完成训练模块的转移
This commit is contained in:
241
yolov5/classify/predict.py
Normal file
241
yolov5/classify/predict.py
Normal file
@ -0,0 +1,241 @@
|
||||
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
||||
"""
|
||||
Run YOLOv5 classification inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
|
||||
|
||||
Usage - sources:
|
||||
$ python classify/predict.py --weights yolov5s-cls.pt --source 0 # webcam
|
||||
img.jpg # image
|
||||
vid.mp4 # video
|
||||
screen # screenshot
|
||||
path/ # directory
|
||||
list.txt # list of images
|
||||
list.streams # list of streams
|
||||
'path/*.jpg' # glob
|
||||
'https://youtu.be/LNwODJXcvt4' # YouTube
|
||||
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
|
||||
|
||||
Usage - formats:
|
||||
$ python classify/predict.py --weights yolov5s-cls.pt # PyTorch
|
||||
yolov5s-cls.torchscript # TorchScript
|
||||
yolov5s-cls.onnx # ONNX Runtime or OpenCV DNN with --dnn
|
||||
yolov5s-cls_openvino_model # OpenVINO
|
||||
yolov5s-cls.engine # TensorRT
|
||||
yolov5s-cls.mlmodel # CoreML (macOS-only)
|
||||
yolov5s-cls_saved_model # TensorFlow SavedModel
|
||||
yolov5s-cls.pb # TensorFlow GraphDef
|
||||
yolov5s-cls.tflite # TensorFlow Lite
|
||||
yolov5s-cls_edgetpu.tflite # TensorFlow Edge TPU
|
||||
yolov5s-cls_paddle_model # PaddlePaddle
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from ultralytics.utils.plotting import Annotator
|
||||
|
||||
from models.common import DetectMultiBackend
|
||||
from utils.augmentations import classify_transforms
|
||||
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
|
||||
from utils.general import (
|
||||
LOGGER,
|
||||
Profile,
|
||||
check_file,
|
||||
check_img_size,
|
||||
check_imshow,
|
||||
check_requirements,
|
||||
colorstr,
|
||||
cv2,
|
||||
increment_path,
|
||||
print_args,
|
||||
strip_optimizer,
|
||||
)
|
||||
from utils.torch_utils import select_device, smart_inference_mode
|
||||
|
||||
|
||||
@smart_inference_mode()
|
||||
def run(
|
||||
weights=ROOT / "yolov5s-cls.pt", # model.pt path(s)
|
||||
source=ROOT / "data/images", # file/dir/URL/glob/screen/0(webcam)
|
||||
data=ROOT / "data/coco128.yaml", # dataset.yaml path
|
||||
imgsz=(224, 224), # inference size (height, width)
|
||||
device="", # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
view_img=False, # show results
|
||||
save_txt=False, # save results to *.txt
|
||||
nosave=False, # do not save images/videos
|
||||
augment=False, # augmented inference
|
||||
visualize=False, # visualize features
|
||||
update=False, # update all models
|
||||
project=ROOT / "runs/predict-cls", # save results to project/name
|
||||
name="exp", # save results to project/name
|
||||
exist_ok=False, # existing project/name ok, do not increment
|
||||
half=False, # use FP16 half-precision inference
|
||||
dnn=False, # use OpenCV DNN for ONNX inference
|
||||
vid_stride=1, # video frame-rate stride
|
||||
):
|
||||
"""Conducts YOLOv5 classification inference on diverse input sources and saves results."""
