LorenzoSun-V
commented
1 year ago The same issue here.
Open AFallDay opened 1 year ago
LorenzoSun-V
commented
1 year ago The same issue here.
LorenzoSun-V
commented
1 year ago I comment out the code of the picture below, and the issue can be solved. But the params seem to be the same as before pruning.
AFallDay
commented
1 year ago
@LorenzoSun-V
Thanks, this does detect it, but the same parameters equate to no pruning。
AFallDay
commented
1 year ago I comment out the code of the picture below, and the issue can be solved. But the params seem to be the same as before pruning.
It seems to be in need of fine tuning, do you have the code for fine tuning please?
LorenzoSun-V
commented
1 year ago I referred to yolov7's code and tested it on yolov5-v7.0 successfully. Hope this is helpful.
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
try:
import comet_ml # must be imported before torch (if installed)
except ImportError:
comet_ml = None
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[0] # 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 val as validate # for end-of-epoch mAP
from models.experimental import attempt_load
from models.yolo import Model
from utils.autoanchor import check_anchors
from utils.autobatch import check_train_batch_size
from utils.callbacks import Callbacks
from utils.dataloaders import create_dataloader
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, methods, one_cycle, print_args, print_mutation, strip_optimizer,
yaml_save)
from utils.loggers import Loggers
from utils.loggers.comet.comet_utils import check_comet_resume
from utils.loss import ComputeLoss
from utils.metrics import fitness
from utils.plots import plot_evolve
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): # 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 = \
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
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}:
loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
# Register actions
for k in methods(loggers):
callbacks.register_action(k, callback=getattr(loggers, k))
# Process custom dataset artifact link
data_dict = loggers.remote_dataset
if resume: # If resuming runs from remote artifact
weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size
# Config
plots = not evolve and not opt.noplots # create plots
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 = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
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 = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
amp = check_amp(model) # check AMP
################################################################################
# Pruning
import torch_pruning as tp
model.eval()
print(model)
example_inputs = torch.randn(1, 3, opt.imgsz, opt.imgsz).to(device)
imp = tp.importance.MagnitudeImportance(p=2) # L2 norm pruning
ignored_layers = []
from models.yolo import Detect
for m in model.modules():
if isinstance(m, (Detect)):
ignored_layers.append(m.m)
iterative_steps = 1 # progressive pruning
pruner = tp.pruner.MagnitudePruner(
model,
example_inputs,
importance=imp,
iterative_steps=iterative_steps,
pruning_ratio=opt.target_prune_rate, # remove 50% channels, ResNet18 = {64, 128, 256, 512} => ResNet18_Half = {32, 64, 128, 256}
ignored_layers=ignored_layers,
)
base_macs, base_nparams = tp.utils.count_ops_and_params(model, example_inputs)
pruner.step()
pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(model, example_inputs)
print(model)
print("Before Pruning: MACs=%f G, #Params=%f G"%(base_macs/1e9, base_nparams/1e9))
print("After Pruning: MACs=%f G, #Params=%f G"%(pruned_macs/1e9, pruned_nparams/1e9))
####################################################################################
# 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)
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:
lf = lambda x: (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,
seed=opt.seed)
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,
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
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) # 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) # 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(3, device=device) # mean losses
if RANK != -1:
train_loader.sampler.set_epoch(epoch)
pbar = enumerate(train_loader)
LOGGER.info(('\n' + '%11s' * 7) % ('Epoch', 'GPU_mem', 'box_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, _) 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)) # loss scaled by batch_size
if RANK != -1:
loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
if opt.quad:
loss *= 4.
# 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' * 5) %
(f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths, list(mloss))
if callbacks.stop_training:
return
# 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)
# 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)
# 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')
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) # val best model with plots
if is_coco:
callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
callbacks.run('on_train_end', last, best, epoch, results)
torch.cuda.empty_cache()
return results
def parse_opt(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.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.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', 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')
parser.add_argument('--target-prune-rate', default=0.5, type=float, help='Target pruning rate')
# Logger arguments
parser.add_argument('--entity', default=None, help='Entity')
parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option')
parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval')
parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use')
return parser.parse_known_args()[0] if known else parser.parse_args()
def main(opt, callbacks=Callbacks()):
# Checks
if RANK in {-1, 0}:
print_args(vars(opt))
check_git_status()
check_requirements(ROOT / 'requirements.txt')
# Resume (from specified or most recent last.pt)
if opt.resume and not check_comet_resume(opt) and not opt.evolve:
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'): # if default project name, rename to runs/evolve
opt.project = str(ROOT / 'runs/evolve')
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 + 7] * 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
keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', 'val/box_loss',
'val/obj_loss', 'val/cls_loss')
print_mutation(keys, 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):
# Usage: 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)
I referred to yolov7's code and tested it on yolov5-v7.0 successfully. Hope this is helpful.
