Model builder (#29)
Co-authored-by: Ayush Chaurasia <ayush.chuararsia@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>pull/31/head
Ayush Chaurasia
2 years ago
committed by
GitHub
parent
c5cb76b356
commit
7b560f7861
27 changed files with 2623 additions and 408 deletions
@ -0,0 +1,49 @@ |
||||
# Ultralytics, GPL-3.0 license |
||||
|
||||
# Parameters |
||||
nc: 80 # number of classes |
||||
depth_multiple: 0.33 # model depth multiple |
||||
width_multiple: 0.50 # layer channel multiple |
||||
anchors: |
||||
- [10,13, 16,30, 33,23] # P3/8 |
||||
- [30,61, 62,45, 59,119] # P4/16 |
||||
- [116,90, 156,198, 373,326] # P5/32 |
||||
|
||||
# YOLOv5 v6.0 backbone |
||||
backbone: |
||||
# [from, number, module, args] |
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 |
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4 |
||||
[-1, 3, C3, [128]], |
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8 |
||||
[-1, 6, C3, [256]], |
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16 |
||||
[-1, 9, C3, [512]], |
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 |
||||
[-1, 3, C3, [1024]], |
||||
[-1, 1, SPPF, [1024, 5]], # 9 |
||||
] |
||||
|
||||
# YOLOv5 v6.0 head |
||||
head: |
||||
[[-1, 1, Conv, [512, 1, 1]], |
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']], |
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4 |
||||
[-1, 3, C3, [512, False]], # 13 |
||||
|
||||
[-1, 1, Conv, [256, 1, 1]], |
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']], |
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3 |
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small) |
||||
|
||||
[-1, 1, Conv, [256, 3, 2]], |
||||
[[-1, 14], 1, Concat, [1]], # cat head P4 |
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium) |
||||
|
||||
[-1, 1, Conv, [512, 3, 2]], |
||||
[[-1, 10], 1, Concat, [1]], # cat head P5 |
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large) |
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) |
||||
] |
||||
|
||||
@ -0,0 +1,34 @@ |
||||
import torch |
||||
|
||||
from ultralytics.yolo.utils.checks import check_yaml |
||||
from ultralytics.yolo.utils.modeling.tasks import DetectionModel |
||||
|
||||
|
||||
def test_model_parser(): |
||||
cfg = check_yaml("../assets/dummy_model.yaml") # check YAML |
||||
|
||||
# Create model |
||||
model = DetectionModel(cfg) |
||||
print(model) |
||||
''' |
||||
# Options |
||||
if opt.line_profile: # profile layer by layer |
||||
model(im, profile=True) |
||||
|
||||
elif opt.profile: # profile forward-backward |
||||
results = profile(input=im, ops=[model], n=3) |
||||
|
||||
elif opt.test: # test all models |
||||
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'): |
||||
try: |
||||
_ = Model(cfg) |
||||
except Exception as e: |
||||
print(f'Error in {cfg}: {e}') |
||||
|
||||
else: # report fused model summary |
||||
model.fuse() |
||||
''' |
||||
|
||||
|
||||
if __name__ == "__main__": |
||||
test_model_parser() |
||||
@ -1,3 +1,4 @@ |
||||
from .base import BaseDataset |
||||
from .build import build_classification_dataloader, build_dataloader |
||||
from .dataset import ClassificationDataset, SemanticDataset, YOLODataset |
||||
from .dataset_wrappers import MixAndRectDataset |
||||
|
||||
@ -1,18 +1,40 @@ |
||||
from .general import Profile, WorkingDirectory, check_version, download, increment_path, save_yaml |
||||
from .torch_utils import LOCAL_RANK, RANK, WORLD_SIZE, DDP_model, select_device, torch_distributed_zero_first |
||||
|
||||
__all__ = [ |
||||
# general |
||||
"increment_path", |
||||
"save_yaml", |
||||
"WorkingDirectory", |
||||
"download", |
||||
"check_version", |
||||
"Profile", |
||||
# torch |
||||
"torch_distributed_zero_first", |
||||
"LOCAL_RANK", |
||||
"RANK", |
||||
"WORLD_SIZE", |
||||
"DDP_model", |
||||
"select_device"] |
||||
import contextlib |
||||
import logging |
||||
import os |
||||
import platform |
||||
from pathlib import Path |
||||
|
||||
from .files import user_config_dir |
||||
from .loggers import emojis, set_logging |
||||
|
||||
# Constants |
||||
|
||||
FILE = Path(__file__).resolve() |
||||
ROOT = FILE.parents[2] # YOLOv5 root directory |
||||
RANK = int(os.getenv('RANK', -1)) |
||||
DATASETS_DIR = ROOT.parent / 'datasets' # YOLOv5 datasets directory |
||||
NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiprocessing threads |
||||
AUTOINSTALL = str(os.getenv('YOLOv5_AUTOINSTALL', True)).lower() == 'true' # global auto-install mode |
||||
FONT = 'Arial.ttf' # https://ultralytics.com/assets/Arial.ttf |
||||
|
||||
CONFIG_DIR = user_config_dir() # Ultralytics settings dir |
||||
|
||||
set_logging() # run before defining LOGGER |
||||
LOGGER = logging.getLogger("yolov5") # define globally |
||||
if platform.system() == "Windows": |
||||
for fn in LOGGER.info, LOGGER.warning: |
||||
setattr(LOGGER, fn.__name__, lambda x: fn(emojis(x))) # emoji safe logging |
||||
|
||||
|
||||
class TryExcept(contextlib.ContextDecorator): |
||||
# YOLOv5 TryExcept class. Usage: @TryExcept() decorator or 'with TryExcept():' context manager |
||||
def __init__(self, msg=''): |
||||
self.msg = msg |
||||
|
||||
def __enter__(self): |
||||
pass |
||||
|
||||
def __exit__(self, exc_type, value, traceback): |
||||
if value: |
||||
print(emojis(f'{self.msg}{value}')) |
||||
return True |
||||
|
||||
@ -0,0 +1,74 @@ |
||||
import contextlib |
||||
import os |
||||
import platform |
||||
from pathlib import Path |
||||
|
||||
import yaml |
||||
|
||||
|
||||
class WorkingDirectory(contextlib.ContextDecorator): |
||||
# Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager |
||||
def __init__(self, new_dir): |
||||
self.dir = new_dir # new dir |
||||
self.cwd = Path.cwd().resolve() # current dir |
||||
|
||||
def __enter__(self): |
||||
os.chdir(self.dir) |
||||
|
||||
def __exit__(self, exc_type, exc_val, exc_tb): |
||||
os.chdir(self.cwd) |
||||
|
||||
|
||||
def is_writeable(dir, test=False): |
||||
# Return True if directory has write permissions, test opening a file with write permissions if test=True |
||||
if not test: |
||||
return os.access(dir, os.W_OK) # possible issues on Windows |
||||
file = Path(dir) / 'tmp.txt' |
||||
try: |
||||
with open(file, 'w'): # open file with write permissions |
||||
pass |
||||
file.unlink() # remove file |
||||
return True |
||||
except OSError: |
||||
return False |
||||
|
||||
|
||||
def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'): |
||||
# Return path of user configuration directory. Prefer environment variable if exists. Make dir if required. |
||||
env = os.getenv(env_var) |
||||
if env: |
||||
path = Path(env) # use environment variable |
||||
else: |
||||
cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs |
||||
path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir |
||||
path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable |
||||
path.mkdir(exist_ok=True) # make if required |
||||
return path |
||||
|
||||
|
||||
def increment_path(path, exist_ok=False, sep='', mkdir=False): |
||||
""" |
||||
Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. |
||||
# TODO: docs |
||||
""" |
||||
path = Path(path) # os-agnostic |
||||
if path.exists() and not exist_ok: |
||||
path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '') |
||||
|
||||
# Method 1 |
||||
for n in range(2, 9999): |
||||
p = f'{path}{sep}{n}{suffix}' # increment path |
||||
if not os.path.exists(p): # |
||||
break |
||||
path = Path(p) |
||||
|
||||
if mkdir: |
||||
path.mkdir(parents=True, exist_ok=True) # make directory |
||||
|
||||
return path |
||||
|
||||
|
||||
def save_yaml(file='data.yaml', data=None): |
||||
# Single-line safe yaml saving |
||||
with open(file, 'w') as f: |
||||
yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False) |
||||
@ -1,3 +1,57 @@ |
||||
import logging |
||||
import os |
||||
import platform |
||||
|
||||
from .base import default_callbacks |
||||
|
||||
__all__ = ["default_callbacks"] |
||||
VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true' # global verbose mode |
||||
|
||||
|
||||
# console logging utils |
||||
def emojis(str=''): |
||||
# Return platform-dependent emoji-safe version of string |
||||
return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str |
||||
|
||||
|
||||
def colorstr(*input): |
||||
# Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world') |
||||
*args, string = input if len(input) > 1 else ("blue", "bold", input[0]) # color arguments, string |
||||
colors = { |
||||
"black": "\033[30m", # basic colors |