|
||||
source = str(source)
|
||||
save_img = not nosave and not source.endswith(".txt") # save inference images
|
||||
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
|
||||
is_url = source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://"))
|
||||
webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
|
||||
screenshot = source.lower().startswith("screen")
|
||||
if is_url and is_file:
|
||||
source = check_file(source) # download
|
||||
|
||||
# Directories
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
(save_dir / "labels" if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Load model
|
||||
device = select_device(device)
|
||||
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
|
||||
stride, names, pt = model.stride, model.names, model.pt
|
||||
imgsz = check_img_size(imgsz, s=stride) # check image size
|
||||
|
||||
# Dataloader
|
||||
bs = 1 # batch_size
|
||||
if webcam:
|
||||
view_img = check_imshow(warn=True)
|
||||
dataset = LoadStreams(source, img_size=imgsz, transforms=classify_transforms(imgsz[0]), vid_stride=vid_stride)
|
||||
bs = len(dataset)
|
||||
elif screenshot:
|
||||
dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
else:
|
||||
dataset = LoadImages(source, img_size=imgsz, transforms=classify_transforms(imgsz[0]), vid_stride=vid_stride)
|
||||
vid_path, vid_writer = [None] * bs, [None] * bs
|
||||
|
||||
# Run inference
|
||||
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
|
||||
seen, windows, dt = 0, [], (Profile(device=device), Profile(device=device), Profile(device=device))
|
||||
for path, im, im0s, vid_cap, s in dataset:
|
||||
with dt[0]:
|
||||
im = torch.Tensor(im).to(model.device)
|
||||
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
|
||||
if len(im.shape) == 3:
|
||||
im = im[None] # expand for batch dim
|
||||
|
||||
# Inference
|
||||
with dt[1]:
|
||||
results = model(im)
|
||||
|
||||
# Post-process
|
||||
with dt[2]:
|
||||
pred = F.softmax(results, dim=1) # probabilities
|
||||
|
||||
# Process predictions
|
||||
for i, prob in enumerate(pred): # per image
|
||||
seen += 1
|
||||
if webcam: # batch_size >= 1
|
||||
p, im0, frame = path[i], im0s[i].copy(), dataset.count
|
||||
s += f"{i}: "
|
||||
else:
|
||||
p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0)
|
||||
|
||||
p = Path(p) # to Path
|
||||
save_path = str(save_dir / p.name) # im.jpg
|
||||
txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}") # im.txt
|
||||
|
||||
s += "{:g}x{:g} ".format(*im.shape[2:]) # print string
|
||||
annotator = Annotator(im0, example=str(names), pil=True)
|
||||
|
||||
# Print results
|
||||
top5i = prob.argsort(0, descending=True)[:5].tolist() # top 5 indices
|
||||
s += f"{', '.join(f'{names[j]} {prob[j]:.2f}' for j in top5i)}, "
|
||||
|
||||
# Write results
|
||||
text = "\n".join(f"{prob[j]:.2f} {names[j]}" for j in top5i)
|
||||
if save_img or view_img: # Add bbox to image
|
||||
annotator.text([32, 32], text, txt_color=(255, 255, 255))
|
||||
if save_txt: # Write to file
|
||||
with open(f"{txt_path}.txt", "a") as f:
|
||||
f.write(text + "\n")
|
||||
|
||||
# Stream results
|
||||
im0 = annotator.result()
|
||||
if view_img:
|
||||
if platform.system() == "Linux" and p not in windows:
|
||||
windows.append(p)
|
||||
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
||||
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(1) # 1 millisecond
|
||||
|
||||
# Save results (image with detections)
|
||||
if save_img:
|
||||
if dataset.mode == "image":
|
||||
cv2.imwrite(save_path, im0)
|
||||
else: # 'video' or 'stream'
|
||||
if vid_path[i] != save_path: # new video
|
||||
vid_path[i] = save_path
|
||||
if isinstance(vid_writer[i], cv2.VideoWriter):
|
||||
vid_writer[i].release() # release previous video writer
|
||||
if vid_cap: # video
|
||||
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
||||
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
else: # stream
|
||||
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
||||
save_path = str(Path(save_path).with_suffix(".mp4")) # force *.mp4 suffix on results videos
|
||||
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
|
||||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f"{s}{dt[1].dt * 1e3:.1f}ms")
|
||||
|
||||
# Print results
|
||||
t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image
|
||||
LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" % t)
|
||||
if save_txt or save_img:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ""
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
|
||||
if update:
|
||||
strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)
|
||||
|
||||
|
||||
def parse_opt():
|
||||
"""Parses command line arguments for YOLOv5 inference settings including model, source, device, and image size."""
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s-cls.pt", help="model path(s)")
|
||||
parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)")
|
||||
parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="(optional) dataset.yaml path")
|
||||
parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[224], help="inference size h,w")
|
||||
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
|
||||
parser.add_argument("--view-img", action="store_true", help="show results")
|
||||
parser.add_argument("--save-txt", action="store_true", help="save results to *.txt")
|
||||
parser.add_argument("--nosave", action="store_true", help="do not save images/videos")
|
||||
parser.add_argument("--augment", action="store_true", help="augmented inference")
|
||||
parser.add_argument("--visualize", action="store_true", help="visualize features")
|
||||
parser.add_argument("--update", action="store_true", help="update all models")
|
||||
parser.add_argument("--project", default=ROOT / "runs/predict-cls", help="save results to project/name")
|
||||
parser.add_argument("--name", default="exp", help="save results to project/name")
|
||||
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
|
||||
parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
|
||||
parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
|
||||
parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
"""Executes YOLOv5 model inference with options for ONNX DNN and video frame-rate stride adjustments."""
