def forward(self, imgs, size=640, augment=False, profile=False):
# Inference from various sources. For height=720, width=1280, RGB images example inputs are:
# filename: imgs = 'data/samples/zidane.jpg'
# URI: = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(720,1280,3)
# PIL: = Image.open('image.jpg') # HWC x(720,1280,3)
# numpy: = np.zeros((720,1280,3)) # HWC
# torch: = torch.zeros(16,3,720,1280) # BCHW
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
p = next(self.model.parameters()) # for device and type
if isinstance(imgs, torch.Tensor): # torch
return self.model(imgs.to(p.device).type_as(p), augment,
profile) # inference
# Pre-process
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (
1, [imgs]) # number of images, list of images
shape0, shape1 = [], [] # image and inference shapes
for i, im in enumerate(imgs):
if isinstance(im, str): # filename or uri
im = Image.open(
requests.get(im, stream=True).raw
if im.startswith('http') else im) # open
im = np.array(im) # to numpy
if im.shape[0] < 5: # image in CHW
im = im.transpose(
(1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
im = im[:, :, :3] if im.ndim == 3 else np.tile(
im[:, :, None], 3) # enforce 3ch input
s = im.shape[:2] # HWC
shape0.append(s) # image shape
g = (size / max(s)) # gain
shape1.append([y * g for y in s])
imgs[i] = im # update
shape1 = [
make_divisible(x, int(self.stride.max()))
for x in np.stack(shape1, 0).max(0)
] # inference shape
x = [letterbox(im, new_shape=shape1, auto=False)[0]
for im in imgs] # pad
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
x = torch.from_numpy(x).to(
p.device).type_as(p) / 255. # uint8 to fp16/32
# Inference
with torch.no_grad():
y = self.model(x, augment, profile)[0] # forward
y = non_max_suppression(y,
conf_thres=self.conf,
iou_thres=self.iou,
classes=self.classes) # NMS
# Post-process
for i in range(n):
scale_coords(shape1, y[i][:, :4], shape0[i])
return Detections(imgs, y, self.names)
def forward(self, imgs, size=640, augment=False, profile=False):
# supports inference from various sources. For height=720, width=1280, RGB images example inputs are:
# opencv: x = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(720,1280,3)
# PIL: x = Image.open('image.jpg') # HWC x(720,1280,3)
# numpy: x = np.zeros((720,1280,3)) # HWC
# torch: x = torch.zeros(16,3,720,1280) # BCHW
# multiple: x = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
p = next(self.model.parameters()) # for device and type
if isinstance(imgs, torch.Tensor): # torch
return self.model(imgs.to(p.device).type_as(p), augment,
profile) # inference
# Pre-process
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])
shape0, shape1 = [], [] # image and inference shapes
for i, img in enumerate(imgs):
if isinstance(img, str):
img = Image.open(img)
img = np.array(img)
if img.shape[0] < 5:
img = img.transpose((1, 2, 0))
img = img[:, :, :3] if img.ndim == 3 else np.tile(
img[:, :, None], 3)
s = img.shape[:2] # HWC
shape0.append(s) # image shape
g = (size / max(s)) # gain
shape1.append([y * g for y in s])
imgs[i] = img
shape1 = [
make_divisible(x, int(self.stride.max()))
for x in np.stack(shape1, 0).max(0)
] # inference shape
x = [letterbox(img, new_shape=shape1, auto=False)[0]
for img in imgs] # pad
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
x = torch.from_numpy(x).to(
p.device).type_as(p) / 255. # uint8 to fp16/32
# Inference
with torch.no_grad():
y = self.model(x, augment, profile)[0]
# y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
y = non_max_suppression_torch_ops(y,
conf_thres=self.conf,
iou_thres=self.iou,
classes=self.classes)
# Post-process
for i in range(n):
scale_coords(shape1, y[i][:, :4], shape0[i])
return Detections(imgs, y, self.names)
def parse_model(d, ch): # model_dict, input_channels(3)
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except NameError:
pass
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:
ch = []
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
def forward(self, x, size=640, augment=False, profile=False):
# supports inference from various sources. For height=720, width=1280, RGB images example inputs are:
# opencv: x = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(720,1280,3)
# PIL: x = Image.open('image.jpg') # HWC x(720,1280,3)
# numpy: x = np.zeros((720,1280,3)) # HWC
# torch: x = torch.zeros(16,3,720,1280) # BCHW
# multiple: x = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
p = next(self.model.parameters()) # for device and type
if isinstance(x, torch.Tensor): # torch
return self.model(x.to(p.device).type_as(p), augment, profile) # inference
# Pre-process
if not isinstance(x, list):
x = [x]
shape0, shape1 = [], [] # image and inference shapes
batch = range(len(x)) # batch size
for i in batch:
x[i] = np.array(x[i])[:, :, :3] # up to 3 channels if png
s = x[i].shape[:2] # HWC
shape0.append(s) # image shape
g = (size / max(s)) # gain
shape1.append([y * g for y in s])
shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
x = [letterbox(x[i], new_shape=shape1, auto=False)[0] for i in batch] # pad
x = np.stack(x, 0) if batch[-1] else x[0][None] # stack
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
x = torch.from_numpy(x).to(p.device).type_as(p) / 255. # uint8 to fp16/32
# Inference
x = self.model(x, augment, profile) # forward
x = non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes) # NMS
# Post-process
for i in batch:
if x[i] is not None:
x[i][:, :4] = scale_coords(shape1, x[i][:, :4], shape0[i])
return x
def forward(self, imgs, size=640, augment=False, profile=False):
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
# file: imgs = 'data/images/zidane.jpg' # str or PosixPath
# URI: = 'https://ultralytics.com/images/zidane.jpg'
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
# numpy: = np.zeros((640,1280,3)) # HWC
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
t = [time_sync()]
p = next(self.model.parameters()) if self.pt else torch.zeros(
1) # for device and type
autocast = self.amp and (p.device.type != 'cpu'
) # Automatic Mixed Precision (AMP) inference
if isinstance(imgs, torch.Tensor): # torch
with amp.autocast(enabled=autocast):
return self.model(
imgs.to(p.device).type_as(p), augment,
profile) # inference
# Pre-process
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (
1, [imgs]) # number of images, list of images
shape0, shape1, files = [], [], [
] # image and inference shapes, filenames
for i, im in enumerate(imgs):
f = f'image{i}' # filename
if isinstance(im, (str, Path)): # filename or uri
im, f = Image.open(
requests.get(im, stream=True).raw if str(im).