||||
"red": "\033[31m", |
||||
"green": "\033[32m", |
||||
"yellow": "\033[33m", |
||||
"blue": "\033[34m", |
||||
"magenta": "\033[35m", |
||||
"cyan": "\033[36m", |
||||
"white": "\033[37m", |
||||
"bright_black": "\033[90m", # bright colors |
||||
"bright_red": "\033[91m", |
||||
"bright_green": "\033[92m", |
||||
"bright_yellow": "\033[93m", |
||||
"bright_blue": "\033[94m", |
||||
"bright_magenta": "\033[95m", |
||||
"bright_cyan": "\033[96m", |
||||
"bright_white": "\033[97m", |
||||
"end": "\033[0m", # misc |
||||
"bold": "\033[1m", |
||||
"underline": "\033[4m",} |
||||
return "".join(colors[x] for x in args) + f"{string}" + colors["end"] |
||||
|
||||
|
||||
def set_logging(name=None, verbose=VERBOSE): |
||||
# Sets level and returns logger |
||||
is_kaggle = os.environ.get("PWD") == "/kaggle/working" and os.environ.get( |
||||
"KAGGLE_URL_BASE") == "https://www.kaggle.com" |
||||
is_colab = "COLAB_GPU" in os.environ |
||||
if is_colab or is_kaggle: |
||||
for h in logging.root.handlers: |
||||
logging.root.removeHandler(h) # remove all handlers associated with the root logger object |
||||
rank = int(os.getenv("RANK", -1)) # rank in world for Multi-GPU trainings |
||||
level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR |
||||
log = logging.getLogger(name) |
||||
log.setLevel(level) |
||||
handler = logging.StreamHandler() |
||||
handler.setFormatter(logging.Formatter("%(message)s")) |
||||
handler.setLevel(level) |
||||
log.addHandler(handler) |
||||
|
||||
@ -0,0 +1,113 @@ |
||||
import contextlib |
||||
|
||||
import yaml |
||||
|
||||
from ultralytics.yolo.utils.downloads import attempt_download |
||||
|
||||
from .modules import * |
||||
|
||||
|
||||
def attempt_load_weights(weights, device=None, inplace=True, fuse=True): |
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a |
||||
|
||||
model = Ensemble() |
||||
for w in weights if isinstance(weights, list) else [weights]: |
||||
ckpt = torch.load(attempt_download(w), map_location='cpu') # load |
||||
ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float() # FP32 model |
||||
|
||||
# Model compatibility updates |
||||
if not hasattr(ckpt, 'stride'): |
||||
ckpt.stride = torch.tensor([32.]) |
||||
if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)): |
||||
ckpt.names = dict(enumerate(ckpt.names)) # convert to dict |
||||
|
||||
model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval()) # model in eval mode |
||||
|
||||
# Module compatibility updates |
||||
for m in model.modules(): |
||||
t = type(m) |
||||
if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model): |
||||
m.inplace = inplace # torch 1.7.0 compatibility |
||||
if t is Detect and not isinstance(m.anchor_grid, list): |
||||
delattr(m, 'anchor_grid') |
||||
setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl) |
||||
elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'): |
||||
m.recompute_scale_factor = None # torch 1.11.0 compatibility |
||||
|
||||
# Return model |
||||
if len(model) == 1: |
||||
return model[-1] |
||||
|
||||
# Return detection ensemble |
||||
print(f'Ensemble created with {weights}\n') |
||||
for k in 'names', 'nc', 'yaml': |
||||
setattr(model, k, getattr(model[0], k)) |
||||
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride |
||||
assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}' |
||||
return model |
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3) |
||||
# Parse a YOLOv5 model.yaml dictionary |
||||
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}") |
||||
anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation') |
||||
if act: |
||||
Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU() |
||||
LOGGER.info(f"{colorstr('activation:')} {act}") # print |
||||
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): |
||||
with contextlib.suppress(NameError): |
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings |
||||
|
||||
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain |
||||
if m in { |
||||
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, CrossConv, BottleneckCSP, C3, |
||||
C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}: |
||||
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, C3x}: |
||||
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) |
||||
# TODO: channel, gw, gd |
||||
elif m in {Detect, Segment}: |
||||
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) |
||||
if m is Segment: |
||||
args[3] = make_divisible(args[3] * gw, 8) |
||||
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 yaml_load(file='data.yaml'): |
||||
# Single-line safe yaml loading |
||||
with open(file, errors='ignore') as f: |
||||
return yaml.safe_load(f) |
||||
@ -0,0 +1,324 @@ |
||||
import json |
||||
import platform |
||||
from collections import OrderedDict, namedtuple |
||||
from pathlib import Path |
||||
from urllib.parse import urlparse |
||||
|
||||
import cv2 |
||||
import numpy as np |
||||
import torch |
||||
import torch.nn as nn |
||||
from PIL import Image |
||||
|
||||
from ultralytics.yolo.utils import LOGGER, ROOT |
||||
from ultralytics.yolo.utils.checks import check_requirements, check_suffix, check_version |
||||
from ultralytics.yolo.utils.downloads import attempt_download, is_url |
||||
from ultralytics.yolo.utils.ops import xywh2xyxy |
||||
|
||||
|
||||
class AutoBackend(nn.Module): |
||||
# YOLOv5 MultiBackend class for python inference on various backends |
||||
def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True): |
||||
# Usage: |
||||
# PyTorch: weights = *.pt |
||||
# TorchScript: *.torchscript |
||||
# ONNX Runtime: *.onnx |
||||
# ONNX OpenCV DNN: *.onnx --dnn |
||||
# OpenVINO: *.xml |
||||
# CoreML: *.mlmodel |
||||
# TensorRT: *.engine |
||||
# TensorFlow SavedModel: *_saved_model |
||||
# TensorFlow GraphDef: *.pb |
||||
# TensorFlow Lite: *.tflite |
||||
# TensorFlow Edge TPU: *_edgetpu.tflite |
||||
# PaddlePaddle: *_paddle_model |
||||
from ultralytics.yolo.utils.modeling import attempt_load_weights, yaml_load |
||||
|
||||
super().__init__() |
||||
w = str(weights[0] if isinstance(weights, list) else weights) |
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w) |
||||
fp16 &= pt or jit or onnx or engine # FP16 |
||||
nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH) |
||||
stride = 32 # default stride |
||||
cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA |
||||
if not (pt or triton): |
||||
w = attempt_download(w) # download if not local |
||||
|
||||
if pt: # PyTorch |
||||
model = attempt_load_weights(weights if isinstance(weights, list) else w, |
||||
device=device, |
||||
inplace=True, |
||||
fuse=fuse) |
||||
stride = max(int(model.stride.max()), 32) # model stride |
||||
names = model.module.names if hasattr(model, 'module') else model.names # get class names |
||||
model.half() if fp16 else model.float() |
||||
self.model = model # explicitly assign for to(), cpu(), cuda(), half() |
||||
elif jit: # TorchScript |
||||
LOGGER.info(f'Loading {w} for TorchScript inference...') |
||||
extra_files = {'config.txt': ''} # model metadata |
||||
model = torch.jit.load(w, _extra_files=extra_files, map_location=device) |
||||
model.half() if fp16 else model.float() |
||||
if extra_files['config.txt']: # load metadata dict |
||||
d = json.loads(extra_files['config.txt'], |
||||
object_hook=lambda d: {int(k) if k.isdigit() else k: v |
||||
for k, v in d.items()}) |
||||
stride, names = int(d['stride']), d['names'] |
||||
elif dnn: # ONNX OpenCV DNN |
||||
LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...') |
||||
check_requirements('opencv-python>=4.5.4') |
||||
net = cv2.dnn.readNetFromONNX(w) |
||||
elif onnx: # ONNX Runtime |
||||
LOGGER.info(f'Loading {w} for ONNX Runtime inference...') |
||||
check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime')) |
||||
import onnxruntime |
||||
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider'] |
||||
session = onnxruntime.InferenceSession(w, providers=providers) |
||||
output_names = [x.name for x in session.get_outputs()] |
||||
meta = session.get_modelmeta().custom_metadata_map # metadata |
||||
if 'stride' in meta: |
||||
stride, names = int(meta['stride']), eval(meta['names']) |
||||
elif xml: # OpenVINO |
||||
LOGGER.info(f'Loading {w} for OpenVINO inference...') |
||||
check_requirements('openvino') # requires openvino-dev: https://pypi.org/project/openvino-dev/ |
||||
from openvino.runtime import Core, Layout, get_batch |
||||
ie = Core() |
||||