|
||||
check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop"))
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
382
yolov5/classify/train.py
Normal file
382
yolov5/classify/train.py
Normal file
@ -0,0 +1,382 @@
|
||||
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
||||
"""
|
||||
Train a YOLOv5 classifier model on a classification dataset.
|
||||
|
||||
Usage - Single-GPU training:
|
||||
$ python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224
|
||||
|
||||
Usage - Multi-GPU DDP training:
|
||||
$ python -m torch.distributed.run --nproc_per_node 4 --master_port 2022 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3
|
||||
|
||||
Datasets: --data mnist, fashion-mnist, cifar10, cifar100, imagenette, imagewoof, imagenet, or 'path/to/data'
|
||||
YOLOv5-cls models: --model yolov5n-cls.pt, yolov5s-cls.pt, yolov5m-cls.pt, yolov5l-cls.pt, yolov5x-cls.pt
|
||||
Torchvision models: --model resnet50, efficientnet_b0, etc. See https://pytorch.org/vision/stable/models.html
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from copy import deepcopy
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.distributed as dist
|
||||
import torch.hub as hub
|
||||
import torch.optim.lr_scheduler as lr_scheduler
|
||||
import torchvision
|
||||
from torch.cuda import amp
|
||||
from tqdm import tqdm
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from classify import val as validate
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import ClassificationModel, DetectionModel
|
||||
from utils.dataloaders import create_classification_dataloader
|
||||
from utils.general import (
|
||||
DATASETS_DIR,
|
||||
LOGGER,
|
||||
TQDM_BAR_FORMAT,
|
||||
WorkingDirectory,
|
||||
check_git_info,
|
||||
check_git_status,
|
||||
check_requirements,
|
||||
colorstr,
|
||||
download,
|
||||
increment_path,
|
||||
init_seeds,
|
||||
print_args,
|
||||
yaml_save,
|
||||
)
|
||||
from utils.loggers import GenericLogger
|
||||
from utils.plots import imshow_cls
|
||||
from utils.torch_utils import (
|
||||
ModelEMA,
|
||||
de_parallel,
|
||||
model_info,
|
||||
reshape_classifier_output,
|
||||
select_device,
|
||||
smart_DDP,
|
||||
smart_optimizer,
|
||||
smartCrossEntropyLoss,
|
||||
torch_distributed_zero_first,
|
||||
)
|
||||
|
||||
LOCAL_RANK = int(os.getenv("LOCAL_RANK", -1)) # https://pytorch.org/docs/stable/elastic/run.html
|
||||
RANK = int(os.getenv("RANK", -1))
|
||||
WORLD_SIZE = int(os.getenv("WORLD_SIZE", 1))
|
||||
GIT_INFO = check_git_info()
|
||||
|
||||
|
||||
def train(opt, device):
|
||||
"""Trains a YOLOv5 model, managing datasets, model optimization, logging, and saving checkpoints."""
|
||||
init_seeds(opt.seed + 1 + RANK, deterministic=True)
|
||||
save_dir, data, bs, epochs, nw, imgsz, pretrained = (
|
||||
opt.save_dir,
|
||||
Path(opt.data),
|
||||
opt.batch_size,
|
||||
opt.epochs,
|
||||
min(os.cpu_count() - 1, opt.workers),
|
||||
opt.imgsz,
|
||||
str(opt.pretrained).lower() == "true",
|
||||
)
|
||||
cuda = device.type != "cpu"
|
||||
|
||||
# Directories
|
||||
wdir = save_dir / "weights"
|
||||
wdir.mkdir(parents=True, exist_ok=True) # make dir
|
||||
last, best = wdir / "last.pt", wdir / "best.pt"
|
||||
|
||||
# Save run settings
|
||||
yaml_save(save_dir / "opt.yaml", vars(opt))
|
||||
|
||||
# Logger
|
||||
logger = GenericLogger(opt=opt, console_logger=LOGGER) if RANK in {-1, 0} else None
|
||||
|
||||
# Download Dataset
|
||||
with torch_distributed_zero_first(LOCAL_RANK), WorkingDirectory(ROOT):
|
||||
data_dir = data if data.is_dir() else (DATASETS_DIR / data)
|
||||
if not data_dir.is_dir():
|
||||
LOGGER.info(f"\nDataset not found ⚠️, missing path {data_dir}, attempting download...")
