Update Readme

README.md

@@ -46,6 +46,7 @@ import torch
 import torchaudio
 
 from audioset_convnext_inf.pytorch.convnext import ConvNeXt
+from audioset_convnext_inf.utils.utilities import read_audioset_label_tags
 
 model = ConvNeXt.from_pretrained("topel/ConvNeXt-Tiny-AT", use_auth_token="ACCESS_TOKEN_GOES_HERE", map_location='cpu')
 
@@ -95,19 +96,30 @@ probs = output["clipwise_output"]
 # Equivalent: probs = torch.sigmoid(logits)
 print("probs size:", probs.size())
 
+current_dir=os.getcwd()
+lb_to_ix, ix_to_lb, id_to_ix, ix_to_id = read_audioset_label_tags(os.path.join(current_dir, "class_labels_indices.csv"))
+
 threshold = 0.25
 sample_labels = np.where(probs[0].clone().detach().cpu() > threshold)[0]
-print("Predicted labels using activity threshold 0.25:\n")
-print(sample_labels)
+print("\nPredicted labels using activity threshold 0.25:\n")
+# print(sample_labels)
+for l in sample_labels:
+    print("%s: %.3f"%(ix_to_lb[l], probs[0,l]))
 ```
 
 Output:
 ```
 logits size: torch.Size([1, 527])
 probs size: torch.Size([1, 527])
+
 Predicted labels using activity threshold 0.25:
 
-[  0 137 138 139 151 506]
+Speech: 0.626
+Music: 0.842
+Musical instrument: 0.362
+Plucked string instrument: 0.307
+Ukulele: 0.703
+Inside, small room: 0.305
 ```