You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
765 lines
34 KiB
Python
765 lines
34 KiB
Python
3 weeks ago
|
# Ultralytics YOLOv5 🚀, AGPL-3.0 license
|
||
|
|
"""
|
||
|
|
Train a YOLOv5 segment model on a segment dataset Models and datasets download automatically from the latest YOLOv5
|
||
|
|
release.
|
||
|
|
|
||
|
|
Usage - Single-GPU training:
|
||
|
|
$ python segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 # from pretrained (recommended)
|
||
|
|
$ python segment/train.py --data coco128-seg.yaml --weights '' --cfg yolov5s-seg.yaml --img 640 # from scratch
|
||
|
|
|
||
|
|
Usage - Multi-GPU DDP training:
|
||
|
|
$ python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 --device 0,1,2,3
|
||
|
|
|
||
|
|
Models: https://github.com/ultralytics/yolov5/tree/master/models
|
||
|
|
Datasets: https://github.com/ultralytics/yolov5/tree/master/data
|
||
|
|
Tutorial: https://docs.ultralytics.com/yolov5/tutorials/train_custom_data
|
||
|
|
"""
|
||
|
|
|
||
|
|
import argparse
|
||
|
|
import math
|
||
|
|
import os
|
||
|
|
import random
|
||
|
|
import subprocess
|
||
|
|
import sys
|
||
|
|
import time
|
||
|
|
from copy import deepcopy
|
||
|
|
from datetime import datetime
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
import torch
|
||
|
|
import torch.distributed as dist
|
||
|
|
import torch.nn as nn
|
||
|
|
import yaml
|
||
|
|
from torch.optim import lr_scheduler
|
||
|
|
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
|
||
|
|
|
||
|
|
import segment.val as validate # for end-of-epoch mAP
|
||
|
|
from models.experimental import attempt_load
|
||
|
|
from models.yolo import SegmentationModel
|
||
|
|
from utils.autoanchor import check_anchors
|
||
|
|
from utils.autobatch import check_train_batch_size
|
||
|
|
from utils.callbacks import Callbacks
|
||
|
|
from utils.downloads import attempt_download, is_url
|
||
|
|
from utils.general import (
|
||
|
|
LOGGER,
|
||
|
|
TQDM_BAR_FORMAT,
|
||
|
|
check_amp,
|
||
|
|
check_dataset,
|
||
|
|
check_file,
|
||
|
|
check_git_info,
|
||
|
|
check_git_status,
|
||
|
|
check_img_size,
|
||
|
|
check_requirements,
|
||
|
|
check_suffix,
|
||
|
|
check_yaml,
|
||
|
|
colorstr,
|
||
|
|
get_latest_run,
|
||
|
|
increment_path,
|
||
|
|
init_seeds,
|
||
|
|
intersect_dicts,
|
||
|
|
labels_to_class_weights,
|
||
|
|
labels_to_image_weights,
|
||
|
|
one_cycle,
|
||
|
|
print_args,
|
||
|
|
print_mutation,
|
||
|
|
strip_optimizer,
|
||
|
|
yaml_save,
|
||
|
|
)
|
||
|
|
from utils.loggers import GenericLogger
|
||
|
|
from utils.plots import plot_evolve, plot_labels
|
||
|
|
from utils.segment.dataloaders import create_dataloader
|
||
|
|
from utils.segment.loss import ComputeLoss
|
||
|
|
from utils.segment.metrics import KEYS, fitness
|
||
|
|
from utils.segment.plots import plot_images_and_masks, plot_results_with_masks
|
||
|
|
from utils.torch_utils import (
|
||
|
|
EarlyStopping,
|
||
|
|
ModelEMA,
|
||
|
|
de_parallel,
|
||
|
|
select_device,
|
||
|
|
smart_DDP,
|
||
|
|
smart_optimizer,
|
||
|
|
smart_resume,
|
||
|
|
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(hyp, opt, device, callbacks):
|
||
|
|
"""
|
||
|
|
Trains the YOLOv5 model on a dataset, managing hyperparameters, model optimization, logging, and validation.
|
||
|
|
|
||
|
|
`hyp` is path/to/hyp.yaml or hyp dictionary.