startswith('http') else im), im
im = np.asarray(exif_transpose(im))
elif isinstance(im, Image.Image): # PIL Image
im, f = np.asarray(
exif_transpose(im)), getattr(im, 'filename', f) or f
files.append(Path(f).with_suffix('.jpg').name)
if im.shape[0] < 5: # image in CHW
im = im.transpose(
(1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
im = im[..., :3] if im.ndim == 3 else np.tile(
im[..., None], 3) # enforce 3ch input
s = im.shape[:2] # HWC
shape0.append(s) # image shape
g = (size / max(s)) # gain
shape1.append([y * g for y in s])
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(
im) # update
shape1 = [
make_divisible(x, self.stride) for x in np.stack(shape1, 0).max(0)
] # inference shape
x = [
letterbox(im, new_shape=shape1 if self.pt else size, auto=False)[0]
for im in imgs
] # pad
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
x = torch.from_numpy(x).to(
p.device).type_as(p) / 255 # uint8 to fp16/32
t.append(time_sync())
with amp.autocast(enabled=autocast):
# Inference
y = self.model(x, augment, profile) # forward
t.append(time_sync())
# Post-process
y = non_max_suppression(y if self.dmb else y[0],
self.conf,
iou_thres=self.iou,
classes=self.classes,
agnostic=self.agnostic,
multi_label=self.multi_label,
max_det=self.max_det) # NMS
for i in range(n):
scale_coords(shape1, y[i][:, :4], shape0[i])
t.append(time_sync())
return Detections(imgs, y, files, t, self.names, x.shape)
def parse_model(d, ch): # model_dict, input_channels(3)
logger.info('\n%3s%18s%3s%10s %-40s%-30s' %
('', 'from', 'n', 'params', 'module', 'arguments'))
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d[
'width_multiple']
na = (len(anchors[0]) //
2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m,
args) in enumerate(d['backbone'] +
d['head']): # from, number, module, args
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except:
pass
n = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [
Conv, Bottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3
]:
c1, c2 = ch[f], args[0]
# Normal
# if i > 0 and args[0] != no: # channel expansion factor
# ex = 1.75 # exponential (default 2.0)
# e = math.log(c2 / ch[1]) / math.log(2)
# c2 = int(ch[1] * ex ** e)
# if m != Focus:
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
# Experimental
# if i > 0 and args[0] != no: # channel expansion factor
# ex = 1 + gw # exponential (default 2.0)
# ch1 = 32 # ch[1]
# e = math.log(c2 / ch1) / math.log(2) # level 1-n
# c2 = int(ch1 * ex ** e)
# if m != Focus:
# c2 = make_divisible(c2, 8) if c2 != no else c2
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3]:
args.insert(2, n)
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum([ch[x if x < 0 else x + 1] for x in f])
elif m is Detect:
args.append([ch[x + 1] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f if f < 0 else f + 1] * args[0]**2
elif m is Expand:
c2 = ch[f if f < 0 else f + 1] // args[0]**2
else:
c2 = ch[f if f < 0 else f + 1]
m_ = nn.Sequential(
*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum([x.numel() for x in m_.parameters()]) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
logger.info('%3s%18s%3s%10.0f %-40s%-30s' %
(i, f, n, np, t, args)) # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f)
if x != -1) # append to savelist
layers.append(m_)
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
LOGGER.info(
f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}"
)
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d[
'width_multiple']
na = (len(anchors[0]) //
2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m,
args) in enumerate(d['backbone'] +
d['head']): # from, number, module, args
m_str = m
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except NameError:
pass
n = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [
nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d,
Focus, CrossConv, BottleneckCSP, C3
]:
c1, c2 = ch[f], args[0]
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3]:
args.insert(2, n)
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
elif m is Detect:
args.append([ch[x + 1] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
args.append(imgsz)
else:
c2 = ch[f]
tf_m = eval('TF' + m_str.replace('nn.', ''))
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
else tf_m(*args, w=model.model[i]) # module
torch_m_ = nn.Sequential(
*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum(x.numel() for x in torch_m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(
f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}'
) # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f)
if x != -1) # append to savelist
layers.append(m_)
ch.append(c2)
return keras.Sequential(layers), sorted(save)
