def val_epoch(self, epoch, printer):
top1 = AverageMeter()
top5 = AverageMeter()
losses = AverageMeter()
self.model.eval()
prefetcher = data_prefetcher(self.valid_loader)
X, y = prefetcher.next()
i = 0
with torch.no_grad():
while X is not None:
N = X.size(0)
i += 1
logits = self.model(X)
loss = self.criterion(logits, y)
prec1, prec5 = accuracy(logits, y, topk=(1, 5))
losses.update(loss.item(), N)
top1.update(prec1.item(), N)
top5.update(prec5.item(), N)
if i % self.config.print_freq == 0 or i == len(
self.valid_loader) - 1:
printer(
f'Valid: Epoch: [{epoch}][{i}/{len(self.valid_loader)}]\t'
f'Step {self.steps}\t'
f'Loss {losses.avg:.4f}\t'
f'Prec@(1,5) ({top1.avg:.1%}, {top5.avg:.1%})')
X, y = prefetcher.next()
self.writer.add_scalar('val/loss', losses.avg, self.steps)
self.writer.add_scalar('val/top1', top1.avg, self.steps)
self.writer.add_scalar('val/top5', top5.avg, self.steps)
printer("Valid: [{:3d}/{}] Final Prec@1 {:.4%}".format(
epoch, self.total_epochs - 1, top1.avg))
return top1.avg
def train_epoch(self, epoch, printer=print):
top1 = AverageMeter()
top5 = AverageMeter()
losses = AverageMeter()
cur_lr = self.lr_scheduler.get_last_lr()[0]
self.model.print_alphas(self.logger)
self.model.train()
prefetcher_trn = data_prefetcher(self.train_loader)
prefetcher_val = data_prefetcher(self.valid_loader)
trn_X, trn_y = prefetcher_trn.next()
val_X, val_y = prefetcher_val.next()
i = 0
while trn_X is not None:
i += 1
N = trn_X.size(0)
self.steps += 1
# architect step (alpha)
self.alpha_optim.zero_grad()
self.architect.unrolled_backward(trn_X, trn_y, val_X, val_y,
cur_lr, self.w_optim)
self.alpha_optim.step()
# child network step (w)
self.w_optim.zero_grad()
logits = self.model(trn_X)
loss = self.model.criterion(logits, trn_y)
loss.backward()
nn.utils.clip_grad_norm_(self.model.weights(),
self.config.w_grad_clip)
self.w_optim.step()
prec1, prec5 = accuracy(logits, trn_y, topk=(1, 5))
losses.update(loss.item(), N)
top1.update(prec1.item(), N)
top5.update(prec5.item(), N)
if self.steps % self.log_step == 0:
self.writer.add_scalar('train/lr', round(cur_lr, 5),
self.steps)
self.writer.add_scalar('train/loss', loss.item(), self.steps)
self.writer.add_scalar('train/top1', prec1.item(), self.steps)
self.writer.add_scalar('train/top5', prec5.item(), self.steps)
if i % self.config.print_freq == 0 or i == len(
self.train_loader) - 1:
printer(
f'Train: Epoch: [{epoch}][{i}/{len(self.train_loader) - 1}]\t'
f'Step {self.steps}\t'
f'lr {round(cur_lr, 5)}\t'
f'Loss {losses.val:.4f} ({losses.avg:.4f})\t'
f'Prec@(1,5) ({top1.avg:.1%}, {top5.avg:.1%})\t')
trn_X, trn_y = prefetcher_trn.next()
val_X, val_y = prefetcher_val.next()
printer("Train: [{:3d}/{}] Final Prec@1 {:.4%}".format(
epoch, self.total_epochs - 1, top1.avg))
def train_epoch(self, epoch, printer=print):
top1 = AverageMeter()
top5 = AverageMeter()
losses = AverageMeter()
cur_lr = self.optimizer.param_groups[0]['lr']
self.model.train()
prefetcher = data_prefetcher(self.train_loader)
X, y = prefetcher.next()
i = 0
while X is not None:
i += 1
N = X.size(0)
self.steps += 1
logits, aux_logits = self.model(X)
loss = self.criterion(logits, y)
if self.use_aux:
loss += self.config.aux_weight * self.criterion(aux_logits, y)
self.optimizer.zero_grad()
if self.opt_level == 'O0':
loss.backward()
else:
with amp.scale_loss(loss, self.optimizer) as scaled_loss:
scaled_loss.backward()
nn.utils.clip_grad_norm_(self.model.parameters(),
self.config.grad_clip)
self.optimizer.step()
prec1, prec5 = accuracy(logits, y, topk=(1, 5))
losses.update(loss.item(), N)
top1.update(prec1.item(), N)
top5.update(prec5.item(), N)
if self.steps % self.log_step == 0 and self.rank == 0:
self.writer.add_scalar('train/lr', round(cur_lr, 5),
self.steps)
self.writer.add_scalar('train/loss', loss.item(), self.steps)
self.writer.add_scalar('train/top1', prec1.item(), self.steps)
