Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Update Actions with Lychee and GitHub Token (#12592)

Browse Source 
* Add Ultralytics Actions

* Auto-format by Ultralytics actions

* Update format.yml

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

---------

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Paula DerrengerUltralyticsAssistantGlenn Jocher
 authored and GitHub committed 2024-01-08 01:29:14 +01:00
1 parent f56355d321
commit ad97dc6a6d
47 files changed
+4217 -3462
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

models/tf.py
+149 -103
View File
@@ -27,8 +27,21 @@ import torch
import torch.nn as nn
from tensorflow import keras
from models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv,
DWConvTranspose2d, Focus, autopad)
from models.common import (
C3,
SPP,
SPPF,
Bottleneck,
BottleneckCSP,
C3x,
Concat,
Conv,
CrossConv,
DWConv,
DWConvTranspose2d,
Focus,
autopad,
)
from models.experimental import MixConv2d, attempt_load
from models.yolo import Detect, Segment
from utils.activations import SiLU
@@ -44,7 +57,8 @@ class TFBN(keras.layers.Layer):
gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
epsilon=w.eps)
epsilon=w.eps,
)
def call(self, inputs):
return self.bn(inputs)
@@ -60,7 +74,7 @@ class TFPad(keras.layers.Layer):
self.pad = tf.constant([[0, 0], [pad[0], pad[0]], [pad[1], pad[1]], [0, 0]])
def call(self, inputs):
return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
return tf.pad(inputs, self.pad, mode="constant", constant_values=0)
class TFConv(keras.layers.Layer):
@@ -75,12 +89,13 @@ class TFConv(keras.layers.Layer):
filters=c2,
kernel_size=k,
strides=s,
padding='SAME' if s == 1 else 'VALID',
use_bias=not hasattr(w, 'bn'),
padding="SAME" if s == 1 else "VALID",
use_bias=not hasattr(w, "bn"),
kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
bias_initializer="zeros" if hasattr(w, "bn") else keras.initializers.Constant(w.conv.bias.numpy()),
)
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
self.bn = TFBN(w.bn) if hasattr(w, "bn") else tf.identity
self.act = activations(w.act) if act else tf.identity
def call(self, inputs):
@@ -92,17 +107,18 @@ class TFDWConv(keras.layers.Layer):
def __init__(self, c1, c2, k=1, s=1, p=None, act=True, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert c2 % c1 == 0, f'TFDWConv() output={c2} must be a multiple of input={c1} channels'
assert c2 % c1 == 0, f"TFDWConv() output={c2} must be a multiple of input={c1} channels"
conv = keras.layers.DepthwiseConv2D(
kernel_size=k,
depth_multiplier=c2 // c1,
strides=s,
padding='SAME' if s == 1 else 'VALID',
use_bias=not hasattr(w, 'bn'),
padding="SAME" if s == 1 else "VALID",
use_bias=not hasattr(w, "bn"),
depthwise_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
bias_initializer="zeros" if hasattr(w, "bn") else keras.initializers.Constant(w.conv.bias.numpy()),
)
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
self.bn = TFBN(w.bn) if hasattr(w, "bn") else tf.identity
self.act = activations(w.act) if act else tf.identity
def call(self, inputs):
@@ -114,19 +130,23 @@ class TFDWConvTranspose2d(keras.layers.Layer):
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert c1 == c2, f'TFDWConv() output={c2} must be equal to input={c1} channels'
assert k == 4 and p1 == 1, 'TFDWConv() only valid for k=4 and p1=1'
assert c1 == c2, f"TFDWConv() output={c2} must be equal to input={c1} channels"
assert k == 4 and p1 == 1, "TFDWConv() only valid for k=4 and p1=1"
weight, bias = w.weight.permute(2, 3, 1, 0).numpy(), w.bias.numpy()
self.c1 = c1
self.conv = [
keras.layers.Conv2DTranspose(filters=1,
kernel_size=k,
strides=s,
padding='VALID',
output_padding=p2,
use_bias=True,
kernel_initializer=keras.initializers.Constant(weight[..., i:i + 1]),
bias_initializer=keras.initializers.Constant(bias[i])) for i in range(c1)]
keras.layers.Conv2DTranspose(
filters=1,
kernel_size=k,
strides=s,
padding="VALID",
output_padding=p2,
use_bias=True,
kernel_initializer=keras.initializers.Constant(weight[..., i : i + 1]),
bias_initializer=keras.initializers.Constant(bias[i]),
)
for i in range(c1)
]
def call(self, inputs):
return tf.concat([m(x) for m, x in zip(self.conv, tf.split(inputs, self.c1, 3))], 3)[:, 1:-1, 1:-1]
@@ -176,14 +196,15 @@ class TFConv2d(keras.layers.Layer):
def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
super().__init__()
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
self.conv = keras.layers.Conv2D(filters=c2,
kernel_size=k,
strides=s,
padding='VALID',
use_bias=bias,
kernel_initializer=keras.initializers.Constant(
w.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None)