|
||||
t = time.time()
|
||||
if str(data) == "imagenet":
|
||||
subprocess.run(["bash", str(ROOT / "data/scripts/get_imagenet.sh")], shell=True, check=True)
|
||||
else:
|
||||
url = f"https://github.com/ultralytics/assets/releases/download/v0.0.0/{data}.zip"
|
||||
download(url, dir=data_dir.parent)
|
||||
s = f"Dataset download success ✅ ({time.time() - t:.1f}s), saved to {colorstr('bold', data_dir)}\n"
|
||||
LOGGER.info(s)
|
||||
|
||||
# Dataloaders
|
||||
nc = len([x for x in (data_dir / "train").glob("*") if x.is_dir()]) # number of classes
|
||||
trainloader = create_classification_dataloader(
|
||||
path=data_dir / "train",
|
||||
imgsz=imgsz,
|
||||
batch_size=bs // WORLD_SIZE,
|
||||
augment=True,
|
||||
cache=opt.cache,
|
||||
rank=LOCAL_RANK,
|
||||
workers=nw,
|
||||
)
|
||||
|
||||
test_dir = data_dir / "test" if (data_dir / "test").exists() else data_dir / "val" # data/test or data/val
|
||||
if RANK in {-1, 0}:
|
||||
testloader = create_classification_dataloader(
|
||||
path=test_dir,
|
||||
imgsz=imgsz,
|
||||
batch_size=bs // WORLD_SIZE * 2,
|
||||
augment=False,
|
||||
cache=opt.cache,
|
||||
rank=-1,
|
||||
workers=nw,
|
||||
)
|
||||
|
||||
# Model
|
||||
with torch_distributed_zero_first(LOCAL_RANK), WorkingDirectory(ROOT):
|
||||
if Path(opt.model).is_file() or opt.model.endswith(".pt"):
|
||||
model = attempt_load(opt.model, device="cpu", fuse=False)
|
||||
elif opt.model in torchvision.models.__dict__: # TorchVision models i.e. resnet50, efficientnet_b0
|
||||
model = torchvision.models.__dict__[opt.model](weights="IMAGENET1K_V1" if pretrained else None)
|
||||
else:
|
||||
m = hub.list("ultralytics/yolov5") # + hub.list('pytorch/vision') # models
|
||||
raise ModuleNotFoundError(f"--model {opt.model} not found. Available models are: \n" + "\n".join(m))
|
||||
if isinstance(model, DetectionModel):
|
||||
LOGGER.warning("WARNING ⚠️ pass YOLOv5 classifier model with '-cls' suffix, i.e. '--model yolov5s-cls.pt'")
|
||||
model = ClassificationModel(model=model, nc=nc, cutoff=opt.cutoff or 10) # convert to classification model
|
||||
reshape_classifier_output(model, nc) # update class count
|
||||
for m in model.modules():
|
||||
if not pretrained and hasattr(m, "reset_parameters"):
|
||||
m.reset_parameters()
|
||||
if isinstance(m, torch.nn.Dropout) and opt.dropout is not None:
|
||||
m.p = opt.dropout # set dropout
|
||||
for p in model.parameters():
|
||||
p.requires_grad = True # for training
|
||||
model = model.to(device)
|
||||
|
||||
# Info
|
||||
if RANK in {-1, 0}:
|
||||
model.names = trainloader.dataset.classes # attach class names
|
||||
model.transforms = testloader.dataset.torch_transforms # attach inference transforms
|
||||
model_info(model)
|
||||
if opt.verbose:
|
||||
LOGGER.info(model)
|
||||
images, labels = next(iter(trainloader))
|
||||
file = imshow_cls(images[:25], labels[:25], names=model.names, f=save_dir / "train_images.jpg")
|
||||
logger.log_images(file, name="Train Examples")
|
||||
logger.log_graph(model, imgsz) # log model
|
||||
|
||||
# Optimizer
|
||||
optimizer = smart_optimizer(model, opt.optimizer, opt.lr0, momentum=0.9, decay=opt.decay)
|
||||
|
||||
# Scheduler
|
||||
lrf = 0.01 # final lr (fraction of lr0)
|
||||
|
||||
# lf = lambda x: ((1 + math.cos(x * math.pi / epochs)) / 2) * (1 - lrf) + lrf # cosine
|
||||
def lf(x):
|
||||
"""Linear learning rate scheduler function, scaling learning rate from initial value to `lrf` over `epochs`."""
|
||||
return (1 - x / epochs) * (1 - lrf) + lrf # linear
|
||||
|
||||
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
|
||||
# scheduler = lr_scheduler.OneCycleLR(optimizer, max_lr=lr0, total_steps=epochs, pct_start=0.1,
|
||||
# final_div_factor=1 / 25 / lrf)
|
||||
|
||||
# EMA
|
||||
ema = ModelEMA(model) if RANK in {-1, 0} else None
|
||||
|
||||
# DDP mode
|
||||
if cuda and RANK != -1:
|
||||
model = smart_DDP(model)
|
||||
|
||||
# Train
|
||||
t0 = time.time()
|
||||
criterion = smartCrossEntropyLoss(label_smoothing=opt.label_smoothing) # loss function
|
||||
best_fitness = 0.0
|
||||
scaler = amp.GradScaler(enabled=cuda)
|
||||
val = test_dir.stem # 'val' or 'test'
|
||||
LOGGER.info(
|
||||
f"Image sizes {imgsz} train, {imgsz} test\n"
|
||||
f"Using {nw * WORLD_SIZE} dataloader workers\n"
|
||||
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||||
f"Starting {opt.model} training on {data} dataset with {nc} classes for {epochs} epochs...\n\n"
|
||||
f"{'Epoch':>10}{'GPU_mem':>10}{'train_loss':>12}{f'{val}_loss':>12}{'top1_acc':>12}{'top5_acc':>12}"
|
||||
)
|
||||
for epoch in range(epochs): # loop over the dataset multiple times
|
||||
tloss, vloss, fitness = 0.0, 0.0, 0.0 # train loss, val loss, fitness
|
||||
model.train()
|
||||
if RANK != -1:
|
||||
trainloader.sampler.set_epoch(epoch)
|
||||
pbar = enumerate(trainloader)
|
||||
if RANK in {-1, 0}:
|
||||
pbar = tqdm(enumerate(trainloader), total=len(trainloader), bar_format=TQDM_BAR_FORMAT)
|
||||
for i, (images, labels) in pbar: # progress bar
|
||||
images, labels = images.to(device, non_blocking=True), labels.to(device)
|
||||
|
||||
# Forward
|
||||
with amp.autocast(enabled=cuda): # stability issues when enabled
|
||||
loss = criterion(model(images), labels)
|
||||
|
||||
# Backward
|
||||
scaler.scale(loss).backward()
|
||||
|
||||
# Optimize
|
||||
scaler.unscale_(optimizer) # unscale gradients
|
||||
torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=10.0) # clip gradients
|
||||
scaler.step(optimizer)
|
||||
scaler.update()
|
||||
optimizer.zero_grad()
|
||||
if ema:
|
||||
ema.update(model)
|
||||
|
||||
if RANK in {-1, 0}:
|
||||
# Print
|
||||
tloss = (tloss * i + loss.item()) / (i + 1) # update mean losses
|
||||
mem = "%.3gG" % (torch.cuda.memory_reserved() / 1e9 if torch.cuda.is_available() else 0) # (GB)
|
||||
pbar.desc = f"{f'{epoch + 1}/{epochs}':>10}{mem:>10}{tloss:>12.3g}" + " " * 36
|
||||
|
||||
# Test
|
||||
if i == len(pbar) - 1: # last batch
|
||||
top1, top5, vloss = validate.run(
|
||||
model=ema.ema, dataloader=testloader, criterion=criterion, pbar=pbar
|
||||
) # test accuracy, loss
|
||||
fitness = top1 # define fitness as top1 accuracy
|
||||
|
||||
# Scheduler
|
||||
scheduler.step()
|
||||
|
||||
# Log metrics
|
||||
if RANK in {-1, 0}:
|
||||
# Best fitness
|
||||
if fitness > best_fitness:
|
||||
best_fitness = fitness
|
||||
|
||||
# Log
|
||||
metrics = {
|
||||
"train/loss": tloss,
|
||||
f"{val}/loss": vloss,
|
||||
"metrics/accuracy_top1": top1,
|
||||
"metrics/accuracy_top5": top5,
|
||||
"lr/0": optimizer.param_groups[0]["lr"],
|
||||
} # learning rate
|
||||
logger.log_metrics(metrics, epoch)
|
||||
|
||||
# Save model
|
||||
final_epoch = epoch + 1 == epochs
|
||||
if (not opt.nosave) or final_epoch:
|
||||
ckpt = {
|
||||
"epoch": epoch,
|
||||
"best_fitness": best_fitness,
|
||||
"model": deepcopy(ema.ema).half(), # deepcopy(de_parallel(model)).half(),
|
||||
"ema": None, # deepcopy(ema.ema).half(),
|
||||
"updates": ema.updates,
|
||||
"optimizer": None, # optimizer.state_dict(),
|
||||
"opt": vars(opt),
|
||||
"git": GIT_INFO, # {remote, branch, commit} if a git repo
|
||||
"date": datetime.now().isoformat(),
|
||||
}
|
||||
|
||||
# Save last, best and delete
|
||||
torch.save(ckpt, last)
|
||||
if best_fitness == fitness:
|
||||
torch.save(ckpt, best)
|
||||
del ckpt
|
||||
|
||||
# Train complete
|
||||
if RANK in {-1, 0} and final_epoch:
|
||||
LOGGER.info(
|
||||
f"\nTraining complete ({(time.time() - t0) / 3600:.3f} hours)"
|
||||
f"\nResults saved to {colorstr('bold', save_dir)}"
|
||||
f"\nPredict: python classify/predict.py --weights {best} --source im.jpg"
|
||||
f"\nValidate: python classify/val.py --weights {best} --data {data_dir}"
|
||||
f"\nExport: python export.py --weights {best} --include onnx"
|
||||