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 try: import comet_ml # must be imported before torch (if installed) except ImportError: comet_ml = None 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[0] # 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 val as validate # for end-of-epoch mAP from models.experimental import attempt_load from models.yolo import Model from utils.autoanchor import check_anchors from utils.autobatch import check_train_batch_size from utils.callbacks import Callbacks from utils.dataloaders import create_dataloader 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, methods, one_cycle, print_args, print_mutation, strip_optimizer, yaml_save) from utils.loggers import Loggers from utils.loggers.comet.comet_utils import check_comet_resume from utils.loss import ComputeLoss from utils.metrics import fitness from utils.plots import plot_evolve 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): # 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 = \ 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 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}: loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance # Register actions for k in methods(loggers): callbacks.register_action(k, callback=getattr(loggers, k)) # Process custom dataset artifact link data_dict = loggers.remote_dataset if resume: # If resuming runs from remote artifact weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size # Config plots = not evolve and not opt.noplots # create plots 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 = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create 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 = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create amp = check_amp(model) # check AMP ################################################################################ # Pruning import torch_pruning as tp model.eval() print(model) example_inputs = torch.randn(1, 3, opt.imgsz, opt.imgsz).to(device) imp = tp.importance.MagnitudeImportance(p=2) # L2 norm pruning ignored_layers = [] from models.yolo import Detect for m in model.modules(): if isinstance(m, (Detect)): ignored_layers.append(m.m) iterative_steps = 1 # progressive pruning pruner = tp.pruner.MagnitudePruner( model, example_inputs, importance=imp, iterative_steps=iterative_steps, pruning_ratio=opt.target_prune_rate, # remove 50% channels, ResNet18 = {64, 128, 256, 512} => ResNet18_Half = {32, 64, 128, 256} ignored_layers=ignored_layers, ) base_macs, base_nparams = tp.utils.count_ops_and_params(model, example_inputs) pruner.step() pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(model, example_inputs) print(model) print("Before Pruning: MACs=%f G, #Params=%f G"%(base_macs/1e9, base_nparams/1e9)) print("After Pruning: MACs=%f G, #Params=%f G"%(pruned_macs/1e9, pruned_nparams/1e9)) #################################################################################### # 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) 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: lf = lambda x: (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, seed=opt.seed) 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, 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 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) # 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) # 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(3, device=device) # mean losses if RANK != -1: train_loader.sampler.set_epoch(epoch) pbar = enumerate(train_loader) LOGGER.info(('\n' + '%11s' * 7) % ('Epoch', 'GPU_mem', 'box_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, _) 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)) # loss scaled by batch_size if RANK != -1: loss *= WORLD_SIZE # gradient averaged between devices in DDP mode if opt.quad: loss *= 4. # 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' * 5) % (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1])) callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths, list(mloss)) if callbacks.stop_training: return # 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) # 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) # 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') 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) # val best model with plots if is_coco: callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi) callbacks.run('on_train_end', last, best, epoch, results) torch.cuda.empty_cache() return results def parse_opt(known=False): parser = argparse.ArgumentParser() parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.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.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', 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') parser.add_argument('--target-prune-rate', default=0.5, type=float, help='Target pruning rate') # Logger arguments parser.add_argument('--entity', default=None, help='Entity') parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option') parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval') parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use') return parser.parse_known_args()[0] if known else parser.parse_args() def main(opt, callbacks=Callbacks()): # Checks if RANK in {-1, 0}: print_args(vars(opt)) check_git_status() check_requirements(ROOT / 'requirements.txt') # Resume (from specified or most recent last.pt) if opt.resume and not check_comet_resume(opt) and not opt.evolve: 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'): # if default project name, rename to runs/evolve opt.project = str(ROOT / 'runs/evolve') 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 + 7] * 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 keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', 'val/box_loss', 'val/obj_loss', 'val/cls_loss') print_mutation(keys, 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): # Usage: 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)
Thanks again, I've tried your method but find that the mAP after training is not up to the original level, any way to fine tune it? thanks
LorenzoSun-V
commented
1 year ago Try this script:
python train_after_pruning.py \
--weights ${pretrained} \
--cfg ${cfg} \
--batch-size ${bs} \
--data ${data} \
--device ${device} \
--project ${project} \
--name ${name} \
--epochs ${epochs} \
--imgsz ${imgsz} \
--target-prune-rate ${rate}--weights: path of fp32 model --cfg: cfg file of corresponding model --data: path of your dataset yaml file --imgsz: trainning image size --target-prune-rate: ratio of pruning, 0.3 or 0.5
The mAP after pruning may be lower, but not a lot. In my case, mAP@.5 is as the same as before, but mAP@.5:.95 is 1% lower.