|
||
|
|
"""
|
||
|
|
(
|
||
|
|
save_dir,
|
||
|
|
epochs,
|
||
|
|
batch_size,
|
||
|
|
weights,
|
||
|
|
single_cls,
|
||
|
|
evolve,
|
||
|
|
data,
|
||
|
|
cfg,
|
||
|
|
resume,
|
||
|
|
noval,
|
||
|
|
nosave,
|
||
|
|
workers,
|
||
|
|
freeze,
|
||
|
|
mask_ratio,
|
||
|
|
) = (
|
||
|
|
Path(opt.save_dir),
|
||
|
|
opt.epochs,
|
||
|
|
opt.batch_size,
|
||
|
|
opt.weights,
|
||
|
|
opt.single_cls,
|
||
|
|
opt.evolve,
|
||
|
|
opt.data,
|
||
|
|
opt.cfg,
|
||
|
|
opt.resume,
|
||
|
|
opt.noval,
|
||
|
|
opt.nosave,
|
||
|
|
opt.workers,
|
||
|
|
opt.freeze,
|
||
|
|
opt.mask_ratio,
|
||
|
|
)
|
||
|
|
# callbacks.run('on_pretrain_routine_start')
|
||
|
|
|
||
|
|
# Directories
|
||
|
|
w = save_dir / "weights" # weights dir
|
||
|
|
(w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir
|
||
|
|
last, best = w / "last.pt", w / "best.pt"
|
||
|
|
|
||
|
|
# Hyperparameters
|
||
|
|
if isinstance(hyp, str):
|
||
|
|
with open(hyp, errors="ignore") as f:
|
||
|
|
hyp = yaml.safe_load(f) # load hyps dict
|
||
|
|
LOGGER.info(colorstr("hyperparameters: ") + ", ".join(f"{k}={v}" for k, v in hyp.items()))
|
||
|
|
opt.hyp = hyp.copy() # for saving hyps to checkpoints
|
||
|
|
|
||
|
|
# Save run settings
|
||
|
|
if not evolve:
|
||
|
|
yaml_save(save_dir / "hyp.yaml", hyp)
|
||
|
|
yaml_save(save_dir / "opt.yaml", vars(opt))
|
||
|
|
|
||
|
|
# Loggers
|
||
|
|
data_dict = None
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
logger = GenericLogger(opt=opt, console_logger=LOGGER)
|
||
|
|
|
||
|
|
# Config
|
||
|
|
plots = not evolve and not opt.noplots # create plots
|
||
|
|
overlap = not opt.no_overlap
|
||
|
|
cuda = device.type != "cpu"
|
||
|
|
init_seeds(opt.seed + 1 + RANK, deterministic=True)
|
||
|
|
with torch_distributed_zero_first(LOCAL_RANK):
|
||
|
|
data_dict = data_dict or check_dataset(data) # check if None
|
||
|
|
train_path, val_path = data_dict["train"], data_dict["val"]
|
||
|
|
nc = 1 if single_cls else int(data_dict["nc"]) # number of classes
|
||
|
|
names = {0: "item"} if single_cls and len(data_dict["names"]) != 1 else data_dict["names"] # class names
|
||
|
|
is_coco = isinstance(val_path, str) and val_path.endswith("coco/val2017.txt") # COCO dataset
|
||
|
|
|
||
|
|
# Model
|
||
|
|
check_suffix(weights, ".pt") # check weights
|
||
|
|
pretrained = weights.endswith(".pt")
|
||
|
|
if pretrained:
|
||
|
|
with torch_distributed_zero_first(LOCAL_RANK):
|
||
|
|
weights = attempt_download(weights) # download if not found locally
|
||
|
|
ckpt = torch.load(weights, map_location="cpu") # load checkpoint to CPU to avoid CUDA memory leak
|
||
|
|
model = SegmentationModel(cfg or ckpt["model"].yaml, ch=3, nc=nc, anchors=hyp.get("anchors")).to(device)
|
||
|
|
exclude = ["anchor"] if (cfg or hyp.get("anchors")) and not resume else [] # exclude keys
|
||
|
|
csd = ckpt["model"].float().state_dict() # checkpoint state_dict as FP32
|
||
|
|
csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
|
||
|
|
model.load_state_dict(csd, strict=False) # load
|
||
|
|
LOGGER.info(f"Transferred {len(csd)}/{len(model.state_dict())} items from {weights}") # report
|
||
|
|
else:
|
||
|
|
model = SegmentationModel(cfg, ch=3, nc=nc, anchors=hyp.get("anchors")).to(device) # create
|
||
|
|
amp = check_amp(model) # check AMP
|
||
|
|
|
||
|
|
# Freeze
|
||
|
|
freeze = [f"model.{x}." for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # layers to freeze
|
||
|
|
for k, v in model.named_parameters():
|
||
|
|
v.requires_grad = True # train all layers
|
||
|
|
# v.register_hook(lambda x: torch.nan_to_num(x)) # NaN to 0 (commented for erratic training results)
|
||
|
|
if any(x in k for x in freeze):
|
||
|
|
LOGGER.info(f"freezing {k}")
|
||
|
|
v.requires_grad = False
|
||
|
|
|
||
|
|
# Image size
|
||
|
|
gs = max(int(model.stride.max()), 32) # grid size (max stride)
|
||
|
|
imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple
|
||
|
|
|
||
|
|
# Batch size
|
||
|
|
if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size
|
||
|
|
batch_size = check_train_batch_size(model, imgsz, amp)
|
||
|
|
logger.update_params({"batch_size": batch_size})
|
||
|
|
# loggers.on_params_update({"batch_size": batch_size})
|
||
|
|
|
||
|
|
# Optimizer
|
||
|
|
nbs = 64 # nominal batch size
|
||
|
|
accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing
|
||
|
|
hyp["weight_decay"] *= batch_size * accumulate / nbs # scale weight_decay
|
||
|
|
optimizer = smart_optimizer(model, opt.optimizer, hyp["lr0"], hyp["momentum"], hyp["weight_decay"])
|
||
|
|
|
||
|
|
# Scheduler
|
||
|
|
if opt.cos_lr:
|
||
|
|
lf = one_cycle(1, hyp["lrf"], epochs) # cosine 1->hyp['lrf']
|
||
|
|
else:
|
||
|
|
|
||
|
|
def lf(x):
|
||
|
|
"""Linear learning rate scheduler decreasing from 1 to hyp['lrf'] over 'epochs'."""