if not Path(w).is_file(): # if not *.xml |
||||
w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir |
||||
network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin')) |
||||
if network.get_parameters()[0].get_layout().empty: |
||||
network.get_parameters()[0].set_layout(Layout("NCHW")) |
||||
batch_dim = get_batch(network) |
||||
if batch_dim.is_static: |
||||
batch_size = batch_dim.get_length() |
||||
executable_network = ie.compile_model(network, device_name="CPU") # device_name="MYRIAD" for Intel NCS2 |
||||
stride, names = self._load_metadata(Path(w).with_suffix('.yaml')) # load metadata |
||||
elif engine: # TensorRT |
||||
LOGGER.info(f'Loading {w} for TensorRT inference...') |
||||
import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download |
||||
check_version(trt.__version__, '7.0.0', hard=True) # require tensorrt>=7.0.0 |
||||
if device.type == 'cpu': |
||||
device = torch.device('cuda:0') |
||||
Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr')) |
||||
logger = trt.Logger(trt.Logger.INFO) |
||||
with open(w, 'rb') as f, trt.Runtime(logger) as runtime: |
||||
model = runtime.deserialize_cuda_engine(f.read()) |
||||
context = model.create_execution_context() |
||||
bindings = OrderedDict() |
||||
output_names = [] |
||||
fp16 = False # default updated below |
||||
dynamic = False |
||||
for i in range(model.num_bindings): |
||||
name = model.get_binding_name(i) |
||||
dtype = trt.nptype(model.get_binding_dtype(i)) |
||||
if model.binding_is_input(i): |
||||
if -1 in tuple(model.get_binding_shape(i)): # dynamic |
||||
dynamic = True |
||||
context.set_binding_shape(i, tuple(model.get_profile_shape(0, i)[2])) |
||||
if dtype == np.float16: |
||||
fp16 = True |
||||
else: # output |
||||
output_names.append(name) |
||||
shape = tuple(context.get_binding_shape(i)) |
||||
im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device) |
||||
bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr())) |
||||
binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items()) |
||||
batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size |
||||
elif coreml: # CoreML |
||||
LOGGER.info(f'Loading {w} for CoreML inference...') |
||||
import coremltools as ct |
||||
model = ct.models.MLModel(w) |
||||
elif saved_model: # TF SavedModel |
||||
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...') |
||||
import tensorflow as tf |
||||
keras = False # assume TF1 saved_model |
||||
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w) |
||||
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt |
||||
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...') |
||||
import tensorflow as tf |
||||
|
||||
def wrap_frozen_graph(gd, inputs, outputs): |
||||
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped |
||||
ge = x.graph.as_graph_element |
||||
return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs)) |
||||
|
||||
def gd_outputs(gd): |
||||
name_list, input_list = [], [] |
||||
for node in gd.node: # tensorflow.core.framework.node_def_pb2.NodeDef |
||||
name_list.append(node.name) |
||||
input_list.extend(node.input) |
||||
return sorted(f'{x}:0' for x in list(set(name_list) - set(input_list)) if not x.startswith('NoOp')) |
||||
|
||||
gd = tf.Graph().as_graph_def() # TF GraphDef |
||||
with open(w, 'rb') as f: |
||||
gd.ParseFromString(f.read()) |
||||
frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs=gd_outputs(gd)) |
||||
elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python |
||||
try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu |
||||
from tflite_runtime.interpreter import Interpreter, load_delegate |
||||
except ImportError: |
||||
import tensorflow as tf |
||||
Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate, |
||||
if edgetpu: # TF Edge TPU https://coral.ai/software/#edgetpu-runtime |
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...') |
||||
delegate = { |
||||
'Linux': 'libedgetpu.so.1', |
||||
'Darwin': 'libedgetpu.1.dylib', |
||||
'Windows': 'edgetpu.dll'}[platform.system()] |
||||
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)]) |
||||
else: # TFLite |
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite inference...') |
||||
interpreter = Interpreter(model_path=w) # load TFLite model |
||||
interpreter.allocate_tensors() # allocate |
||||
input_details = interpreter.get_input_details() # inputs |
||||
output_details = interpreter.get_output_details() # outputs |
||||
elif tfjs: # TF.js |
||||
raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported') |
||||
elif paddle: # PaddlePaddle |
||||
LOGGER.info(f'Loading {w} for PaddlePaddle inference...') |
||||
check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle') |
||||
import paddle.inference as pdi |
||||
if not Path(w).is_file(): # if not *.pdmodel |
||||
w = next(Path(w).rglob('*.pdmodel')) # get *.xml file from *_openvino_model dir |
||||
weights = Path(w).with_suffix('.pdiparams') |
||||
config = pdi.Config(str(w), str(weights)) |
||||
if cuda: |
||||
config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0) |
||||
predictor = pdi.create_predictor(config) |
||||
input_handle = predictor.get_input_handle(predictor.get_input_names()[0]) |
||||
output_names = predictor.get_output_names() |
||||
elif triton: # NVIDIA Triton Inference Server |
||||
LOGGER.info('Triton Inference Server not supported...') |
||||
''' |
||||
TODO: |
||||
check_requirements('tritonclient[all]') |
||||
from utils.triton import TritonRemoteModel |
||||
model = TritonRemoteModel(url=w) |
||||
nhwc = model.runtime.startswith("tensorflow") |
||||
''' |
||||
else: |
||||
raise NotImplementedError(f'ERROR: {w} is not a supported format') |
||||
|
||||
# class names |
||||
if 'names' not in locals(): |
||||
names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)} |
||||
if names[0] == 'n01440764' and len(names) == 1000: # ImageNet |
||||
names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] # human-readable names |
||||
|
||||
self.__dict__.update(locals()) # assign all variables to self |
||||
|
||||
def forward(self, im, augment=False, visualize=False): |
||||
# YOLOv5 MultiBackend inference |
||||
b, ch, h, w = im.shape # batch, channel, height, width |
||||
if self.fp16 and im.dtype != torch.float16: |
||||
im = im.half() # to FP16 |
||||
if self.nhwc: |
||||
im = im.permute(0, 2, 3, 1) # torch BCHW to numpy BHWC shape(1,320,192,3) |
||||
|
||||
if self.pt: # PyTorch |
||||
y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im) |
||||
elif self.jit: # TorchScript |
||||
y = self.model(im) |
||||
elif self.dnn: # ONNX OpenCV DNN |
||||
im = im.cpu().numpy() # torch to numpy |
||||
self.net.setInput(im) |
||||
y = self.net.forward() |
||||
elif self.onnx: # ONNX Runtime |
||||
im = im.cpu().numpy() # torch to numpy |
||||
y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im}) |
||||
elif self.xml: # OpenVINO |
||||
im = im.cpu().numpy() # FP32 |
||||
y = list(self.executable_network([im]).values()) |
||||
elif self.engine: # TensorRT |
||||
if self.dynamic and im.shape != self.bindings['images'].shape: |
||||
i = self.model.get_binding_index('images') |
||||
self.context.set_binding_shape(i, im.shape) # reshape if dynamic |
||||
self.bindings['images'] = self.bindings['images']._replace(shape=im.shape) |
||||
for name in self.output_names: |
||||
i = self.model.get_binding_index(name) |
||||
self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i))) |
||||
s = self.bindings['images'].shape |
||||
assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}" |
||||
self.binding_addrs['images'] = int(im.data_ptr()) |
||||
self.context.execute_v2(list(self.binding_addrs.values())) |
||||
y = [self.bindings[x].data for x in sorted(self.output_names)] |
||||
elif self.coreml: # CoreML |
||||
im = im.cpu().numpy() |
||||
im = Image.fromarray((im[0] * 255).astype('uint8')) |
||||
# im = im.resize((192, 320), Image.ANTIALIAS) |
||||
y = self.model.predict({'image': im}) # coordinates are xywh normalized |
||||
if 'confidence' in y: |
||||
box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels |
||||
conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float) |
||||
y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) |
||||
else: |
||||
y = list(reversed(y.values())) # reversed for segmentation models (pred, proto) |
||||
elif self.paddle: # PaddlePaddle |
||||
im = im.cpu().numpy().astype(np.float32) |
||||
self.input_handle.copy_from_cpu(im) |
||||
self.predictor.run() |
||||
y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names] |