AFallDay
commented
12 months ago Try this script:
python train_after_pruning.py \ --weights ${pretrained} \ --cfg ${cfg} \ --batch-size ${bs} \ --data ${data} \ --device ${device} \ --project ${project} \ --name ${name} \ --epochs ${epochs} \ --imgsz ${imgsz} \ --target-prune-rate ${rate}--weights: path of fp32 model --cfg: cfg file of corresponding model --data: path of your dataset yaml file --imgsz: trainning image size --target-prune-rate: ratio of pruning, 0.3 or 0.5
The mAP after pruning may be lower, but not a lot. In my case, mAP@.5 is as the same as before, but mAP@.5:.95 is 1% lower.
thanks, but I can't find the file named train_after_pruning.py, how can I get it ?please
LorenzoSun-V
commented
12 months ago Actually, just copy above code I provided to a file and name this file as "train_after_pruning.py".
max190
commented
11 months ago Try this script:
python train_after_pruning.py \ --weights ${pretrained} \ --cfg ${cfg} \ --batch-size ${bs} \ --data ${data} \ --device ${device} \ --project ${project} \ --name ${name} \ --epochs ${epochs} \ --imgsz ${imgsz} \ --target-prune-rate ${rate}--weights: path of fp32 model --cfg: cfg file of corresponding model --data: path of your dataset yaml file --imgsz: trainning image size --target-prune-rate: ratio of pruning, 0.3 or 0.5
The mAP after pruning may be lower, but not a lot. In my case, mAP@.5 is as the same as before, but mAP@.5:.95 is 1% lower.
@LorenzoSun-V thanks for the train_after_pruning script. I was having some issues in getting good accuracy in retraining after pruning in case of COCO dataset and yolov5s model architecture. Can you please tell me for what dataset and model configuration you got, mAP@.5 is as the same as before, but mAP@.5:.95 is 1% lower as you had stated. Also, in my case I trained for 100 epochs with image size 320 and target prune rate of 0.5. But my mAP did drop significantly 0.34 from 0.48 in case of reference yolov5s model.
LorenzoSun-V
commented
11 months ago @max190 , in my case, the dataset is labeled well and the task is relatively easy(just 2 classes for detection, and the features of each class are quite explicit). I suspect some important channels in your case had been pruned so your mAP was much lower even after training. Maybe you can try to use yolov5m and 0.3 pruning ratio.
maolinLiu666
commented
9 months ago @max190 , in my case, the dataset is labeled well and the task is relatively easy(just 2 classes for detection, and the features of each class are quite explicit). I suspect some important channels in your case had been pruned so your mAP was much lower even after training. Maybe you can try to use yolov5m and 0.3 pruning ratio.
@LorenzoSun-V Thank you for providing the pruning code for v5. I ran it smoothly with it, but when I used it for inference in the video, the effect became unsatisfactory, and many targets were not detected. Is there still code that needs fine-tuning? Can you provide some code for fine-tuning? Thank you for your answer. Looking forward to hearing from you
dengxiongshi
commented
2 months ago @maolinLiu666 I also got the same. Have you solved it?
happyiminjay1
commented
1 month ago @max190 , in my case, the dataset is labeled well and the task is relatively easy(just 2 classes for detection, and the features of each class are quite explicit). I suspect some important channels in your case had been pruned so your mAP was much lower even after training. Maybe you can try to use yolov5m and 0.3 pruning ratio.
@LorenzoSun-V Thank you for providing the pruning code for v5. I ran it smoothly with it, but when I used it for inference in the video, the effect became unsatisfactory, and many targets were not detected. Is there still code that needs fine-tuning? Can you provide some code for fine-tuning? Thank you for your answer. Looking forward to hearing from you
MealHunter
commented
12 hours ago I referred to yolov7's code and tested it on yolov5-v7.0 successfully. Hope this is helpful.