|
||
|
|
return (1 - x / epochs) * (1.0 - hyp["lrf"]) + hyp["lrf"] # linear
|
||
|
|
|
||
|
|
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
|
||
|
|
|
||
|
|
# EMA
|
||
|
|
ema = ModelEMA(model) if RANK in {-1, 0} else None
|
||
|
|
|
||
|
|
# Resume
|
||
|
|
best_fitness, start_epoch = 0.0, 0
|
||
|
|
if pretrained:
|
||
|
|
if resume:
|
||
|
|
best_fitness, start_epoch, epochs = smart_resume(ckpt, optimizer, ema, weights, epochs, resume)
|
||
|
|
del ckpt, csd
|
||
|
|
|
||
|
|
# DP mode
|
||
|
|
if cuda and RANK == -1 and torch.cuda.device_count() > 1:
|
||
|
|
LOGGER.warning(
|
||
|
|
"WARNING ⚠️ DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n"
|
||
|
|
"See Multi-GPU Tutorial at https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training to get started."
|
||
|
|
)
|
||
|
|
model = torch.nn.DataParallel(model)
|
||
|
|
|
||
|
|
# SyncBatchNorm
|
||
|
|
if opt.sync_bn and cuda and RANK != -1:
|
||
|
|
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
|
||
|
|
LOGGER.info("Using SyncBatchNorm()")
|
||
|
|
|
||
|
|
# Trainloader
|
||
|
|
train_loader, dataset = create_dataloader(
|
||
|
|
train_path,
|
||
|
|
imgsz,
|
||
|
|
batch_size // WORLD_SIZE,
|
||
|
|
gs,
|
||
|
|
single_cls,
|
||
|
|
hyp=hyp,
|
||
|
|
augment=True,
|
||
|
|
cache=None if opt.cache == "val" else opt.cache,
|
||
|
|
rect=opt.rect,
|
||
|
|
rank=LOCAL_RANK,
|
||
|
|
workers=workers,
|
||
|
|
image_weights=opt.image_weights,
|
||
|
|
quad=opt.quad,
|
||
|
|
prefix=colorstr("train: "),
|
||
|
|
shuffle=True,
|
||
|
|
mask_downsample_ratio=mask_ratio,
|
||
|
|
overlap_mask=overlap,
|
||
|
|
)
|
||
|
|
labels = np.concatenate(dataset.labels, 0)
|
||
|
|
mlc = int(labels[:, 0].max()) # max label class
|
||
|
|
assert mlc < nc, f"Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}"
|
||
|
|
|
||
|
|
# Process 0
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
val_loader = create_dataloader(
|
||
|
|
val_path,
|
||
|
|
imgsz,
|
||
|
|
batch_size // WORLD_SIZE * 2,
|
||
|
|
gs,
|
||
|
|
single_cls,
|
||
|
|
hyp=hyp,
|
||
|
|
cache=None if noval else opt.cache,
|
||
|
|
rect=True,
|
||
|
|
rank=-1,
|
||
|
|
workers=workers * 2,
|
||
|
|
pad=0.5,
|
||
|
|
mask_downsample_ratio=mask_ratio,
|
||
|
|
overlap_mask=overlap,
|
||
|
|
prefix=colorstr("val: "),
|
||
|
|
)[0]
|
||
|
|
|
||
|
|
if not resume:
|
||
|
|
if not opt.noautoanchor:
|
||
|
|
check_anchors(dataset, model=model, thr=hyp["anchor_t"], imgsz=imgsz) # run AutoAnchor
|
||
|
|
model.half().float() # pre-reduce anchor precision
|
||
|
|
|
||
|
|
if plots:
|
||
|
|
plot_labels(labels, names, save_dir)
|
||
|
|
# callbacks.run('on_pretrain_routine_end', labels, names)
|
||
|
|
|
||
|
|
# DDP mode
|
||
|
|
if cuda and RANK != -1:
|
||
|
|
model = smart_DDP(model)
|
||
|
|
|
||
|
|
# Model attributes
|
||
|
|
nl = de_parallel(model).model[-1].nl # number of detection layers (to scale hyps)
|
||
|
|
hyp["box"] *= 3 / nl # scale to layers
|
||
|
|
hyp["cls"] *= nc / 80 * 3 / nl # scale to classes and layers
|
||
|
|
hyp["obj"] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
|
||
|
|
hyp["label_smoothing"] = opt.label_smoothing
|
||
|
|
model.nc = nc # attach number of classes to model
|
||
|
|
model.hyp = hyp # attach hyperparameters to model
|
||
|
|
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
|
||
|
|
model.names = names
|
||
|
|
|
||
|
|
# Start training
|
||
|
|
t0 = time.time()
|
||
|
|
nb = len(train_loader) # number of batches
|
||
|
|
nw = max(round(hyp["warmup_epochs"] * nb), 100) # number of warmup iterations, max(3 epochs, 100 iterations)
|
||
|
|
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
|
||
|
|
last_opt_step = -1
|
||
|
|
maps = np.zeros(nc) # mAP per class
|
||
|
|
results = (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
|
||
|
|
scheduler.last_epoch = start_epoch - 1 # do not move
|
||
|
|
scaler = torch.cuda.amp.GradScaler(enabled=amp)
|
||
|
|
stopper, stop = EarlyStopping(patience=opt.patience), False
|
||
|
|
compute_loss = ComputeLoss(model, overlap=overlap) # init loss class
|
||
|
|
# callbacks.run('on_train_start')
|
||
|
|
LOGGER.info(
|
||
|
|
f'Image sizes {imgsz} train, {imgsz} val\n'
|
||
|
|
f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
|
||
|
|
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||
|
|
f'Starting training for {epochs} epochs...'