||||
elif self.triton: # NVIDIA Triton Inference Server |
||||
y = self.model(im) |
||||
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) |
||||
im = im.cpu().numpy() |
||||
if self.saved_model: # SavedModel |
||||
y = self.model(im, training=False) if self.keras else self.model(im) |
||||
elif self.pb: # GraphDef |
||||
y = self.frozen_func(x=self.tf.constant(im)) |
||||
else: # Lite or Edge TPU |
||||
input = self.input_details[0] |
||||
int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model |
||||
if int8: |
||||
scale, zero_point = input['quantization'] |
||||
im = (im / scale + zero_point).astype(np.uint8) # de-scale |
||||
self.interpreter.set_tensor(input['index'], im) |
||||
self.interpreter.invoke() |
||||
y = [] |
||||
for output in self.output_details: |
||||
x = self.interpreter.get_tensor(output['index']) |
||||
if int8: |
||||
scale, zero_point = output['quantization'] |
||||
x = (x.astype(np.float32) - zero_point) * scale # re-scale |
||||
y.append(x) |
||||
y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y] |
||||
y[0][..., :4] *= [w, h, w, h] # xywh normalized to pixels |
||||
|
||||
if isinstance(y, (list, tuple)): |
||||
return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y] |
||||
else: |
||||
return self.from_numpy(y) |
||||
|
||||
def from_numpy(self, x): |
||||
return torch.from_numpy(x).to(self.device) if isinstance(x, np.ndarray) else x |
||||
|
||||
def warmup(self, imgsz=(1, 3, 640, 640)): |
||||
# Warmup model by running inference once |
||||
warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton |
||||
if any(warmup_types) and (self.device.type != 'cpu' or self.triton): |
||||
im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input |
||||
for _ in range(2 if self.jit else 1): # |
||||
self.forward(im) # warmup |
||||
|
||||
@staticmethod |
||||
def _model_type(p='path/to/model.pt'): |
||||
# Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx |
||||
# types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle] |
||||
from export import export_formats |
||||
sf = list(export_formats().Suffix) # export suffixes |
||||
if not is_url(p, check=False): |
||||
check_suffix(p, sf) # checks |
||||
url = urlparse(p) # if url may be Triton inference server |
||||
types = [s in Path(p).name for s in sf] |
||||
types[8] &= not types[9] # tflite &= not edgetpu |
||||
triton = not any(types) and all([any(s in url.scheme for s in ["http", "grpc"]), url.netloc]) |
||||
return types + [triton] |
||||
|
||||
@staticmethod |
||||
def _load_metadata(f=Path('path/to/meta.yaml')): |
||||
from ultralytics.yolo.utils.modeling import yaml_load |
||||
|
||||
# Load metadata from meta.yaml if it exists |
||||
if f.exists(): |
||||
d = yaml_load(f) |
||||
return d['stride'], d['names'] # assign stride, names |
||||
return None, None |
||||
@ -0,0 +1,635 @@ |
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license |
||||
""" |
||||
Common modules |
||||
""" |
||||
|
||||
import argparse |
||||
import math |
||||
import warnings |
||||
from copy import copy |
||||
from pathlib import Path |
||||
|
||||
import cv2 |
||||
import numpy as np |
||||
import pandas as pd |
||||
import requests |
||||
import torch |
||||
import torch.nn as nn |
||||
from PIL import Image, ImageOps |
||||
from torch.cuda import amp |
||||
|
||||
from ultralytics.yolo.data.augment import LetterBox |
||||
from ultralytics.yolo.utils import LOGGER |
||||
from ultralytics.yolo.utils.checks import check_version |
||||
from ultralytics.yolo.utils.files import increment_path |
||||
from ultralytics.yolo.utils.loggers import colorstr |
||||
from ultralytics.yolo.utils.ops import Profile, make_divisible, non_max_suppression, scale_boxes, xyxy2xywh |
||||
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box |
||||
from ultralytics.yolo.utils.torch_utils import copy_attr, smart_inference_mode |
||||
|
||||
from .autobackend import AutoBackend |
||||
|
||||
# from utils.plots import feature_visualization TODO |
||||
|
||||
|
||||
def autopad(k, p=None, d=1): # kernel, padding, dilation |
||||
# Pad to 'same' shape outputs |
||||
if d > 1: |
||||
k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size |
||||
if p is None: |
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad |
||||
return p |
||||
|
||||
|
||||
class Conv(nn.Module): |
||||
# Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation) |
||||
default_act = nn.SiLU() # default activation |
||||
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): |
||||
super().__init__() |
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) |
||||
self.bn = nn.BatchNorm2d(c2) |
||||
self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() |
||||
|
||||
def forward(self, x): |
||||
return self.act(self.bn(self.conv(x))) |
||||
|
||||
def forward_fuse(self, x): |
||||
return self.act(self.conv(x)) |
||||
|
||||
|
||||
class DWConv(Conv): |
||||
# Depth-wise convolution |
||||
def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation |
||||
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act) |
||||
|
||||
|
||||
class DWConvTranspose2d(nn.ConvTranspose2d): |
||||
# Depth-wise transpose convolution |
||||
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out |
||||
super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2)) |
||||
|
||||
|
||||
class TransformerLayer(nn.Module): |
||||
# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance) |
||||
def __init__(self, c, num_heads): |
||||
super().__init__() |
||||
self.q = nn.Linear(c, c, bias=False) |
||||
self.k = nn.Linear(c, c, bias=False) |
||||
self.v = nn.Linear(c, c, bias=False) |
||||
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads) |
||||
self.fc1 = nn.Linear(c, c, bias=False) |
||||
self.fc2 = nn.Linear(c, c, bias=False) |
||||
|
||||
def forward(self, x): |
||||
x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x |
||||
x = self.fc2(self.fc1(x)) + x |
||||
return x |
||||
|
||||
|
||||
class TransformerBlock(nn.Module): |
||||
# Vision Transformer https://arxiv.org/abs/2010.11929 |
||||
def __init__(self, c1, c2, num_heads, num_layers): |
||||
super().__init__() |
||||
self.conv = None |
||||
if c1 != c2: |
||||
self.conv = Conv(c1, c2) |
||||
self.linear = nn.Linear(c2, c2) # learnable position embedding |
||||
self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers))) |
||||
self.c2 = c2 |
||||
|
||||
def forward(self, x): |
||||
if self.conv is not None: |
||||
x = self.conv(x) |
||||
b, _, w, h = x.shape |
||||
p = x.flatten(2).permute(2, 0, 1) |
||||
return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h) |
||||
|
||||
|
||||
class Bottleneck(nn.Module): |
||||
# Standard bottleneck |
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion |
||||
super().__init__() |
||||
c_ = int(c2 * e) # hidden channels |
||||
self.cv1 = Conv(c1, c_, 1, 1) |
||||
self.cv2 = Conv(c_, c2, 3, 1, g=g) |
||||
self.add = shortcut and c1 == c2 |
||||
|
||||
def forward(self, x): |
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) |
||||
|
||||
|
||||
class BottleneckCSP(nn.Module): |
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks |
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion |
||||
super().__init__() |
||||
c_ = int(c2 * e) # hidden channels |
||||
self.cv1 = Conv(c1, c_, 1, 1) |
||||
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False) |
||||
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False) |
||||
self.cv4 = Conv(2 * c_, c2, 1, 1) |
||||
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3) |
||||
self.act = nn.SiLU() |
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) |
||||
|
||||
def forward(self, x): |
||||
y1 = self.cv3(self.m(self.cv1(x))) |
||||
y2 = self.cv2(x) |
||||
return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1)))) |
||||
|
||||
|
||||
class CrossConv(nn.Module): |
||||
# Cross Convolution Downsample |
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): |
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut |
||||
super().__init__() |
||||
c_ = int(c2 * e) # hidden channels |
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s)) |
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) |
||||
self.add = shortcut and c1 == c2 |
||||
|
||||
def forward(self, x): |
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) |
||||
|
||||
|
||||
class C3(nn.Module): |
||||
# CSP Bottleneck with 3 convolutions |
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion |
||||
super().__init__() |
||||
c_ = int(c2 * e) # hidden channels |
||||
self.cv1 = Conv(c1, c_, 1, 1) |
||||
self.cv2 = Conv(c1, c_, 1, 1) |
||||
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) |
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) |
||||
|
||||
def forward(self, x): |
||||
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)) |
||||
|
||||
|
||||
class C3x(C3): |
||||
# C3 module with cross-convolutions |
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): |
||||
super().__init__(c1, c2, n, shortcut, g, e) |
||||
c_ = int(c2 * e) |
||||
self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n))) |
||||
|
||||
|
||||
class C3TR(C3): |
||||
# C3 module with TransformerBlock() |
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): |
||||
super().__init__(c1, c2, n, shortcut, g, e) |
||||
c_ = int(c2 * e) |
||||
self.m = TransformerBlock(c_, c_, 4, n) |
||||
|
||||
|
||||
class C3SPP(C3): |
||||
# C3 module with SPP() |
||||
def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5): |
||||
super().__init__(c1, c2, n, shortcut, g, e) |
||||
c_ = int(c2 * e) |
||||
self.m = SPP(c_, c_, k) |
||||
|
||||
|
||||
class C3Ghost(C3): |
||||
# C3 module with GhostBottleneck() |
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): |
||||
super().__init__(c1, c2, n, shortcut, g, e) |
||||
c_ = int(c2 * e) # hidden channels |
||||
self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n))) |
||||
|
||||
|
||||
class SPP(nn.Module): |
||||
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729 |
||||
def __init__(self, c1, c2, k=(5, 9, 13)): |
||||
super().__init__() |
||||
c_ = c1 // 2 # hidden channels |
||||
self.cv1 = Conv(c1, c_, 1, 1) |
||||
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) |
||||
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) |
||||
|
||||
def forward(self, x): |
||||
x = self.cv1(x) |
||||
with warnings.catch_warnings(): |
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning |
||||
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) |
||||
|
||||
|
||||
class SPPF(nn.Module): |
||||
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher |
||||
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13)) |
||||
super().__init__() |
||||
c_ = c1 // 2 # hidden channels |
||||
self.cv1 = Conv(c1, c_, 1, 1) |
||||
self.cv2 = Conv(c_ * 4, c2, 1, 1) |
||||
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) |
||||
|
||||
def forward(self, x): |
||||
x = self.cv1(x) |
||||
with warnings.catch_warnings(): |
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning |
||||
y1 = self.m(x) |
||||
y2 = self.m(y1) |
||||
return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1)) |
||||
|
||||
|
||||
class Focus(nn.Module): |
||||
# Focus wh information into c-space |
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups |
||||
super().__init__() |
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act) |
||||
# self.contract = Contract(gain=2) |
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2) |
||||
return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1)) |
||||
# return self.conv(self.contract(x)) |
||||
|
||||
|
||||
class GhostConv(nn.Module): |
||||
# Ghost Convolution https://github.com/huawei-noah/ghostnet |
||||
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups |
||||
super().__init__() |
||||
c_ = c2 // 2 # hidden channels |
||||
self.cv1 = Conv(c1, c_, k, s, None, g, act=act) |
||||
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act) |
||||
|
||||
def forward(self, x): |
||||
y = self.cv1(x) |
||||
return torch.cat((y, self.cv2(y)), 1) |
||||
|
||||
|
||||
class GhostBottleneck(nn.Module): |
||||
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet |
||||
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride |
||||
super().__init__() |
||||
c_ = c2 // 2 |
||||
self.conv = nn.Sequential( |
||||
GhostConv(c1, c_, 1, 1), # pw |
||||
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw |
||||
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear |
||||
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1, |
||||
act=False)) if s == 2 else nn.Identity() |
||||
|
||||
def forward(self, x): |
||||
return self.conv(x) + self.shortcut(x) |
||||
|
||||
|
||||
class Contract(nn.Module): |
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40) |
||||
def __init__(self, gain=2): |
||||
super().__init__() |
||||
self.gain = gain |
||||
|
||||
def forward(self, x): |
||||
b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain' |
||||
s = self.gain |
||||
x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2) |
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40) |
||||
return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40) |
||||
|
||||
|
||||
class Expand(nn.Module): |
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160) |
||||
def __init__(self, gain=2): |
||||
super().__init__() |
||||
self.gain = gain |
||||
|
||||
def forward(self, x): |
||||
b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain' |
||||
s = self.gain |
||||
x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80) |
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2) |
||||
return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160) |
||||
|
||||
|
||||
class Concat(nn.Module): |
||||
# Concatenate a list of tensors along dimension |
||||
def __init__(self, dimension=1): |
||||
super().__init__() |
||||
self.d = dimension |
||||
|
||||
def forward(self, x): |
||||
return torch.cat(x, self.d) |
||||
|
||||
|
||||
class AutoShape(nn.Module): |
||||
# YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS |
||||
conf = 0.25 # NMS confidence threshold |
||||
iou = 0.45 # NMS IoU threshold |
||||
agnostic = False # NMS class-agnostic |
||||
multi_label = False # NMS multiple labels per box |
||||
classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs |
||||
max_det = 1000 # maximum number of detections per image |
||||
amp = False # Automatic Mixed Precision (AMP) inference |
||||
|
||||
def __init__(self, model, verbose=True): |
||||
super().__init__() |
||||
if verbose: |
||||
LOGGER.info('Adding AutoShape... ') |
||||
copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=()) # copy attributes |
||||
self.dmb = isinstance(model, AutoBackend) # DetectMultiBackend() instance |
||||
self.pt = not self.dmb or model.pt # PyTorch model |
||||
self.model = model.eval() |
||||
if self.pt: |
||||
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect() |
||||
m.inplace = False # Detect.inplace=False for safe multithread inference |
||||
m.export = True # do not output loss values |
||||
|
||||
def _apply(self, fn): |
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers |
||||
self = super()._apply(fn) |
||||
if self.pt: |
||||
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect() |
||||
m.stride = fn(m.stride) |
||||
m.grid = list(map(fn, m.grid)) |
||||
if isinstance(m.anchor_grid, list): |
||||
m.anchor_grid = list(map(fn, m.anchor_grid)) |
||||
return self |
||||
|
||||
@smart_inference_mode() |
||||
def forward(self, ims, size=640, augment=False, profile=False): |
||||
# Inference from various sources. For size(height=640, width=1280), RGB images example inputs are: |
||||
# file: ims = '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 |
||||
|
||||
dt = (Profile(), Profile(), Profile()) |
||||
with dt[0]: |
||||
if isinstance(size, int): # expand |
||||
size = (size, size) |
||||
p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device) # param |
||||
autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference |
||||
if isinstance(ims, torch.Tensor): # torch |
||||
with amp.autocast(autocast): |
||||
return self.model(ims.to(p.device).type_as(p), augment=augment) # inference |
||||
|
||||
# Pre-process |
||||
n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims]) # number, list of images |
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames |
||||
for i, im in enumerate(ims): |
||||
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(ImageOps.exif_transpose(im)) |
||||
elif isinstance(im, Image.Image): # PIL Image |
||||
im, f = np.asarray(ImageOps.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 cv2.cvtColor(im, cv2.COLOR_GRAY2BGR) # enforce 3ch input |
||||
s = im.shape[:2] # HWC |
||||
shape0.append(s) # image shape |
||||
g = max(size) / max(s) # gain |
||||
shape1.append([y * g for y in s]) |
||||
ims[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update |
||||
shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] if self.pt else size # inf shape |