f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{best}')"
|
||||
f"\nVisualize: https://netron.app\n"
|
||||
)
|
||||
|
||||
# Plot examples
|
||||
images, labels = (x[:25] for x in next(iter(testloader))) # first 25 images and labels
|
||||
pred = torch.max(ema.ema(images.to(device)), 1)[1]
|
||||
file = imshow_cls(images, labels, pred, de_parallel(model).names, verbose=False, f=save_dir / "test_images.jpg")
|
||||
|
||||
# Log results
|
||||
meta = {"epochs": epochs, "top1_acc": best_fitness, "date": datetime.now().isoformat()}
|
||||
logger.log_images(file, name="Test Examples (true-predicted)", epoch=epoch)
|
||||
logger.log_model(best, epochs, metadata=meta)
|
||||
|
||||
|
||||
def parse_opt(known=False):
|
||||
"""Parses command line arguments for YOLOv5 training including model path, dataset, epochs, and more, returning
|
||||
parsed arguments.
|
||||
"""
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--model", type=str, default="yolov5s-cls.pt", help="initial weights path")
|
||||
parser.add_argument("--data", type=str, default="imagenette160", help="cifar10, cifar100, mnist, imagenet, ...")
|
||||
parser.add_argument("--epochs", type=int, default=10, help="total training epochs")
|
||||
parser.add_argument("--batch-size", type=int, default=64, help="total batch size for all GPUs")
|
||||
parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=224, help="train, val image size (pixels)")
|
||||
parser.add_argument("--nosave", action="store_true", help="only save final checkpoint")
|
||||
parser.add_argument("--cache", type=str, nargs="?", const="ram", help='--cache images in "ram" (default) or "disk"')
|
||||
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
|
||||
parser.add_argument("--workers", type=int, default=8, help="max dataloader workers (per RANK in DDP mode)")
|
||||
parser.add_argument("--project", default=ROOT / "runs/train-cls", help="save to project/name")
|
||||
parser.add_argument("--name", default="exp", help="save to project/name")
|
||||
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
|
||||
parser.add_argument("--pretrained", nargs="?", const=True, default=True, help="start from i.e. --pretrained False")
|
||||
parser.add_argument("--optimizer", choices=["SGD", "Adam", "AdamW", "RMSProp"], default="Adam", help="optimizer")
|
||||
parser.add_argument("--lr0", type=float, default=0.001, help="initial learning rate")
|
||||
parser.add_argument("--decay", type=float, default=5e-5, help="weight decay")
|
||||
parser.add_argument("--label-smoothing", type=float, default=0.1, help="Label smoothing epsilon")
|
||||
parser.add_argument("--cutoff", type=int, default=None, help="Model layer cutoff index for Classify() head")
|
||||
parser.add_argument("--dropout", type=float, default=None, help="Dropout (fraction)")
|
||||
parser.add_argument("--verbose", action="store_true", help="Verbose mode")
|
||||
parser.add_argument("--seed", type=int, default=0, help="Global training seed")
|
||||
parser.add_argument("--local_rank", type=int, default=-1, help="Automatic DDP Multi-GPU argument, do not modify")
|
||||
return parser.parse_known_args()[0] if known else parser.parse_args()
|
||||
|
||||
|
||||
def main(opt):
|
||||
"""Executes YOLOv5 training with given options, handling device setup and DDP mode; includes pre-training checks."""
|
||||
if RANK in {-1, 0}:
|
||||
print_args(vars(opt))
|
||||
check_git_status()
|
||||
check_requirements(ROOT / "requirements.txt")
|
||||
|
||||
# DDP mode
|
||||
device = select_device(opt.device, batch_size=opt.batch_size)
|
||||
if LOCAL_RANK != -1:
|
||||
assert opt.batch_size != -1, "AutoBatch is coming soon for classification, please pass a valid --batch-size"
|
||||
assert opt.batch_size % WORLD_SIZE == 0, f"--batch-size {opt.batch_size} must be multiple of WORLD_SIZE"
|
||||
assert torch.cuda.device_count() > LOCAL_RANK, "insufficient CUDA devices for DDP command"
|
||||
torch.cuda.set_device(LOCAL_RANK)
|
||||
device = torch.device("cuda", LOCAL_RANK)
|
||||
dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
|
||||
|
||||
# Parameters
|
||||
opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok) # increment run
|
||||
|
||||
# Train
|
||||
train(opt, device)
|
||||
|
||||
|
||||
def run(**kwargs):
|
||||
"""
|
||||
Executes YOLOv5 model training or inference with specified parameters, returning updated options.