self.conv = keras.layers.Conv2D(
filters=c2,
kernel_size=k,
strides=s,
padding="VALID",
use_bias=bias,
kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None,
)
def call(self, inputs):
return self.conv(inputs)
@@ -233,8 +254,9 @@ class TFC3x(keras.layers.Layer):
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
self.m = keras.Sequential([
TFCrossConv(c_, c_, k=3, s=1, g=g, e=1.0, shortcut=shortcut, w=w.m[j]) for j in range(n)])
self.m = keras.Sequential(
[TFCrossConv(c_, c_, k=3, s=1, g=g, e=1.0, shortcut=shortcut, w=w.m[j]) for j in range(n)]
)
def call(self, inputs):
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
@@ -247,7 +269,7 @@ class TFSPP(keras.layers.Layer):
c_ = c1 // 2 # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding="SAME") for x in k]
def call(self, inputs):
x = self.cv1(inputs)
@@ -261,7 +283,7 @@ class TFSPPF(keras.layers.Layer):
c_ = c1 // 2 # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding="SAME")
def call(self, inputs):
x = self.cv1(inputs)
@@ -307,10 +329,10 @@ class TFDetect(keras.layers.Layer):
# Normalize xywh to 0-1 to reduce calibration error
xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
y = tf.concat([xy, wh, tf.sigmoid(y[..., 4:5 + self.nc]), y[..., 5 + self.nc:]], -1)
y = tf.concat([xy, wh, tf.sigmoid(y[..., 4 : 5 + self.nc]), y[..., 5 + self.nc :]], -1)
z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1), )
return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1),)
@staticmethod
def _make_grid(nx=20, ny=20):
@@ -340,11 +362,10 @@ class TFSegment(TFDetect):
class TFProto(keras.layers.Layer):
def __init__(self, c1, c_=256, c2=32, w=None):
super().__init__()
self.cv1 = TFConv(c1, c_, k=3, w=w.cv1)
self.upsample = TFUpsample(None, scale_factor=2, mode='nearest')
self.upsample = TFUpsample(None, scale_factor=2, mode="nearest")
self.cv2 = TFConv(c_, c_, k=3, w=w.cv2)
self.cv3 = TFConv(c_, c2, w=w.cv3)
@@ -356,7 +377,7 @@ class TFUpsample(keras.layers.Layer):
# TF version of torch.nn.Upsample()
def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
super().__init__()
assert scale_factor % 2 == 0, 'scale_factor must be multiple of 2'
assert scale_factor % 2 == 0, "scale_factor must be multiple of 2"
self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * scale_factor, x.shape[2] * scale_factor), mode)
# self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
# with default arguments: align_corners=False, half_pixel_centers=False
@@ -371,7 +392,7 @@ class TFConcat(keras.layers.Layer):
# TF version of torch.concat()
def __init__(self, dimension=1, w=None):
super().__init__()
assert dimension == 1, 'convert only NCHW to NHWC concat'
assert dimension == 1, "convert only NCHW to NHWC concat"
self.d = 3
def call(self, inputs):
@@ -380,15 +401,20 @@ class TFConcat(keras.layers.Layer):
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, ch_mul = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get(
'channel_multiple')
anchors, nc, gd, gw, ch_mul = (
d["anchors"],
d["nc"],
d["depth_multiple"],
d["width_multiple"],
d.get("channel_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)
if not ch_mul:
ch_mul = 8
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
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):
@@ -399,8 +425,20 @@ def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
n = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [
nn.Conv2d, Conv, DWConv, DWConvTranspose2d, Bottleneck, SPP, SPPF, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3x]:
nn.Conv2d,
Conv,
DWConv,
DWConvTranspose2d,
Bottleneck,
SPP,
SPPF,
MixConv2d,
Focus,
CrossConv,
BottleneckCSP,
C3,
C3x,
]:
c1, c2 = ch[f], args[0]
c2 = make_divisible(c2 * gw, ch_mul) if c2 != no else c2
@@ -422,15 +460,18 @@ def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
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
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
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
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)
@@ -439,30 +480,33 @@ def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
class TFModel:
# TF YOLOv5 model
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
def __init__(self, cfg="yolov5s.yaml", ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg) as f:
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
# Define model
if nc and nc != self.yaml['nc']:
if nc and nc != self.yaml["nc"]:
LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
self.yaml["nc"] = nc # override yaml value
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
def predict(self,
inputs,
tf_nms=False,
