# labels = cutout(img, labels)
nL = len(labels) # number of labels
if nL:
labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0]) # xyxy to xywh normalized
if self.augment:
# flip up-down
if random.random() < hyp['flipud']:
img = np.flipud(img)
if nL:
labels[:, 2] = 1 - labels[:, 2]
# flip left-right
if random.random() < hyp['fliplr']:
img = np.fliplr(img)
if nL:
labels[:, 1] = 1 - labels[:, 1]
labels_out = torch.zeros((nL, 6))
if nL:
labels_out[:, 1:] = torch.from_numpy(labels)
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3 x img_height x img_width
img = np.ascontiguousarray(img)
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