||||
x = [LetterBox(shape1, auto=False)(image=im)["img"] for im in ims] # pad |
||||
x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW |
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32 |
||||
|
||||
with amp.autocast(autocast): |
||||
# Inference |
||||
with dt[1]: |
||||
y = self.model(x, augment=augment) # forward |
||||
|
||||
# Post-process |
||||
with dt[2]: |
||||
y = non_max_suppression(y if self.dmb else y[0], |
||||
self.conf, |
||||
self.iou, |
||||
self.classes, |
||||
self.agnostic, |
||||
self.multi_label, |
||||
max_det=self.max_det) # NMS |
||||
for i in range(n): |
||||
scale_boxes(shape1, y[i][:, :4], shape0[i]) |
||||
|
||||
return Detections(ims, y, files, dt, self.names, x.shape) |
||||
|
||||
|
||||
class Detections: |
||||
# YOLOv5 detections class for inference results |
||||
def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None): |
||||
super().__init__() |
||||
d = pred[0].device # device |
||||
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims] # normalizations |
||||
self.ims = ims # list of images as numpy arrays |
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls) |
||||
self.names = names # class names |
||||
self.files = files # image filenames |
||||
self.times = times # profiling times |
||||
self.xyxy = pred # xyxy pixels |
||||
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels |
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized |
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized |
||||
self.n = len(self.pred) # number of images (batch size) |
||||
self.t = tuple(x.t / self.n * 1E3 for x in times) # timestamps (ms) |
||||
self.s = tuple(shape) # inference BCHW shape |
||||
|
||||
def _run(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')): |
||||
s, crops = '', [] |
||||
for i, (im, pred) in enumerate(zip(self.ims, self.pred)): |
||||
s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string |
||||
if pred.shape[0]: |
||||
for c in pred[:, -1].unique(): |
||||
n = (pred[:, -1] == c).sum() # detections per class |
||||
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string |
||||
s = s.rstrip(', ') |
||||
if show or save or render or crop: |
||||
annotator = Annotator(im, example=str(self.names)) |
||||
for *box, conf, cls in reversed(pred): # xyxy, confidence, class |
||||
label = f'{self.names[int(cls)]} {conf:.2f}' |
||||
if crop: |
||||
file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None |
||||
crops.append({ |
||||
'box': box, |
||||
'conf': conf, |
||||
'cls': cls, |
||||
'label': label, |
||||
'im': save_one_box(box, im, file=file, save=save)}) |
||||
else: # all others |
||||
annotator.box_label(box, label if labels else '', color=colors(cls)) |
||||
im = annotator.im |
||||
else: |
||||
s += '(no detections)' |
||||
|
||||
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np |
||||
if show: |
||||
im.show(self.files[i]) # show |
||||
if save: |
||||
f = self.files[i] |
||||
im.save(save_dir / f) # save |
||||
if i == self.n - 1: |
||||
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}") |
||||
if render: |
||||
self.ims[i] = np.asarray(im) |
||||
if pprint: |
||||
s = s.lstrip('\n') |
||||
return f'{s}\nSpeed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {self.s}' % self.t |
||||
if crop: |
||||
if save: |
||||
LOGGER.info(f'Saved results to {save_dir}\n') |
||||
return crops |
||||
|
||||
def show(self, labels=True): |
||||
self._run(show=True, labels=labels) # show results |
||||
|
||||
def save(self, labels=True, save_dir='runs/detect/exp', exist_ok=False): |
||||
save_dir = increment_path(save_dir, exist_ok, mkdir=True) # increment save_dir |
||||
self._run(save=True, labels=labels, save_dir=save_dir) # save results |
||||
|
||||
def crop(self, save=True, save_dir='runs/detect/exp', exist_ok=False): |
||||
save_dir = increment_path(save_dir, exist_ok, mkdir=True) if save else None |
||||
return self._run(crop=True, save=save, save_dir=save_dir) # crop results |
||||
|
||||
def render(self, labels=True): |
||||
self._run(render=True, labels=labels) # render results |
||||
return self.ims |
||||
|
||||
def pandas(self): |
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0]) |
||||
new = copy(self) # return copy |
||||
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns |
||||
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns |
||||
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]): |
||||
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update |
||||
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a]) |
||||
return new |
||||
|
||||
def tolist(self): |
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():' |
||||
r = range(self.n) # iterable |
||||
x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r] |
||||
# for d in x: |
||||
# for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']: |
||||
# setattr(d, k, getattr(d, k)[0]) # pop out of list |
||||
return x |
||||
|
||||
def print(self): |
||||
LOGGER.info(self.__str__()) |
||||
|
||||
def __len__(self): # override len(results) |
||||
return self.n |
||||
|
||||
def __str__(self): # override print(results) |
||||
return self._run(pprint=True) # print results |
||||
|
||||
def __repr__(self): |
||||
return f'YOLOv5 {self.__class__} instance\n' + self.__str__() |
||||
|
||||
|
||||
class Proto(nn.Module): |
||||
# YOLOv5 mask Proto module for segmentation models |
||||
def __init__(self, c1, c_=256, c2=32): # ch_in, number of protos, number of masks |
||||
super().__init__() |
||||
self.cv1 = Conv(c1, c_, k=3) |
||||
self.upsample = nn.Upsample(scale_factor=2, mode='nearest') |
||||
self.cv2 = Conv(c_, c_, k=3) |
||||
self.cv3 = Conv(c_, c2) |
||||
|
||||
def forward(self, x): |
||||
return self.cv3(self.cv2(self.upsample(self.cv1(x)))) |
||||
|
||||
|
||||
class Ensemble(nn.ModuleList): |
||||
# Ensemble of models |
||||
def __init__(self): |
||||
super().__init__() |
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False): |
||||
y = [module(x, augment, profile, visualize)[0] for module in self] |
||||
# y = torch.stack(y).max(0)[0] # max ensemble |
||||
# y = torch.stack(y).mean(0) # mean ensemble |
||||
y = torch.cat(y, 1) # nms ensemble |
||||
return y, None # inference, train output |
||||
|
||||
|
||||
# heads |
||||
class Detect(nn.Module): |
||||
# YOLOv5 Detect head for detection models |
||||
stride = None # strides computed during build |
||||
dynamic = False # force grid reconstruction |
||||
export = False # export mode |
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer |
||||
super().__init__() |
||||
self.nc = nc # number of classes |
||||
self.no = nc + 5 # number of outputs per anchor |
||||
self.nl = len(anchors) # number of detection layers |
||||
self.na = len(anchors[0]) // 2 # number of anchors |
||||
self.grid = [torch.empty(0) for _ in range(self.nl)] # init grid |
||||
self.anchor_grid = [torch.empty(0) for _ in range(self.nl)] # init anchor grid |
||||
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2) |
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv |
||||
self.inplace = inplace # use inplace ops (e.g. slice assignment) |
||||
|
||||
def forward(self, x): |
||||
z = [] # inference output |
||||
for i in range(self.nl): |
||||
x[i] = self.m[i](x[i]) # conv |
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85) |
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous() |
||||
|
||||
if not self.training: # inference |
||||
if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]: |
||||
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i) |
||||
|
||||
if isinstance(self, Segment): # (boxes + masks) |
||||
xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4) |
||||
xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i] # xy |
||||
wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i] # wh |
||||
y = torch.cat((xy, wh, conf.sigmoid(), mask), 4) |
||||
else: # Detect (boxes only) |
||||
xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4) |
||||
xy = (xy * 2 + self.grid[i]) * self.stride[i] # xy |
||||
wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh |
||||
y = torch.cat((xy, wh, conf), 4) |
||||
z.append(y.view(bs, self.na * nx * ny, self.no)) |
||||
|
||||
return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x) |
||||
|
||||
def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')): |
||||
d = self.anchors[i].device |
||||
t = self.anchors[i].dtype |
||||
shape = 1, self.na, ny, nx, 2 # grid shape |
||||
y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t) |