agnostic_nms=False,
topk_per_class=100,
topk_all=100,
iou_thres=0.45,
conf_thres=0.25):
def predict(
self,
inputs,
tf_nms=False,
agnostic_nms=False,
topk_per_class=100,
topk_all=100,
iou_thres=0.45,
conf_thres=0.25,
):
y = [] # outputs
x = inputs
for m in self.model.layers:
@@ -482,14 +526,10 @@ class TFModel:
nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
else:
boxes = tf.expand_dims(boxes, 2)
nms = tf.image.combined_non_max_suppression(boxes,
scores,
topk_per_class,
topk_all,
iou_thres,
conf_thres,
clip_boxes=False)
return (nms, )
nms = tf.image.combined_non_max_suppression(
boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False
)
return (nms,)
return x # output [1,6300,85] = [xywh, conf, class0, class1, ...]
# x = x[0] # [x(1,6300,85), ...] to x(6300,85)
# xywh = x[..., :4] # x(6300,4) boxes
@@ -508,36 +548,42 @@ class AgnosticNMS(keras.layers.Layer):
# TF Agnostic NMS
def call(self, input, topk_all, iou_thres, conf_thres):
# wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres),
input,
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
name='agnostic_nms')
return tf.map_fn(
lambda x: self._nms(x, topk_all, iou_thres, conf_thres),
input,
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
name="agnostic_nms",
)
@staticmethod
def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
boxes, classes, scores = x
class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
scores_inp = tf.reduce_max(scores, -1)
selected_inds = tf.image.non_max_suppression(boxes,
scores_inp,
max_output_size=topk_all,
iou_threshold=iou_thres,
score_threshold=conf_thres)
selected_inds = tf.image.non_max_suppression(
boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres
)
selected_boxes = tf.gather(boxes, selected_inds)
padded_boxes = tf.pad(selected_boxes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
mode='CONSTANT',
constant_values=0.0)
padded_boxes = tf.pad(
selected_boxes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
mode="CONSTANT",
constant_values=0.0,
)
selected_scores = tf.gather(scores_inp, selected_inds)
padded_scores = tf.pad(selected_scores,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode='CONSTANT',
constant_values=-1.0)
padded_scores = tf.pad(
selected_scores,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode="CONSTANT",
constant_values=-1.0,
)
selected_classes = tf.gather(class_inds, selected_inds)
padded_classes = tf.pad(selected_classes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode='CONSTANT',
constant_values=-1.0)
padded_classes = tf.pad(
selected_classes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode="CONSTANT",
constant_values=-1.0,
)
valid_detections = tf.shape(selected_inds)[0]
return padded_boxes, padded_scores, padded_classes, valid_detections
@@ -551,7 +597,7 @@ def activations(act=nn.SiLU):
elif isinstance(act, (nn.SiLU, SiLU)):
return lambda x: keras.activations.swish(x)
else:
raise Exception(f'no matching TensorFlow activation found for PyTorch activation {act}')
raise Exception(f"no matching TensorFlow activation found for PyTorch activation {act}")
def representative_dataset_gen(dataset, ncalib=100):
@@ -566,14 +612,14 @@ def representative_dataset_gen(dataset, ncalib=100):
def run(
weights=ROOT / 'yolov5s.pt', # weights path
imgsz=(640, 640), # inference size h,w
batch_size=1, # batch size
dynamic=False, # dynamic batch size
weights=ROOT / "yolov5s.pt", # weights path
imgsz=(640, 640), # inference size h,w
batch_size=1, # batch size
dynamic=False, # dynamic batch size
):
# PyTorch model
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
model = attempt_load(weights, device=torch.device('cpu'), inplace=True, fuse=False)
model = attempt_load(weights, device=torch.device("cpu"), inplace=True, fuse=False)
_ = model(im) # inference
model.info()
@@ -587,15 +633,15 @@ def run(
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
keras_model.summary()
LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
LOGGER.info("PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.")
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
parser.add_argument("--weights", type=str, default=ROOT / "yolov5s.pt", help="weights path")
parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], help="inference size h,w")
parser.add_argument("--batch-size", type=int, default=1, help="batch size")
parser.add_argument("--dynamic", action="store_true", help="dynamic batch size")
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(vars(opt))
@@ -606,6 +652,6 @@ def main(opt):
run(**vars(opt))
if __name__ == '__main__':
if __name__ == "__main__":
opt = parse_opt()
main(opt)