self.writer.add_scalar('train/top5', prec5.item(), self.steps)
if self.gpu == 0 and (i % self.config.print_freq == 0
or i == len(self.train_loader) - 1):
printer(
f'Train: Epoch: [{epoch}][{i}/{len(self.train_loader) - 1}]\t'
f'Step {self.steps}\t'
f'lr {round(cur_lr, 5)}\t'
f'Loss {losses.val:.4f} ({losses.avg:.4f})\t'
f'Prec@(1,5) ({top1.avg:.1%}, {top5.avg:.1%})\t')
X, y = prefetcher.next()
if self.gpu == 0:
printer("Train: [{:3d}/{}] Final Prec@1 {:.4%}".format(
epoch, self.total_epochs - 1, top1.avg))
def validate(valid_loader, model, criterion, epoch, cur_step):
top1 = AverageMeter()
top5 = AverageMeter()
losses = AverageMeter()
model.eval()
with torch.no_grad():
for step, (X, y) in enumerate(valid_loader):
X, y = X.to(device, non_blocking=True), y.to(device,
non_blocking=True)
N = X.size(0)
logits, _ = model(X)
loss = criterion(logits, y)
prec1, prec5 = accuracy(logits, y, topk=(1, 5))
losses.update(loss.item(), N)
top1.update(prec1.item(), N)
top5.update(prec5.item(), N)
if step % config.print_freq == 0 or step == len(valid_loader) - 1:
logger.info(
"Valid: [{:3d}/{}] Step {:03d}/{:03d} Loss {losses.avg:.3f} "
"Prec@(1,5) ({top1.avg:.1%}, {top5.avg:.1%})".format(
epoch + 1,
config.epochs,
step,
len(valid_loader) - 1,
losses=losses,
top1=top1,
top5=top5))
writer.add_scalar('val/loss', losses.avg, cur_step)
writer.add_scalar('val/top1', top1.avg, cur_step)
writer.add_scalar('val/top5', top5.avg, cur_step)
logger.info("Valid: [{:3d}/{}] Final Prec@1 {:.4%}".format(
epoch + 1, config.epochs, top1.avg))
return top1.avg
def train(train_loader, model, optimizer, criterion, epoch):
top1 = AverageMeter()
top5 = AverageMeter()
losses = AverageMeter()
cur_step = epoch * len(train_loader)
cur_lr = optimizer.param_groups[0]['lr']
logger.info("Epoch {} LR {}".format(epoch, cur_lr))
writer.add_scalar('train/lr', cur_lr, cur_step)
model.train()
for step, (X, y) in enumerate(train_loader):
X, y = X.to(device, non_blocking=True), y.to(device, non_blocking=True)
N = X.size(0)
optimizer.zero_grad()
logits, aux_logits = model(X)
loss = criterion(logits, y)
if config.aux_weight > 0.:
loss += config.aux_weight * criterion(aux_logits, y)
loss.backward()
# gradient clipping
nn.utils.clip_grad_norm_(model.parameters(), config.grad_clip)
optimizer.step()
prec1, prec5 = accuracy(logits, y, topk=(1, 5))
losses.update(loss.item(), N)
top1.update(prec1.item(), N)
top5.update(prec5.item(), N)
if step % config.print_freq == 0 or step == len(train_loader) - 1:
logger.info(
"Train: [{:3d}/{}] Step {:03d}/{:03d} Loss {losses.avg:.3f} "
"Prec@(1,5) ({top1.avg:.1%}, {top5.avg:.1%})".format(
epoch + 1,
config.epochs,
step,
len(train_loader) - 1,
losses=losses,
top1=top1,
top5=top5))
writer.add_scalar('train/loss', loss.item(), cur_step)
writer.add_scalar('train/top1', prec1.item(), cur_step)
writer.add_scalar('train/top5', prec5.item(), cur_step)
cur_step += 1
logger.info("Train: [{:3d}/{}] Final Prec@1 {:.4%}".format(
epoch + 1, config.epochs, top1.avg))
img_id,
cfg.txt_data_dir,
img_scale,
img_name,
j,
classes=cfg.names_class,
conf_th=cfg.score_th,
use_orignal_scale=True)
val_preds.extend(pred_content)
if len(pred_content) > 0:
img_report_dict_algorithm[img_id[j]] = 1
else:
img_report_dict_algorithm[img_id[j]] = 0
detections += len(pred_content)
# # calc mAP
rec_total, prec_total, ap_total = AverageMeter(), AverageMeter(
), AverageMeter()
# gt_dict = parse_gt_rec(cfg.val_file, cfg.img_size, cfg.letterbox_resize)
gt_dict = parse_gt_rec_ori_scale(cfg.val_file, cfg.img_size,
cfg.letterbox_resize)
print("gt dict is", gt_dict)
print("val_preds is", val_preds)
info = ""
for ii in range(cfg.class_num):
npos, nd, rec, prec, ap = voc_eval(gt_dict,
val_preds,
ii,
iou_thres=cfg.iou_thr,
use_07_metric=cfg.use_voc_07_metric)
info += 'EVAL: Class {}: Recall: {:.4f}, Precision: {:.4f}, AP: {:.4f}\n'.format(
ii, rec, prec, ap)