|
||
|
|
)
|
||
|
|
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||
|
|
# callbacks.run('on_train_epoch_start')
|
||
|
|
model.train()
|
||
|
|
|
||
|
|
# Update image weights (optional, single-GPU only)
|
||
|
|
if opt.image_weights:
|
||
|
|
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
|
||
|
|
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
|
||
|
|
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
|
||
|
|
|
||
|
|
# Update mosaic border (optional)
|
||
|
|
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
|
||
|
|
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
|
||
|
|
|
||
|
|
mloss = torch.zeros(4, device=device) # mean losses
|
||
|
|
if RANK != -1:
|
||
|
|
train_loader.sampler.set_epoch(epoch)
|
||
|
|
pbar = enumerate(train_loader)
|
||
|
|
LOGGER.info(
|
||
|
|
("\n" + "%11s" * 8)
|
||
|
|
% ("Epoch", "GPU_mem", "box_loss", "seg_loss", "obj_loss", "cls_loss", "Instances", "Size")
|
||
|
|
)
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
pbar = tqdm(pbar, total=nb, bar_format=TQDM_BAR_FORMAT) # progress bar
|
||
|
|
optimizer.zero_grad()
|
||
|
|
for i, (imgs, targets, paths, _, masks) in pbar: # batch ------------------------------------------------------
|
||
|
|
# callbacks.run('on_train_batch_start')
|
||
|
|
ni = i + nb * epoch # number integrated batches (since train start)
|
||
|
|
imgs = imgs.to(device, non_blocking=True).float() / 255 # uint8 to float32, 0-255 to 0.0-1.0
|
||
|
|
|
||
|
|
# Warmup
|
||
|
|
if ni <= nw:
|
||
|
|
xi = [0, nw] # x interp
|
||
|
|
# compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
|
||
|
|
accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round())
|
||
|
|
for j, x in enumerate(optimizer.param_groups):
|
||
|
|
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
|
||
|
|
x["lr"] = np.interp(ni, xi, [hyp["warmup_bias_lr"] if j == 0 else 0.0, x["initial_lr"] * lf(epoch)])
|
||
|
|
if "momentum" in x:
|
||
|
|
x["momentum"] = np.interp(ni, xi, [hyp["warmup_momentum"], hyp["momentum"]])
|
||
|
|
|
||
|
|
# Multi-scale
|
||
|
|
if opt.multi_scale:
|
||
|
|
sz = random.randrange(int(imgsz * 0.5), int(imgsz * 1.5) + gs) // gs * gs # size
|
||
|
|
sf = sz / max(imgs.shape[2:]) # scale factor
|
||
|
|
if sf != 1:
|
||
|
|
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
|
||
|
|
imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
|
||
|
|
|
||
|
|
# Forward
|
||
|
|
with torch.cuda.amp.autocast(amp):
|
||
|
|
pred = model(imgs) # forward
|
||
|
|
loss, loss_items = compute_loss(pred, targets.to(device), masks=masks.to(device).float())
|
||
|
|
if RANK != -1:
|
||
|
|
loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
|
||
|
|
if opt.quad:
|
||
|
|
loss *= 4.0
|
||
|
|
|
||
|
|
# Backward
|
||
|
|
scaler.scale(loss).backward()
|
||
|
|
|
||
|
|
# Optimize - https://pytorch.org/docs/master/notes/amp_examples.html
|
||
|
|
if ni - last_opt_step >= accumulate:
|
||
|
|
scaler.unscale_(optimizer) # unscale gradients
|
||
|
|
torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=10.0) # clip gradients
|
||
|
|
scaler.step(optimizer) # optimizer.step
|
||
|
|
scaler.update()
|
||
|
|
optimizer.zero_grad()
|
||
|
|
if ema:
|
||
|
|
ema.update(model)
|
||
|
|
last_opt_step = ni
|
||
|
|
|
||
|
|
# Log
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||
|
|
mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
|
||
|
|
pbar.set_description(
|
||
|
|
("%11s" * 2 + "%11.4g" * 6)
|
||
|
|
% (f"{epoch}/{epochs - 1}", mem, *mloss, targets.shape[0], imgs.shape[-1])
