Update DPTNet_eval/DPTNet_quant_sep.py

DPTNet_eval/DPTNet_quant_sep.py

@@ -46,49 +46,47 @@ def get_conf():
 def load_dpt_model():
     print('Load Separation Model...')
 
-    # 從環境變數取得 Secret Token
     speech_sep_token = os.getenv("SpeechSeparation")
     if not speech_sep_token:
         raise EnvironmentError("環境變數 SpeechSeparation 未設定！")
 
-    # 從 HF Hub 下載模型權重
     model_path = hf_hub_download(
         repo_id="DeepLearning101/speech-separation",
         filename="train_dptnet_aishell_partOverlap_B2_300epoch_quan-int8.p",
         token=speech_sep_token
     )
 
-    # 取得模型參數
     conf_filterbank, conf_masknet = get_conf()
 
-    # 建立模型架構（⚠️ 這邊要與訓練時完全一樣）
     try:
         model_class = getattr(asteroid_test, "DPTNet")
         model = model_class(**conf_filterbank, **conf_masknet)
     except Exception as e:
         raise RuntimeError("模型結構錯誤：請確認 asteroid_test.py 是否與訓練時相同") from e
 
-    # 套用量化設定
-    try:
-        model = torch.quantization.quantize_dynamic(
-            model,
-            {torch.nn.LSTM, torch.nn.Linear},
-            dtype=torch.qint8
-        )
-    except Exception as e:
-        print("量化設定失敗:", e)
+    model = torch.quantization.quantize_dynamic(
+        model,
+        {torch.nn.LSTM, torch.nn.Linear},
+        dtype=torch.qint8
+    )
 
-    # 載入權重（忽略不匹配的 keys）
     state_dict = torch.load(model_path, map_location="cpu")
     own_state = model.state_dict()
-    filtered_state_dict = {
-        k: v for k, v in state_dict.items() if k in own_state and v.shape == own_state[k].shape
-    }
 
-    # 忽略找不到的 keys，也不強制要求全部 match
+    # 只保留是 torch.Tensor 的 key-value pairs
+    filtered_state_dict = {}
+    for k, v in state_dict.items():
+        if k in own_state:
+            if isinstance(v, torch.Tensor) and isinstance(own_state[k], torch.Tensor):
+                if v.shape == own_state[k].shape:
+                    filtered_state_dict[k] = v
+                else:
+                    print(f"Skip '{k}': shape mismatch")
+            else:
+                print(f"Skip '{k}': not a tensor")
+
     missing_keys, unexpected_keys = model.load_state_dict(filtered_state_dict, strict=False)
 
-    # 印出警告訊息方便除錯
     if missing_keys:
         print("⚠️ Missing keys:", missing_keys)
     if unexpected_keys: