utils.writeLogs('\n[Phase 3] : Training model')
print('| Training Epochs = ' + str(cf.num_epochs))
utils.writeLogs('| Training Epochs = ' + str(cf.num_epochs))
print('| Initial Learning Rate = ' + str(cf.lr))
utils.writeLogs('| Initial Learning Rate = ' + str(cf.lr))
print('| Optimizer = ' + str(cf.optim_type))
utils.writeLogs('| Optimizer = ' + str(cf.optim_type))
elapsed_time = 0
for epoch in range(cf.start_epoch, cf.start_epoch+cf.num_epochs):
start_time = time.time()
train(epoch)
test(epoch)
epoch_time = time.time() - start_time
elapsed_time += epoch_time
print('| Elapsed time : %d:%02d:%02d' %(cf.get_hms(elapsed_time)))
utils.writeLogs(str('| Elapsed time : %d:%02d:%02d' %(cf.get_hms(elapsed_time))))
print('\n[Phase 4] : Testing model')
utils.writeLogs('\n[Phase 4] : Testing model')
print('* Test results : Acc@1 = %.2f%%' %(best_acc))
utils.writeLogs(str('* Test results : Acc@1 = %.2f%%' %(best_acc)))
'acc': acc,
'epoch': epoch,
}
if not os.path.isdir('checkpoint'):
os.mkdir('checkpoint')
save_point = './checkpoint/' + args.dataset + os.sep
if not os.path.isdir(save_point):
os.mkdir(save_point)
torch.save(state, save_point + file_name + str(cf.num_samples) + '.t7')
best_acc = acc
print('\n[Phase 3] : Training model')
print('| Training Epochs = ' + str(cf.num_epochs))
print('| Initial Learning Rate = ' + str(cf.lr))
print('| Optimizer = ' + str(cf.optim_type))
elapsed_time = 0
for epoch in range(cf.start_epoch, cf.start_epoch + cf.num_epochs):
start_time = time.time()
train(epoch)
test(epoch)
epoch_time = time.time() - start_time
elapsed_time += epoch_time
print('| Elapsed time : %d:%02d:%02d' % (cf.get_hms(elapsed_time)))
print('\n[Phase 4] : Testing model')
print('* Test results : Acc@1 = %.2f%%' % (best_acc))