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 try: import comet_ml # must be imported before torch (if installed) except ImportError: comet_ml = None 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[0] # 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 val as validate # for end-of-epoch mAP from models.experimental import attempt_load from models.yolo import Model from utils.autoanchor import check_anchors from utils.autobatch import check_train_batch_size from utils.callbacks import Callbacks from utils.dataloaders import create_dataloader 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, methods, one_cycle, print_args, print_mutation, strip_optimizer, yaml_save) from utils.loggers import Loggers from utils.loggers.comet.comet_utils import check_comet_resume from utils.loss import ComputeLoss from utils.metrics import fitness from utils.plots import plot_evolve 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): # 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 = \ 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 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}: loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance # Register actions for k in methods(loggers): callbacks.register_action(k, callback=getattr(loggers, k)) # Process custom dataset artifact link data_dict = loggers.remote_dataset if resume: # If resuming runs from remote artifact weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size # Config plots = not evolve and not opt.noplots # create plots 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 = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create 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 = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create amp = check_amp(model) # check AMP ################################################################################ # Pruning import torch_pruning as tp model.eval() print(model) example_inputs = torch.randn(1, 3, opt.imgsz, opt.imgsz).to(device) imp = tp.importance.MagnitudeImportance(p=2) # L2 norm pruning ignored_layers = [] from models.yolo import Detect for m in model.modules(): if isinstance(m, (Detect)): ignored_layers.append(m.m) iterative_steps = 1 # progressive pruning pruner = tp.pruner.MagnitudePruner( model, example_inputs, importance=imp, iterative_steps=iterative_steps, pruning_ratio=opt.target_prune_rate, # remove 50% channels, ResNet18 = {64, 128, 256, 512} => ResNet18_Half = {32, 64, 128, 256} ignored_layers=ignored_layers, ) base_macs, base_nparams = tp.utils.count_ops_and_params(model, example_inputs) pruner.step() pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(model, example_inputs) print(model) print("Before Pruning: MACs=%f G, #Params=%f G"%(base_macs/1e9, base_nparams/1e9)) print("After Pruning: MACs=%f G, #Params=%f G"%(pruned_macs/1e9, pruned_nparams/1e9)) #################################################################################### # 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) 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: lf = lambda x: (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, seed=opt.seed) 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, 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 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) # 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) # 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(3, device=device) # mean losses if RANK != -1: train_loader.sampler.set_epoch(epoch) pbar = enumerate(train_loader) LOGGER.info(('\n' + '%11s' * 7) % ('Epoch', 'GPU_mem', 'box_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, _) 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)) # loss scaled by batch_size if RANK != -1: loss *= WORLD_SIZE # gradient averaged between devices in DDP mode if opt.quad: loss *= 4. # 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' * 5) % (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1])) callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths, list(mloss)) if callbacks.stop_training: return # 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) # 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) # 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') 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) # val best model with plots if is_coco: callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi) callbacks.run('on_train_end', last, best, epoch, results) torch.cuda.empty_cache() return results def parse_opt(known=False): parser = argparse.ArgumentParser() parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.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.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', 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') parser.add_argument('--target-prune-rate', default=0.5, type=float, help='Target pruning rate') # Logger arguments parser.add_argument('--entity', default=None, help='Entity') parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option') parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval') parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use') return parser.parse_known_args()[0] if known else parser.parse_args() def main(opt, callbacks=Callbacks()): # Checks if RANK in {-1, 0}: print_args(vars(opt)) check_git_status() check_requirements(ROOT / 'requirements.txt') # Resume (from specified or most recent last.pt) if opt.resume and not check_comet_resume(opt) and not opt.evolve: 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'): # if default project name, rename to runs/evolve opt.project = str(ROOT / 'runs/evolve') 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 + 7] * 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 keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', 'val/box_loss', 'val/obj_loss', 'val/cls_loss') print_mutation(keys, 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): # Usage: 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)
I want to implement breakpoint continuation of training in your code, but there is a problem that the model structure does not match the shape of the weights after pruning. I would like to ask how to solve it?