|
||
|
|
)
|
||
|
|
# callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths)
|
||
|
|
# if callbacks.stop_training:
|
||
|
|
# return
|
||
|
|
|
||
|
|
# Mosaic plots
|
||
|
|
if plots:
|
||
|
|
if ni < 3:
|
||
|
|
plot_images_and_masks(imgs, targets, masks, paths, save_dir / f"train_batch{ni}.jpg")
|
||
|
|
if ni == 10:
|
||
|
|
files = sorted(save_dir.glob("train*.jpg"))
|
||
|
|
logger.log_images(files, "Mosaics", epoch)
|
||
|
|
# end batch ------------------------------------------------------------------------------------------------
|
||
|
|
|
||
|
|
# Scheduler
|
||
|
|
lr = [x["lr"] for x in optimizer.param_groups] # for loggers
|
||
|
|
scheduler.step()
|
||
|
|
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
# mAP
|
||
|
|
# callbacks.run('on_train_epoch_end', epoch=epoch)
|
||
|
|
ema.update_attr(model, include=["yaml", "nc", "hyp", "names", "stride", "class_weights"])
|
||
|
|
final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
|
||
|
|
if not noval or final_epoch: # Calculate mAP
|
||
|
|
results, maps, _ = validate.run(
|
||
|
|
data_dict,
|
||
|
|
batch_size=batch_size // WORLD_SIZE * 2,
|
||
|
|
imgsz=imgsz,
|
||
|
|
half=amp,
|
||
|
|
model=ema.ema,
|
||
|
|
single_cls=single_cls,
|
||
|
|
dataloader=val_loader,
|
||
|
|
save_dir=save_dir,
|
||
|
|
plots=False,
|
||
|
|
callbacks=callbacks,
|
||
|
|
compute_loss=compute_loss,
|
||
|
|
mask_downsample_ratio=mask_ratio,
|
||
|
|
overlap=overlap,
|
||
|
|
)
|
||
|
|
|
||
|
|
# Update best mAP
|
||
|
|
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
|
||
|
|
stop = stopper(epoch=epoch, fitness=fi) # early stop check
|
||
|
|
if fi > best_fitness:
|
||
|
|
best_fitness = fi
|
||
|
|
log_vals = list(mloss) + list(results) + lr
|
||
|
|
# callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi)
|
||
|
|
# Log val metrics and media
|
||
|
|
metrics_dict = dict(zip(KEYS, log_vals))
|
||
|
|
logger.log_metrics(metrics_dict, epoch)
|
||
|
|
|
||
|
|
# Save model
|
||
|
|
if (not nosave) or (final_epoch and not evolve): # if save
|
||
|
|
ckpt = {
|
||
|
|
"epoch": epoch,
|
||
|
|
"best_fitness": best_fitness,
|
||
|
|
"model": deepcopy(de_parallel(model)).half(),
|
||
|
|
"ema": deepcopy(ema.ema).half(),
|
||
|
|
"updates": ema.updates,
|
||
|
|
"optimizer": 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 == fi:
|
||
|
|
torch.save(ckpt, best)
|
||
|
|
if opt.save_period > 0 and epoch % opt.save_period == 0:
|
||
|
|
torch.save(ckpt, w / f"epoch{epoch}.pt")
|
||
|
|
logger.log_model(w / f"epoch{epoch}.pt")
|
||
|
|
del ckpt
|
||
|
|
# callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)
|
||
|
|
|
||
|
|
# EarlyStopping
|
||
|
|
if RANK != -1: # if DDP training
|
||
|
|
broadcast_list = [stop if RANK == 0 else None]
|
||
|
|
dist.broadcast_object_list(broadcast_list, 0) # broadcast 'stop' to all ranks
|
||
|
|
if RANK != 0:
|
||
|
|
stop = broadcast_list[0]
|
||
|
|
if stop:
|
||
|
|
break # must break all DDP ranks
|
||
|
|
|
||
|
|
# end epoch ----------------------------------------------------------------------------------------------------
|
||
|
|
# end training -----------------------------------------------------------------------------------------------------
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
LOGGER.info(f"\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.")
|
||
|
|
for f in last, best:
|
||
|
|
if f.exists():
|
||
|
|
strip_optimizer(f) # strip optimizers
|
||
|
|
if f is best:
|
||
|
|
LOGGER.info(f"\nValidating {f}...")
