labels=None,
transform=Compose([
LoadAudio(),
audio_transform,
DropFields(("audio", "filename", "sr")),
]),
clean_transform=Compose([
LoadAudio(),
MapLabels(class_map=class_map),
]),
),
shuffle=False,
batch_size=args.batch_size,
collate_fn=make_collate_fn(
{"signal": audio_transform.padding_value}),
**loader_kwargs)
model = TwoDimensionalCNNClassificationModel(experiment,
device=args.device)
model.load_best_model(fold)
model.eval()
val_preds = model.predict(test_loader)
all_predictions += val_preds / config.data._n_folds
result = pd.DataFrame(all_predictions,
columns=get_class_names_from_classmap(class_map))
result["fname"] = test_df.fname
result.to_csv(args.output_df, index=False)
best_metric = max(scores)
experiment.register_result("fold{}.metric".format(fold), best_metric)
torch.save(
model.state_dict(),
os.path.join(experiment.checkpoints, "fold_{}".format(fold),
"final_model.pth"))
# predictions
model.load_best_model(fold)
# validation
val_preds = model.predict(valid_loader)
val_predictions_df = pd.DataFrame(
val_preds, columns=get_class_names_from_classmap(class_map))
val_predictions_df["fname"] = train_df.fname[valid].values
val_predictions_df.to_csv(os.path.join(
experiment.predictions, "val_preds_fold_{}.csv".format(fold)),
index=False)
del val_predictions_df
# test
test_loader = torch.utils.data.DataLoader(
SoundDataset(audio_files=[
os.path.join(args.test_data_dir, fname)
for fname in test_df.fname.values
],
transform=Compose([
LoadAudio(),
STFT(n_fft=config.data.n_fft,
collate_fn=make_collate_fn({"signal": audio_transform.padding_value}),
)
all_probs = []
all_labels = []
with torch.no_grad():
for sample in loader:
signal, labels = (sample["signal"].to(args.device),
sample["labels"].to(args.device).float())
probs, nonpooled = model(signal)
all_probs.extend(probs.data.cpu().numpy())
all_labels.extend(labels.data.cpu().numpy())
all_probs = np.array(all_probs)
all_labels = np.array(all_labels)
scores = all_labels * np.expand_dims(all_probs, -1)
mean_scores = scores.sum(axis=0) / all_labels.sum(axis=0)
classnames = get_class_names_from_classmap(class_map)
pd.options.display.max_rows = 100
print()
print(pd.DataFrame({"classname": classnames, "scores": mean_scores}))