Spaces:
Runtime error
Runtime error
File size: 4,069 Bytes
5b93456 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import os
import torch
from tqdm import tqdm
from utils.utils import get_lr
def fit_one_epoch(model_train, model, yolo_loss, loss_history, eval_callback, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, Epoch, cuda, fp16, scaler, save_period, save_dir, local_rank=0):
loss = 0
val_loss = 0
if local_rank == 0:
print('Start Train')
pbar = tqdm(total=epoch_step,desc=f'Epoch {epoch + 1}/{Epoch}',postfix=dict,mininterval=0.3)
model_train.train()
for iteration, batch in enumerate(gen):
if iteration >= epoch_step:
break
images, targets = batch[0], batch[1]
with torch.no_grad():
if cuda:
images = images.cuda(local_rank)
targets = [ann.cuda(local_rank) for ann in targets]
optimizer.zero_grad()
if not fp16:
outputs = model_train(images)
loss_value_all = 0
for l in range(len(outputs)):
loss_item = yolo_loss(l, outputs[l], targets)
loss_value_all += loss_item
loss_value = loss_value_all
loss_value.backward()
optimizer.step()
else:
from torch.cuda.amp import autocast
with autocast():
outputs = model_train(images)
loss_value_all = 0
for l in range(len(outputs)):
loss_item = yolo_loss(l, outputs[l], targets)
loss_value_all += loss_item
loss_value = loss_value_all
scaler.scale(loss_value).backward()
scaler.step(optimizer)
scaler.update()
loss += loss_value.item()
if local_rank == 0:
pbar.set_postfix(**{'loss' : loss / (iteration + 1),
'lr' : get_lr(optimizer)})
pbar.update(1)
if local_rank == 0:
pbar.close()
print('Finish Train')
print('Start Validation')
pbar = tqdm(total=epoch_step_val, desc=f'Epoch {epoch + 1}/{Epoch}',postfix=dict,mininterval=0.3)
model_train.eval()
for iteration, batch in enumerate(gen_val):
if iteration >= epoch_step_val:
break
images, targets = batch[0], batch[1]
with torch.no_grad():
if cuda:
images = images.cuda(local_rank)
targets = [ann.cuda(local_rank) for ann in targets]
optimizer.zero_grad()
outputs = model_train(images)
loss_value_all = 0
for l in range(len(outputs)):
loss_item = yolo_loss(l, outputs[l], targets)
loss_value_all += loss_item
loss_value = loss_value_all
val_loss += loss_value.item()
if local_rank == 0:
pbar.set_postfix(**{'val_loss': val_loss / (iteration + 1)})
pbar.update(1)
if local_rank == 0:
pbar.close()
print('Finish Validation')
loss_history.append_loss(epoch + 1, loss / epoch_step, val_loss / epoch_step_val)
eval_callback.on_epoch_end(epoch + 1, model_train)
print('Epoch:'+ str(epoch + 1) + '/' + str(Epoch))
print('Total Loss: %.3f || Val Loss: %.3f ' % (loss / epoch_step, val_loss / epoch_step_val))
if (epoch + 1) % save_period == 0 or epoch + 1 == Epoch:
torch.save(model.state_dict(), os.path.join(save_dir, "ep%03d-loss%.3f-val_loss%.3f.pth" % (epoch + 1, loss / epoch_step, val_loss / epoch_step_val)))
if len(loss_history.val_loss) <= 1 or (val_loss / epoch_step_val) <= min(loss_history.val_loss):
print('Save best model to best_epoch_weights.pth')
torch.save(model.state_dict(), os.path.join(save_dir, "best_epoch_weights.pth"))
torch.save(model.state_dict(), os.path.join(save_dir, "last_epoch_weights.pth")) |