||||
yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibility |
||||
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5 |
||||
anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape) |
||||
return grid, anchor_grid |
||||
|
||||
|
||||
class Segment(Detect): |
||||
# YOLOv5 Segment head for segmentation models |
||||
def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True): |
||||
super().__init__(nc, anchors, ch, inplace) |
||||
self.nm = nm # number of masks |
||||
self.npr = npr # number of protos |
||||
self.no = 5 + nc + self.nm # number of outputs per anchor |
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv |
||||
self.proto = Proto(ch[0], self.npr, self.nm) # protos |
||||
self.detect = Detect.forward |
||||
|
||||
def forward(self, x): |
||||
p = self.proto(x[0]) |
||||
x = self.detect(self, x) |
||||
return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1]) |
||||
|
||||
|
||||
class Classify(nn.Module): |
||||
# YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2) |
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups |
||||
super().__init__() |
||||
c_ = 1280 # efficientnet_b0 size |
||||
self.conv = Conv(c1, c_, k, s, autopad(k, p), g) |
||||
self.pool = nn.AdaptiveAvgPool2d(1) # to x(b,c_,1,1) |
||||
self.drop = nn.Dropout(p=0.0, inplace=True) |
||||
self.linear = nn.Linear(c_, c2) # to x(b,c2) |
||||
|
||||
def forward(self, x): |
||||
if isinstance(x, list): |
||||
x = torch.cat(x, 1) |
||||
return self.linear(self.drop(self.pool(self.conv(x)).flatten(1))) |
||||
@ -0,0 +1,199 @@ |
||||
import time |
||||
from copy import deepcopy |
||||
|
||||
import thop |
||||
import torch.nn as nn |
||||
|
||||
from ultralytics.yolo.utils import LOGGER |
||||
from ultralytics.yolo.utils.anchors import check_anchor_order |
||||
from ultralytics.yolo.utils.modeling import parse_model |
||||
from ultralytics.yolo.utils.modeling.modules import * |
||||
from ultralytics.yolo.utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, time_sync |
||||
|
||||
|
||||
class BaseModel(nn.Module): |
||||
# YOLOv5 base model |
||||
def forward(self, x, profile=False, visualize=False): |
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train |
||||
|
||||
def _forward_once(self, x, profile=False, visualize=False): |
||||
y, dt = [], [] # outputs |
||||
for m in self.model: |
||||
if m.f != -1: # if not from previous layer |
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers |
||||
if profile: |
||||
self._profile_one_layer(m, x, dt) |
||||
x = m(x) # run |
||||
y.append(x if m.i in self.save else None) # save output |
||||
if visualize: |
||||
pass |
||||
# TODO: feature_visualization(x, m.type, m.i, save_dir=visualize) |
||||
return x |
||||
|
||||
def _profile_one_layer(self, m, x, dt): |
||||
c = m == self.model[-1] # is final layer, copy input as inplace fix |
||||
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs |
||||
t = time_sync() |
||||
for _ in range(10): |
||||
m(x.copy() if c else x) |
||||
dt.append((time_sync() - t) * 100) |
||||
if m == self.model[0]: |
||||
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module") |
||||
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}') |
||||
if c: |
||||
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") |
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers |
||||
LOGGER.info('Fusing layers... ') |
||||
for m in self.model.modules(): |
||||
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'): |
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv |
||||
delattr(m, 'bn') # remove batchnorm |
||||
m.forward = m.forward_fuse # update forward |
||||
self.info() |
||||
return self |
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information |
||||
model_info(self, verbose, img_size) |
||||
|
||||
def _apply(self, fn): |
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers |
||||
self = super()._apply(fn) |
||||
m = self.model[-1] # Detect() |
||||
if isinstance(m, (Detect, Segment)): |
||||
m.stride = fn(m.stride) |
||||
m.grid = list(map(fn, m.grid)) |
||||
if isinstance(m.anchor_grid, list): |
||||
m.anchor_grid = list(map(fn, m.anchor_grid)) |
||||
return self |
||||
|
||||
|
||||
class DetectionModel(BaseModel): |
||||
# YOLO detection model |
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of 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, encoding='ascii', errors='ignore') as f: |
||||
self.yaml = yaml.safe_load(f) # model dict |
||||
|
||||
# Define model |
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels |
||||
if nc and nc != self.yaml['nc']: |
||||
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") |
||||
self.yaml['nc'] = nc # override yaml value |
||||
if anchors: |
||||
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}') |
||||
self.yaml['anchors'] = round(anchors) # override yaml value |
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist |
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names |
||||
self.inplace = self.yaml.get('inplace', True) |
||||
|
||||
# Build strides, anchors |
||||
m = self.model[-1] # Detect() |
||||
if isinstance(m, (Detect, Segment)): |
||||
s = 256 # 2x min stride |
||||
m.inplace = self.inplace |
||||
forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x) |
||||
m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward |
||||
check_anchor_order(m) |
||||
m.anchors /= m.stride.view(-1, 1, 1) |
||||
self.stride = m.stride |
||||
self._initialize_biases() # only run once |
||||
|
||||
# Init weights, biases |
||||
initialize_weights(self) |
||||
self.info() |
||||
LOGGER.info('') |
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False): |
||||
if augment: |
||||
return self._forward_augment(x) # augmented inference, None |
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train |
||||
|
||||
def _forward_augment(self, x): |
||||
img_size = x.shape[-2:] # height, width |
||||
s = [1, 0.83, 0.67] # scales |
||||
f = [None, 3, None] # flips (2-ud, 3-lr) |
||||
y = [] # outputs |
||||
for si, fi in zip(s, f): |
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max())) |
||||
yi = self._forward_once(xi)[0] # forward |
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save |
||||
yi = self._descale_pred(yi, fi, si, img_size) |
||||
y.append(yi) |
||||
y = self._clip_augmented(y) # clip augmented tails |
||||
return torch.cat(y, 1), None # augmented inference, train |
||||
|
||||
def _descale_pred(self, p, flips, scale, img_size): |
||||
# de-scale predictions following augmented inference (inverse operation) |
||||
if self.inplace: |
||||
p[..., :4] /= scale # de-scale |
||||
if flips == 2: |
||||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud |
||||
elif flips == 3: |
||||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr |
||||
else: |
||||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale |
||||
if flips == 2: |
||||
y = img_size[0] - y # de-flip ud |
||||
elif flips == 3: |
||||
x = img_size[1] - x # de-flip lr |
||||
p = torch.cat((x, y, wh, p[..., 4:]), -1) |
||||
return p |
||||
|
||||
def _clip_augmented(self, y): |
||||
# Clip YOLOv5 augmented inference tails |
||||
nl = self.model[-1].nl # number of detection layers (P3-P5) |
||||
g = sum(4 ** x for x in range(nl)) # grid points |
||||
e = 1 # exclude layer count |
||||
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices |
||||
y[0] = y[0][:, :-i] # large |
||||
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices |
||||
y[-1] = y[-1][:, i:] # small |
||||
return y |
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency |
||||
# https://arxiv.org/abs/1708.02002 section 3.3 |
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1. |
||||
m = self.model[-1] # Detect() module |
||||
for mi, s in zip(m.m, m.stride): # from |
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85) |
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image) |
||||
b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum()) # cls |
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True) |
||||
|
||||
|
||||
class SegmentationModel(DetectionModel): |
||||
# YOLOv5 segmentation model |
||||
def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None): |
||||
super().__init__(cfg, ch, nc, anchors) |
||||
|
||||
|
||||
class ClassificationModel(BaseModel): |
||||
# YOLOv5 classification model |
||||
def __init__(self, cfg=None, model=None, nc=1000, cutoff=10): # yaml, model, number of classes, cutoff index |
||||
super().__init__() |
||||