|
||
|
|
results, _, _ = validate.run(
|
||
|
|
data_dict,
|
||
|
|
batch_size=batch_size // WORLD_SIZE * 2,
|
||
|
|
imgsz=imgsz,
|
||
|
|
model=attempt_load(f, device).half(),
|
||
|
|
iou_thres=0.65 if is_coco else 0.60, # best pycocotools at iou 0.65
|
||
|
|
single_cls=single_cls,
|
||
|
|
dataloader=val_loader,
|
||
|
|
save_dir=save_dir,
|
||
|
|
save_json=is_coco,
|
||
|
|
verbose=True,
|
||
|
|
plots=plots,
|
||
|
|
callbacks=callbacks,
|
||
|
|
compute_loss=compute_loss,
|
||
|
|
mask_downsample_ratio=mask_ratio,
|
||
|
|
overlap=overlap,
|
||
|
|
) # val best model with plots
|
||
|
|
if is_coco:
|
||
|
|
# callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
|
||
|
|
metrics_dict = dict(zip(KEYS, list(mloss) + list(results) + lr))
|
||
|
|
logger.log_metrics(metrics_dict, epoch)
|
||
|
|
|
||
|
|
# callbacks.run('on_train_end', last, best, epoch, results)
|
||
|
|
# on train end callback using genericLogger
|
||
|
|
logger.log_metrics(dict(zip(KEYS[4:16], results)), epochs)
|
||
|
|
if not opt.evolve:
|
||
|
|
logger.log_model(best, epoch)
|
||
|
|
if plots:
|
||
|
|
plot_results_with_masks(file=save_dir / "results.csv") # save results.png
|
||
|
|
files = ["results.png", "confusion_matrix.png", *(f"{x}_curve.png" for x in ("F1", "PR", "P", "R"))]
|
||
|
|
files = [(save_dir / f) for f in files if (save_dir / f).exists()] # filter
|
||
|
|
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
|
||
|
|
logger.log_images(files, "Results", epoch + 1)
|
||
|
|
logger.log_images(sorted(save_dir.glob("val*.jpg")), "Validation", epoch + 1)
|
||
|
|
torch.cuda.empty_cache()
|
||
|
|
return results
|
||
|
|
|
||
|
|
|
||
|
|
def parse_opt(known=False):
|
||
|
|
"""
|
||
|
|
Parses command line arguments for training configurations, returning parsed arguments.
|
||
|
|
|
||
|
|
Supports both known and unknown args.
|
||
|
|
"""
|
||
|
|
parser = argparse.ArgumentParser()
|
||
|
|
parser.add_argument("--weights", type=str, default=ROOT / "yolov5s-seg.pt", help="initial weights path")
|
||
|
|
parser.add_argument("--cfg", type=str, default="", help="model.yaml path")
|
||
|
|
parser.add_argument("--data", type=str, default=ROOT / "data/coco128-seg.yaml", help="dataset.yaml path")
|
||
|
|
parser.add_argument("--hyp", type=str, default=ROOT / "data/hyps/hyp.scratch-low.yaml", help="hyperparameters path")
|
||
|
|
parser.add_argument("--epochs", type=int, default=100, help="total training epochs")
|
||
|
|
parser.add_argument("--batch-size", type=int, default=16, help="total batch size for all GPUs, -1 for autobatch")
|
||
|
|
parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=640, help="train, val image size (pixels)")
|
||
|
|
parser.add_argument("--rect", action="store_true", help="rectangular training")
|
||
|
|
parser.add_argument("--resume", nargs="?", const=True, default=False, help="resume most recent training")
|
||
|
|
parser.add_argument("--nosave", action="store_true", help="only save final checkpoint")
|
||
|
|
parser.add_argument("--noval", action="store_true", help="only validate final epoch")
|
||
|
|
parser.add_argument("--noautoanchor", action="store_true", help="disable AutoAnchor")
|
||
|
|
parser.add_argument("--noplots", action="store_true", help="save no plot files")
|
||
|
|
parser.add_argument("--evolve", type=int, nargs="?", const=300, help="evolve hyperparameters for x generations")
|
||
|
|
parser.add_argument("--bucket", type=str, default="", help="gsutil bucket")
|
||
|
|
parser.add_argument("--cache", type=str, nargs="?", const="ram", help="image --cache ram/disk")
|
||
|
|
parser.add_argument("--image-weights", action="store_true", help="use weighted image selection for training")
|
||
|
|
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
|
||
|
|
parser.add_argument("--multi-scale", action="store_true", help="vary img-size +/- 50%%")
|
||
|
|
parser.add_argument("--single-cls", action="store_true", help="train multi-class data as single-class")
|
||
|
|
parser.add_argument("--optimizer", type=str, choices=["SGD", "Adam", "AdamW"], default="SGD", help="optimizer")
|
||
|
|
parser.add_argument("--sync-bn", action="store_true", help="use SyncBatchNorm, only available in DDP mode")
|
||
|
|
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-seg", 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("--quad", action="store_true", help="quad dataloader")
|
||
|
|
parser.add_argument("--cos-lr", action="store_true", help="cosine LR scheduler")
|
||
|
|
parser.add_argument("--label-smoothing", type=float, default=0.0, help="Label smoothing epsilon")
|
||
|
|
parser.add_argument("--patience", type=int, default=100, help="EarlyStopping patience (epochs without improvement)")
|
||
|
|
parser.add_argument("--freeze", nargs="+", type=int, default=[0], help="Freeze layers: backbone=10, first3=0 1 2")
|
||
|
|
parser.add_argument("--save-period", type=int, default=-1, help="Save checkpoint every x epochs (disabled if < 1)")
|
||
|
|
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")
|
||
|
|
|
||
|
|
# Instance Segmentation Args
|
||
|
|
parser.add_argument("--mask-ratio", type=int, default=4, help="Downsample the truth masks to saving memory")
|
||
|
|
parser.add_argument("--no-overlap", action="store_true", help="Overlap masks train faster at slightly less mAP")
|
||
|
|
|
||
|
|
return parser.parse_known_args()[0] if known else parser.parse_args()
|
||
|
|
|
||
|
|
|
||
|
|
def main(opt, callbacks=Callbacks()):
|
||
|
|
"""Initializes training or evolution of YOLOv5 models based on provided configuration and options."""
