f"Time per epoch: {(time_epoch / 60):.2f} min",
f"Time per item: {(time_epoch / total_item):.8f} sec\n",
f"Total epochs: {len(loss)}",
f"Best epoch {min_val_loss_i + 1}\n",
f"Training loss: {loss[min_val_loss_i]:.8f}",
f"Validation loss: {min_val_loss:.8f}"
])
with open(os.path.join(output_path, "train.txt"), "w") as lg:
lg.write(t_corpus)
print(t_corpus)
elif args.test:
start_time = time.time()
predicts = model.predict_generator(
generator=dtgen.next_test_batch(),
steps=dtgen.test_steps,
use_multiprocessing=True,
verbose=1)
predicts = [dtgen.tokenizer.decode(x) for x in predicts]
total_time = time.time() - start_time
with open(os.path.join(output_path, "predict.txt"), "w") as lg:
for pd, gt in zip(predicts, dtgen.dataset["test"]["gt"]):
lg.write(f"TE_L {gt}\nTE_P {pd}\n")
evaluate = evaluation.ocr_metrics(
predicts=predicts,
ground_truth=dtgen.dataset["test"]["gt"],
norm_accentuation=False,
f"Time per item: {time_epoch / total_item}\n",
f"Best epoch {best_epoch_index + 1}",
f"Training loss: {loss[best_epoch_index]:.8f}",
f"Training accuracy: {accuracy[best_epoch_index]:.8f}\n",
f"Validation loss: {val_loss[best_epoch_index]:.8f}",
f"Validation accuracy: {val_accuracy[best_epoch_index]:.8f}"
])
with open(os.path.join(output_path, "train.txt"), "w") as lg:
lg.write(t_corpus)
print(t_corpus)
elif args.test:
start_time = datetime.datetime.now()
predicts = model.predict(x=dtgen.next_test_batch(),
steps=dtgen.steps['test'],
verbose=1)
predicts = [pp.text_standardize(x) for x in predicts]
total_time = datetime.datetime.now() - start_time
old_metric, new_metric = ev.ocr_metrics(
ground_truth=dtgen.dataset['test']['gt'],
data=dtgen.dataset['test']['dt'],
predict=predicts,
norm_accentuation=args.norm_accentuation,
norm_punctuation=args.norm_punctuation)
p_corpus, e_corpus = report(dtgen=dtgen,
predicts=predicts,
f"Time per item: {time_epoch / total_item}\n",
f"Best epoch {best_epoch_index + 1}",
f"Training loss: {loss[best_epoch_index]:.8f}",
f"Training accuracy: {accuracy[best_epoch_index]:.8f}\n",
f"Validation loss: {val_loss[best_epoch_index]:.8f}",
f"Validation accuracy: {val_accuracy[best_epoch_index]:.8f}"
])
with open(os.path.join(output_path, "train.txt"), "w") as lg:
lg.write(t_corpus)
print(t_corpus)
elif args.test:
start_time = datetime.datetime.now()
predicts = model.predict(x=dtgen.next_test_batch(), steps=dtgen.steps['test'], verbose=1)
predicts = [pp.text_standardize(x) for x in predicts]
total_time = datetime.datetime.now() - start_time
old_metric, new_metric = ev.ocr_metrics(ground_truth=dtgen.dataset['test']['gt'],
data=dtgen.dataset['test']['dt'],
predict=predicts,
norm_accentuation=args.norm_accentuation,
norm_punctuation=args.norm_punctuation)
p_corpus, e_corpus = report(dtgen=dtgen,
predicts=predicts,
metrics=[old_metric, new_metric],
total_time=total_time)