self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg) |
||||
|
||||
def _from_detection_model(self, model, nc=1000, cutoff=10): |
||||
# Create a YOLOv5 classification model from a YOLOv5 detection model |
||||
if isinstance(model, AutoBackend): |
||||
model = model.model # unwrap DetectMultiBackend |
||||
model.model = model.model[:cutoff] # backbone |
||||
m = model.model[-1] # last layer |
||||
ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels # ch into module |
||||
c = Classify(ch, nc) # Classify() |
||||
c.i, c.f, c.type = m.i, m.f, 'models.common.Classify' # index, from, type |
||||
model.model[-1] = c # replace |
||||
self.model = model.model |
||||
self.stride = model.stride |
||||
self.save = [] |
||||
self.nc = nc |
||||
|
||||
def _from_yaml(self, cfg): |
||||
# Create a YOLOv5 classification model from a *.yaml file |
||||
self.model = None |
||||
@ -0,0 +1,181 @@ |
||||
from pathlib import Path |
||||
from urllib.error import URLError |
||||
|
||||
import cv2 |
||||
import numpy as np |
||||
import torch |
||||
from PIL import Image, ImageDraw, ImageFont |
||||
|
||||
from ultralytics.yolo.utils import CONFIG_DIR, FONT |
||||
|
||||
from .checks import check_font, check_requirements, is_ascii |
||||
from .files import increment_path |
||||
from .ops import clip_coords, scale_image, xywh2xyxy, xyxy2xywh |
||||
|
||||
|
||||
class Colors: |
||||
# Ultralytics color palette https://ultralytics.com/ |
||||
def __init__(self): |
||||
# hex = matplotlib.colors.TABLEAU_COLORS.values() |
||||
hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB', |
||||
'2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7') |
||||
self.palette = [self.hex2rgb(f'#{c}') for c in hexs] |
||||
self.n = len(self.palette) |
||||
|
||||
def __call__(self, i, bgr=False): |
||||
c = self.palette[int(i) % self.n] |
||||
return (c[2], c[1], c[0]) if bgr else c |
||||
|
||||
@staticmethod |
||||
def hex2rgb(h): # rgb order (PIL) |
||||
return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) |
||||
|
||||
|
||||
colors = Colors() # create instance for 'from utils.plots import colors' |
||||
|
||||
|
||||
class Annotator: |
||||
# YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations |
||||
def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): |
||||
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' |
||||
non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic |
||||
self.pil = pil or non_ascii |
||||
if self.pil: # use PIL |
||||
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) |
||||
self.draw = ImageDraw.Draw(self.im) |
||||
self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font, |
||||
size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) |
||||
else: # use cv2 |
||||
self.im = im |
||||
self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width |
||||
|
||||
def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): |
||||
# Add one xyxy box to image with label |
||||
if self.pil or not is_ascii(label): |
||||
self.draw.rectangle(box, width=self.lw, outline=color) # box |
||||
if label: |
||||
w, h = self.font.getsize(label) # text width, height |
||||
outside = box[1] - h >= 0 # label fits outside box |
||||
self.draw.rectangle( |
||||
(box[0], box[1] - h if outside else box[1], box[0] + w + 1, |
||||
box[1] + 1 if outside else box[1] + h + 1), |
||||
fill=color, |
||||
) |
||||
# self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 |
||||
self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) |
||||
else: # cv2 |
||||
p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) |
||||
cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) |
||||
if label: |
||||
tf = max(self.lw - 1, 1) # font thickness |
||||
w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height |
||||
outside = p1[1] - h >= 3 |
||||
p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 |
||||
cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled |
||||
cv2.putText(self.im, |
||||
label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), |
||||
0, |
||||
self.lw / 3, |
||||
txt_color, |
||||
thickness=tf, |
||||
lineType=cv2.LINE_AA) |
||||
|
||||
def masks(self, masks, colors, im_gpu=None, alpha=0.5): |
||||
"""Plot masks at once. |
||||
Args: |
||||
masks (tensor): predicted masks on cuda, shape: [n, h, w] |
||||
colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n] |
||||
im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1] |
||||
alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque |
||||
""" |
||||
if self.pil: |
||||
# convert to numpy first |
||||
self.im = np.asarray(self.im).copy() |
||||
if im_gpu is None: |
||||
# Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...) |
||||
if len(masks) == 0: |
||||
return |
||||
if isinstance(masks, torch.Tensor): |
||||
masks = torch.as_tensor(masks, dtype=torch.uint8) |
||||
masks = masks.permute(1, 2, 0).contiguous() |
||||
masks = masks.cpu().numpy() |
||||
# masks = np.ascontiguousarray(masks.transpose(1, 2, 0)) |
||||
masks = scale_image(masks.shape[:2], masks, self.im.shape) |
||||
masks = np.asarray(masks, dtype=np.float32) |
||||
colors = np.asarray(colors, dtype=np.float32) # shape(n,3) |
||||
s = masks.sum(2, keepdims=True).clip(0, 1) # add all masks together |
||||
masks = (masks @ colors).clip(0, 255) # (h,w,n) @ (n,3) = (h,w,3) |
||||
self.im[:] = masks * alpha + self.im * (1 - s * alpha) |
||||
else: |
||||
if len(masks) == 0: |
||||
self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 |
||||
colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0 |
||||
colors = colors[:, None, None] # shape(n,1,1,3) |
||||
masks = masks.unsqueeze(3) # shape(n,h,w,1) |
||||
masks_color = masks * (colors * alpha) # shape(n,h,w,3) |
||||
|
||||
inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) |
||||
mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3) |
||||
|
||||
im_gpu = im_gpu.flip(dims=[0]) # flip channel |
||||
im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) |
||||
im_gpu = im_gpu * inv_alph_masks[-1] + mcs |
||||
im_mask = (im_gpu * 255).byte().cpu().numpy() |
||||
self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape) |
||||
if self.pil: |
||||
# convert im back to PIL and update draw |
||||
self.fromarray(self.im) |
||||
|
||||
def rectangle(self, xy, fill=None, outline=None, width=1): |
||||
# Add rectangle to image (PIL-only) |
||||
self.draw.rectangle(xy, fill, outline, width) |
||||
|
||||
def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'): |
||||
# Add text to image (PIL-only) |
||||
if anchor == 'bottom': # start y from font bottom |
||||
w, h = self.font.getsize(text) # text width, height |
||||
xy[1] += 1 - h |
||||
self.draw.text(xy, text, fill=txt_color, font=self.font) |
||||
|
||||
def fromarray(self, im): |
||||
# Update self.im from a numpy array |
||||
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) |
||||
self.draw = ImageDraw.Draw(self.im) |
||||
|
||||
def result(self): |
||||
# Return annotated image as array |
||||
return np.asarray(self.im) |
||||
|
||||
|
||||
def check_pil_font(font=FONT, size=10): |
||||
# Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary |
||||
font = Path(font) |
||||
font = font if font.exists() else (CONFIG_DIR / font.name) |
||||
try: |
||||
return ImageFont.truetype(str(font) if font.exists() else font.name, size) |
||||
except Exception: # download if missing |
||||
try: |
||||
check_font(font) |
||||
return ImageFont.truetype(str(font), size) |
||||
except TypeError: |
||||
check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374 |
||||
except URLError: # not online |
||||
return ImageFont.load_default() |
||||
|
||||
|
||||
def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True): |
||||
# Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop |
||||
xyxy = torch.tensor(xyxy).view(-1, 4) |
||||
b = xyxy2xywh(xyxy) # boxes |
||||
if square: |
||||
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square |
||||
b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad |
||||
xyxy = xywh2xyxy(b).long() |
||||
clip_coords(xyxy, im.shape) |
||||
crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)] |
||||
if save: |
||||
file.parent.mkdir(parents=True, exist_ok=True) # make directory |
||||
f = str(increment_path(file).with_suffix('.jpg')) |
||||
# cv2.imwrite(f, crop) # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue |
||||
Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0) # save RGB |
||||
return crop |
||||
Loading…
Reference in new issue