Before Pruning: MACs=1.009904 G, #Params=0.007226 G After Pruning: MACs=0.379899 G, #Params=0.002635 G image 1/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000009.jpg: 480x640 (no detections), 101.8ms image 2/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000025.jpg: 448x640 (no detections), 82.9ms image 3/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000030.jpg: 448x640 (no detections), 71.5ms image 4/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000034.jpg: 448x640 (no detections), 69.0ms image 5/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000036.jpg: 640x512 (no detections), 91.1ms image 6/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000042.jpg: 480x640 (no detections), 77.8ms image 7/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000049.jpg: 640x512 (no detections), 84.7ms image 8/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000061.jpg: 512x640 (no detections), 89.4ms image 9/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000064.jpg: 640x480 (no detections), 83.9ms image 10/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000071.jpg: 448x640 (no detections), 75.2ms image 11/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000072.jpg: 640x448 (no detections), 84.1ms image 12/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000073.jpg: 640x576 (no detections), 106.5ms image 13/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000074.jpg: 448x640 (no detections), 70.4ms image 14/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000077.jpg: 480x640 (no detections), 79.0ms image 15/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000078.jpg: 640x640 (no detections), 116.0ms image 16/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000081.jpg: 448x640 (no detections), 75.0ms image 17/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000086.jpg: 640x512 (no detections), 78.2ms image 18/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000089.jpg: 480x640 (no detections), 77.8ms image 19/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000092.jpg: 448x640 (no detections), 72.0ms image 20/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000094.jpg: 448x640 (no detections), 73.5ms image 21/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000109.jpg: 416x640 (no detections), 88.5ms image 22/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000110.jpg: 480x640 (no detections), 76.1ms image 23/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000113.jpg: 640x416 (no detections), 79.8ms image 24/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000127.jpg: 512x640 (no detections), 89.1ms image 25/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000133.jpg: 480x640 (no detections), 80.7ms image 26/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000136.jpg: 480x640 (no detections), 78.8ms image 27/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000138.jpg: 576x640 (no detections), 109.7ms image 28/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000142.jpg: 640x480 (no detections), 80.5ms image 29/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000143.jpg: 544x640 (no detections), 100.0ms image 30/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000144.jpg: 480x640 (no detections), 76.2ms image 31/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000149.jpg: 448x640 (no detections), 74.3ms image 32/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000151.jpg: 640x480 (no detections), 84.7ms image 33/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000154.jpg: 640x448 (no detections), 69.5ms image 34/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000164.jpg: 480x640 (no detections), 77.3ms image 35/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000165.jpg: 544x640 (no detections), 90.5ms image 36/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000192.jpg: 480x640 (no detections), 78.4ms image 37/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000194.jpg: 480x640 (no detections), 76.0ms image 38/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000196.jpg: 480x640 (no detections), 80.3ms image 39/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000201.jpg: 448x640 (no detections), 71.8ms image 40/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000208.jpg: 480x640 (no detections), 78.2ms image 41/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000241.jpg: 640x480 (no detections), 81.9ms image 42/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000247.jpg: 448x640 (no detections), 76.5ms image 43/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000250.jpg: 480x640 (no detections), 76.0ms image 44/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000257.jpg: 480x640 (no detections), 83.0ms image 45/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000260.jpg: 448x640 (no detections), 73.5ms image 46/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000263.jpg: 640x608 (no detections), 107.1ms image 47/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000283.jpg: 640x448 (no detections), 72.2ms image 48/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000294.jpg: 448x640 (no detections), 75.4ms image 49/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000307.jpg: 480x640 (no detections), 79.3ms image 50/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000308.jpg: 448x640 (no detections), 73.6ms image 51/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000309.jpg: 640x640 (no detections), 103.1ms image 52/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000312.jpg: 448x640 (no detections), 72.3ms image 53/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000315.jpg: 448x640 (no detections), 75.7ms image 54/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000321.jpg: 480x640 (no detections), 81.6ms image 55/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000322.jpg: 512x640 (no detections), 89.6ms image 56/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000326.jpg: 448x640 (no detections), 78.0ms image 57/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000328.jpg: 512x640 (no detections), 91.2ms image 58/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000332.jpg: 480x640 (no detections), 79.2ms image 59/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000338.jpg: 352x640 (no detections), 78.3ms image 60/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000349.jpg: 480x640 (no detections), 85.9ms image 61/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000357.jpg: 224x640 (no detections), 56.4ms image 62/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000359.jpg: 448x640 (no detections), 75.8ms image 63/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000360.jpg: 480x640 (no detections), 78.8ms image 64/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000368.jpg: 640x480 (no detections), 85.2ms image 