|
||
|
|
if RANK in {-1, 0}:
|
||
|
|
print_args(vars(opt))
|
||
|
|
check_git_status()
|
||
|
|
check_requirements(ROOT / "requirements.txt")
|
||
|
|
|
||
|
|
# Resume
|
||
|
|
if opt.resume and not opt.evolve: # resume from specified or most recent last.pt
|
||
|
|
last = Path(check_file(opt.resume) if isinstance(opt.resume, str) else get_latest_run())
|
||
|
|
opt_yaml = last.parent.parent / "opt.yaml" # train options yaml
|
||
|
|
opt_data = opt.data # original dataset
|
||
|
|
if opt_yaml.is_file():
|
||
|
|
with open(opt_yaml, errors="ignore") as f:
|
||
|
|
d = yaml.safe_load(f)
|
||
|
|
else:
|
||
|
|
d = torch.load(last, map_location="cpu")["opt"]
|
||
|
|
opt = argparse.Namespace(**d) # replace
|
||
|
|
opt.cfg, opt.weights, opt.resume = "", str(last), True # reinstate
|
||
|
|
if is_url(opt_data):
|
||
|
|
opt.data = check_file(opt_data) # avoid HUB resume auth timeout
|
||
|
|
else:
|
||
|
|
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = (
|
||
|
|
check_file(opt.data),
|
||
|
|
check_yaml(opt.cfg),
|
||
|
|
check_yaml(opt.hyp),
|
||
|
|
str(opt.weights),
|
||
|
|
str(opt.project),
|
||
|
|
) # checks
|
||
|
|
assert len(opt.cfg) or len(opt.weights), "either --cfg or --weights must be specified"
|
||
|
|
if opt.evolve:
|
||
|
|
if opt.project == str(ROOT / "runs/train-seg"): # if default project name, rename to runs/evolve-seg
|
||
|
|
opt.project = str(ROOT / "runs/evolve-seg")
|
||
|
|
opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume
|
||
|
|
if opt.name == "cfg":
|
||
|
|
opt.name = Path(opt.cfg).stem # use model.yaml as name
|
||
|
|
opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
|
||
|
|
|
||
|
|
# DDP mode
|
||
|
|
device = select_device(opt.device, batch_size=opt.batch_size)
|
||
|
|
if LOCAL_RANK != -1:
|
||
|
|
msg = "is not compatible with YOLOv5 Multi-GPU DDP training"
|
||
|
|
assert not opt.image_weights, f"--image-weights {msg}"
|
||
|
|
assert not opt.evolve, f"--evolve {msg}"
|
||
|
|
assert opt.batch_size != -1, f"AutoBatch with --batch-size -1 {msg}, 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")
|
||
|
|
|
||
|
|
# Train
|
||
|
|
if not opt.evolve:
|
||
|
|
train(opt.hyp, opt, device, callbacks)
|
||
|
|
|
||
|
|
# Evolve hyperparameters (optional)
|
||
|
|
else:
|
||
|
|
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
|
||
|
|
meta = {
|
||
|
|
"lr0": (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||
|
|
"lrf": (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||
|
|
"momentum": (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
|
||
|
|
"weight_decay": (1, 0.0, 0.001), # optimizer weight decay
|
||
|
|
"warmup_epochs": (1, 0.0, 5.0), # warmup epochs (fractions ok)
|
||
|
|
"warmup_momentum": (1, 0.0, 0.95), # warmup initial momentum
|
||
|
|
"warmup_bias_lr": (1, 0.0, 0.2), # warmup initial bias lr
|
||
|
|
"box": (1, 0.02, 0.2), # box loss gain
|
||
|
|
"cls": (1, 0.2, 4.0), # cls loss gain
|
||
|
|
"cls_pw": (1, 0.5, 2.0), # cls BCELoss positive_weight
|
||
|
|
"obj": (1, 0.2, 4.0), # obj loss gain (scale with pixels)
|
||
|
|
"obj_pw": (1, 0.5, 2.0), # obj BCELoss positive_weight
|
||
|
|
"iou_t": (0, 0.1, 0.7), # IoU training threshold
|
||
|
|
"anchor_t": (1, 2.0, 8.0), # anchor-multiple threshold
|
||
|
|
"anchors": (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
|
||
|
|
"fl_gamma": (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
|
||
|
|
"hsv_h": (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||
|
|
"hsv_s": (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||
|
|
"hsv_v": (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||
|
|
"degrees": (1, 0.0, 45.0), # image rotation (+/- deg)
|
||
|
|
"translate": (1, 0.0, 0.9), # image translation (+/- fraction)
|
||
|
|
"scale": (1, 0.0, 0.9), # image scale (+/- gain)
|
||
|
|
"shear": (1, 0.0, 10.0), # image shear (+/- deg)
|
||
|
|
"perspective": (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||
|
|
"flipud": (1, 0.0, 1.0), # image flip up-down (probability)
|
||
|
|
"fliplr": (0, 0.0, 1.0), # image flip left-right (probability)
|
||
|
|
"mosaic": (1, 0.0, 1.0), # image mixup (probability)
|
||
|
|
"mixup": (1, 0.0, 1.0), # image mixup (probability)
|
||
|
|
"copy_paste": (1, 0.0, 1.0),
|
||
|
|
} # segment copy-paste (probability)
|
||
|
|
|
||
|
|
with open(opt.hyp, errors="ignore") as f:
|
||
|
|
hyp = yaml.safe_load(f) # load hyps dict
|
||
|
|
if "anchors" not in hyp: # anchors commented in hyp.yaml
|
||
|
|
hyp["anchors"] = 3
|
||
|
|
if opt.noautoanchor:
|
||
|
|
del hyp["anchors"], meta["anchors"]
|
||
|
|
opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch
|
||
|
|
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
|
||
|
|
evolve_yaml, evolve_csv = save_dir / "hyp_evolve.yaml", save_dir / "evolve.csv"
|
||
|
|
if opt.bucket:
|
||
|
|
# download evolve.csv if exists
|
||
|
|
subprocess.run(
|
||
|
|
[
|
||
|
|
"gsutil",
|
||
|
|
"cp",
|
||
|
|
f"gs://{opt.bucket}/evolve.csv",
|
||
|
|
str(evolve_csv),
|
||
|
|
]
|
||
|
|
)
|
||
|
|
|
||
|
|
for _ in range(opt.evolve): # generations to evolve
|
||
|
|
if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate
|
||
|
|
# Select parent(s)
|
||
|
|
parent = "single" # parent selection method: 'single' or 'weighted'
|
||
|
|
x = np.loadtxt(evolve_csv, ndmin=2, delimiter=",", skiprows=1)
|
||
|
|
n = min(5, len(x)) # number of previous results to consider
|
||
|
|
x = x[np.argsort(-fitness(x))][:n] # top n mutations
|
||
|
|
w = fitness(x) - fitness(x).min() + 1e-6 # weights (sum > 0)
|
||
|
|
if parent == "single" or len(x) == 1:
|
||
|
|
# x = x[random.randint(0, n - 1)] # random selection
|
||
|
|
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
|
||
|
|
elif parent == "weighted":
|
||
|
|
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
|
||
|
|
|
||
|
|
# Mutate
|
||
|
|
mp, s = 0.8, 0.2 # mutation probability, sigma
|
||
|
|
npr = np.random
|
||
|
|
npr.seed(int(time.time()))
|
||
|
|
g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1
|
||
|
|
ng = len(meta)
|
||
|
|
v = np.ones(ng)
|
||
|
|
while all(v == 1): # mutate until a change occurs (prevent duplicates)
|
||
|
|
v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
|
||
|
|
for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
|
||
|
|
hyp[k] = float(x[i + 12] * v[i]) # mutate
|
||
|
|
|
||
|
|
# Constrain to limits
|
||
|
|
for k, v in meta.items():
|
||
|
|
hyp[k] = max(hyp[k], v[1]) # lower limit
|
||
|
|
hyp[k] = min(hyp[k], v[2]) # upper limit
|
||
|
|
hyp[k] = round(hyp[k], 5) # significant digits
|
||
|
|
|
||
|
|
# Train mutation
|
||
|
|
results = train(hyp.copy(), opt, device, callbacks)
|
||
|
|
callbacks = Callbacks()
|
||
|
|
# Write mutation results
|
||
|
|
print_mutation(KEYS[4:16], results, hyp.copy(), save_dir, opt.bucket)
|
||
|
|
|
||
|
|
# Plot results
|
||
|
|
plot_evolve(evolve_csv)
|
||
|
|
LOGGER.info(
|
||
|
|
f'Hyperparameter evolution finished {opt.evolve} generations\n'
|
||
|
|
f"Results saved to {colorstr('bold', save_dir)}\n"
|
||
|
|
f'Usage example: $ python train.py --hyp {evolve_yaml}'
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
def run(**kwargs):
|
||
|
|
"""
|
||
|
|
Executes YOLOv5 training with given parameters, altering options programmatically; returns updated options.
|
||
|
|
|
||
|
|
Example: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
|
||
|
|
"""
|
||
|
|
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)
|