|
||||
|
||||
Example: from yolov5 import classify; classify.train.run(data=mnist, imgsz=320, model='yolov5m')
|
||||
"""
|
||||
opt = parse_opt(True)
|
||||
for k, v in kwargs.items():
|
||||
setattr(opt, k, v)
|
||||
main(opt)
|
||||
return opt
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
1488
yolov5/classify/tutorial.ipynb
vendored
Normal file
1488
yolov5/classify/tutorial.ipynb
vendored
Normal file
File diff suppressed because it is too large
Load Diff
178
yolov5/classify/val.py
Normal file
178
yolov5/classify/val.py
Normal file
@ -0,0 +1,178 @@
|
||||
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
||||
"""
|
||||
Validate a trained YOLOv5 classification model on a classification dataset.
|
||||
|
||||
Usage:
|
||||
$ bash data/scripts/get_imagenet.sh --val # download ImageNet val split (6.3G, 50000 images)
|
||||
$ python classify/val.py --weights yolov5m-cls.pt --data ../datasets/imagenet --img 224 # validate ImageNet
|
||||
|
||||
Usage - formats:
|
||||
$ python classify/val.py --weights yolov5s-cls.pt # PyTorch
|
||||
yolov5s-cls.torchscript # TorchScript
|
||||
yolov5s-cls.onnx # ONNX Runtime or OpenCV DNN with --dnn
|
||||
yolov5s-cls_openvino_model # OpenVINO
|
||||
yolov5s-cls.engine # TensorRT
|
||||
yolov5s-cls.mlmodel # CoreML (macOS-only)
|
||||
yolov5s-cls_saved_model # TensorFlow SavedModel
|
||||
yolov5s-cls.pb # TensorFlow GraphDef
|
||||
yolov5s-cls.tflite # TensorFlow Lite
|
||||
yolov5s-cls_edgetpu.tflite # TensorFlow Edge TPU
|
||||
yolov5s-cls_paddle_model # PaddlePaddle
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
from tqdm import tqdm
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from models.common import DetectMultiBackend
|
||||
from utils.dataloaders import create_classification_dataloader
|
||||
from utils.general import (
|
||||
LOGGER,
|
||||
TQDM_BAR_FORMAT,
|
||||
Profile,
|
||||
check_img_size,
|
||||
check_requirements,
|
||||
colorstr,
|
||||
increment_path,
|
||||
print_args,
|
||||
)
|
||||
from utils.torch_utils import select_device, smart_inference_mode
|
||||
|
||||
|
||||
@smart_inference_mode()
|
||||
def run(
|
||||
data=ROOT / "../datasets/mnist", # dataset dir
|
||||
weights=ROOT / "yolov5s-cls.pt", # model.pt path(s)
|
||||
batch_size=128, # batch size
|
||||
imgsz=224, # inference size (pixels)
|
||||
device="", # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
workers=8, # max dataloader workers (per RANK in DDP mode)
|
||||
verbose=False, # verbose output
|
||||
project=ROOT / "runs/val-cls", # save to project/name
|
||||
name="exp", # save to project/name
|
||||
exist_ok=False, # existing project/name ok, do not increment
|
||||
half=False, # use FP16 half-precision inference
|
||||
dnn=False, # use OpenCV DNN for ONNX inference
|
||||
model=None,
|
||||
dataloader=None,
|
||||
criterion=None,
|
||||
pbar=None,
|
||||
):
|
||||
"""Validates a YOLOv5 classification model on a dataset, computing metrics like top1 and top5 accuracy."""