65/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000370.jpg: 640x480 (no detections), 83.5ms image 66/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000382.jpg: 480x640 (no detections), 83.1ms image 67/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000384.jpg: 640x448 (no detections), 78.5ms image 68/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000387.jpg: 480x640 (no detections), 88.8ms image 69/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000389.jpg: 480x640 (no detections), 82.5ms image 70/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000394.jpg: 640x640 (no detections), 103.8ms image 71/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000395.jpg: 608x640 (no detections), 115.1ms image 72/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000397.jpg: 480x640 (no detections), 94.8ms image 73/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000400.jpg: 640x640 (no detections), 117.0ms image 74/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000404.jpg: 640x448 (no detections), 86.2ms image 75/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000415.jpg: 640x384 (no detections), 94.9ms image 76/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000419.jpg: 480x640 (no detections), 104.4ms image 77/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000428.jpg: 384x640 (no detections), 91.5ms image 78/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000431.jpg: 416x640 (no detections), 80.0ms image 79/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000436.jpg: 640x448 (no detections), 81.0ms image 80/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000438.jpg: 480x640 (no detections), 91.9ms image 81/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000443.jpg: 480x640 (no detections), 85.9ms image 82/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000446.jpg: 640x480 (no detections), 83.9ms image 83/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000450.jpg: 480x640 (no detections), 86.5ms image 84/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000459.jpg: 640x544 (no detections), 109.8ms image 85/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000471.jpg: 448x640 (no detections), 87.9ms image 86/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000472.jpg: 256x640 (no detections), 68.4ms image 87/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000474.jpg: 640x448 (no detections), 83.2ms image 88/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000486.jpg: 448x640 (no detections), 81.2ms image 89/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000488.jpg: 416x640 (no detections), 73.7ms image 90/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000490.jpg: 640x640 (no detections), 114.1ms image 91/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000491.jpg: 416x640 (no detections), 75.7ms image 92/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000502.jpg: 448x640 (no detections), 81.0ms image 93/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000508.jpg: 480x640 (no detections), 88.9ms image 94/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000510.jpg: 480x640 (no detections), 118.2ms image 95/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000514.jpg: 640x384 (no detections), 72.0ms image 96/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000520.jpg: 480x640 (no detections), 83.2ms image 97/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000529.jpg: 640x448 (no detections), 75.7ms image 98/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000531.jpg: 480x640 (no detections), 84.8ms image 99/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000532.jpg: 480x640 (no detections), 84.2ms image 100/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000536.jpg: 480x640 (no detections), 89.3ms image 101/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000540.jpg: 448x640 (no detections), 78.6ms image 102/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000542.jpg: 512x640 (no detections), 90.9ms image 103/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000544.jpg: 448x640 (no detections), 83.3ms image 104/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000560.jpg: 448x640 (no detections), 78.5ms image 105/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000562.jpg: 640x448 (no detections), 76.4ms image 106/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000564.jpg: 640x544 (no detections), 106.5ms image 107/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000569.jpg: 480x640 (no detections), 92.3ms image 108/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000572.jpg: 640x448 (no detections), 76.2ms image 109/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000575.jpg: 544x640 (no detections), 105.0ms image 110/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000581.jpg: 640x608 (no detections), 116.4ms image 111/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000584.jpg: 448x640 (no detections), 79.8ms image 112/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000589.jpg: 480x640 (no detections), 90.9ms image 113/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000590.jpg: 640x544 (no detections), 100.4ms image 114/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000595.jpg: 480x640 (no detections), 82.8ms image 115/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000597.jpg: 256x640 (no detections), 51.9ms image 116/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000599.jpg: 416x640 (no detections), 70.6ms image 117/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000605.jpg: 480x640 (no detections), 88.3ms image 118/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000612.jpg: 480x640 (no detections), 87.9ms image 119/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000620.jpg: 640x480 (no detections), 80.8ms image 120/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000623.jpg: 640x480 (no detections), 79.6ms image 121/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000625.jpg: 448x640 (no detections), 69.1ms image 122/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000626.jpg: 480x640 (no detections), 92.7ms image 123/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000629.jpg: 448x640 (no detections), 86.0ms image 124/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000634.jpg: 640x448 (no detections), 71.2ms image 125/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000636.jpg: 640x480 (no detections), 111.7ms image 126/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000641.jpg: 448x640 (no detections), 253.3ms image 127/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000643.jpg: 480x640 (no detections), 92.6ms image 128/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000650.jpg: 448x640 (no detections), 76.3ms Speed: 0.6ms pre-process, 86.0ms inference, 7.5ms NMS per image at shape (1, 3, 640, 640) Results saved to runs\detect\exp3