|
||||
# Initialize/load model and set device
|
||||
training = model is not None
|
||||
if training: # called by train.py
|
||||
device, pt, jit, engine = next(model.parameters()).device, True, False, False # get model device, PyTorch model
|
||||
half &= device.type != "cpu" # half precision only supported on CUDA
|
||||
model.half() if half else model.float()
|
||||
else: # called directly
|
||||
device = select_device(device, batch_size=batch_size)
|
||||
|
||||
# Directories
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
save_dir.mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Load model
|
||||
model = DetectMultiBackend(weights, device=device, dnn=dnn, fp16=half)
|
||||
stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
|
||||
imgsz = check_img_size(imgsz, s=stride) # check image size
|
||||
half = model.fp16 # FP16 supported on limited backends with CUDA
|
||||
if engine:
|
||||
batch_size = model.batch_size
|
||||
else:
|
||||
device = model.device
|
||||
if not (pt or jit):
|
||||
batch_size = 1 # export.py models default to batch-size 1
|
||||
LOGGER.info(f"Forcing --batch-size 1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models")
|
||||
|
||||
# Dataloader
|
||||
data = Path(data)
|
||||
test_dir = data / "test" if (data / "test").exists() else data / "val" # data/test or data/val
|
||||
dataloader = create_classification_dataloader(
|
||||
path=test_dir, imgsz=imgsz, batch_size=batch_size, augment=False, rank=-1, workers=workers
|
||||
)
|
||||
|
||||
model.eval()
|
||||
pred, targets, loss, dt = [], [], 0, (Profile(device=device), Profile(device=device), Profile(device=device))
|
||||
n = len(dataloader) # number of batches
|
||||
action = "validating" if dataloader.dataset.root.stem == "val" else "testing"
|
||||
desc = f"{pbar.desc[:-36]}{action:>36}" if pbar else f"{action}"
|
||||
bar = tqdm(dataloader, desc, n, not training, bar_format=TQDM_BAR_FORMAT, position=0)
|
||||
with torch.cuda.amp.autocast(enabled=device.type != "cpu"):
|
||||
for images, labels in bar:
|
||||
with dt[0]:
|
||||
images, labels = images.to(device, non_blocking=True), labels.to(device)
|
||||
|
||||
with dt[1]:
|
||||
y = model(images)
|
||||
|
||||
with dt[2]:
|
||||
pred.append(y.argsort(1, descending=True)[:, :5])
|
||||
targets.append(labels)
|
||||
if criterion:
|
||||
loss += criterion(y, labels)
|
||||
|
||||
loss /= n
|
||||
pred, targets = torch.cat(pred), torch.cat(targets)
|
||||
correct = (targets[:, None] == pred).float()
|
||||
acc = torch.stack((correct[:, 0], correct.max(1).values), dim=1) # (top1, top5) accuracy
|
||||
top1, top5 = acc.mean(0).tolist()
|
||||
|
||||
if pbar:
|
||||
pbar.desc = f"{pbar.desc[:-36]}{loss:>12.3g}{top1:>12.3g}{top5:>12.3g}"
|
||||
if verbose: # all classes
|
||||
LOGGER.info(f"{'Class':>24}{'Images':>12}{'top1_acc':>12}{'top5_acc':>12}")
|
||||
LOGGER.info(f"{'all':>24}{targets.shape[0]:>12}{top1:>12.3g}{top5:>12.3g}")
|
||||
for i, c in model.names.items():
|
||||
acc_i = acc[targets == i]
|
||||
top1i, top5i = acc_i.mean(0).tolist()
|
||||
LOGGER.info(f"{c:>24}{acc_i.shape[0]:>12}{top1i:>12.3g}{top5i:>12.3g}")
|
||||
|
||||
# Print results
|
||||
t = tuple(x.t / len(dataloader.dataset.samples) * 1e3 for x in dt) # speeds per image
|
||||
shape = (1, 3, imgsz, imgsz)
|
||||
LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms post-process per image at shape {shape}" % t)
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
|
||||
|
||||
return top1, top5, loss
|
||||
|
||||
|
||||
def parse_opt():
|
||||
"""Parses and returns command line arguments for YOLOv5 model evaluation and inference settings."""
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--data", type=str, default=ROOT / "../datasets/mnist", help="dataset path")
|
||||
parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s-cls.pt", help="model.pt path(s)")
|
||||
parser.add_argument("--batch-size", type=int, default=128, help="batch size")
|
||||
parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=224, help="inference size (pixels)")
|
||||
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
|
||||
parser.add_argument("--workers", type=int, default=8, help="max dataloader workers (per RANK in DDP mode)")
|
||||
parser.add_argument("--verbose", nargs="?", const=True, default=True, help="verbose output")
|
||||
parser.add_argument("--project", default=ROOT / "runs/val-cls", help="save to project/name")
|
||||
parser.add_argument("--name", default="exp", help="save to project/name")
|
||||
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
|
||||
parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
|
||||
parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
|
||||
opt = parser.parse_args()
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
"""Executes the YOLOv5 model prediction workflow, handling argument parsing and requirement checks."""
|
||||
check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop"))
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
Reference in New Issue
Block a user