feat: first commit

detector_tester.py

@@ -0,0 +1,95 @@
+from src.sample_collector import SampleCollector
+
+# 初始化样本采集器
+collector = SampleCollector()
+
+# 添加猫叫声样本
+import os
+# sounds_dir, species = "./data/cat_sounds_2", "cat"
+sounds_dir, species = "./data/extras/dataset", "cat"
+# sounds_dir, species = "./data/dog_sounds", "dog"
+for file in os.listdir(sounds_dir):
+    if file.endswith(".wav") or file.endswith(".WAV"):
+        collector.add_sounds(os.path.join(sounds_dir, file),species)
+
+# 添加非物种叫声样本
+non_sounds_dir = "./data/non_sounds"
+for file in os.listdir(non_sounds_dir):
+    if file.endswith(".wav") or file.endswith(".WAV"):
+        collector.add_non_sounds(os.path.join(non_sounds_dir, file))
+
+# 查看样本数量
+print(collector.get_sample_counts())
+
+# from src.audio_input import AudioInput
+# from src.audio_processor import AudioProcessor
+# from src.feature_extractor import FeatureExtractor
+# from src.cat_intent_classifier_v2 import CatIntentClassifier
+# import os
+# import numpy as np
+#
+# # 初始化组件
+# audio_input = AudioInput()
+# audio_processor = AudioProcessor()
+# feature_extractor = FeatureExtractor()
+#
+# # 提取情感类别特征
+# emotions_dir = "./cat_intents/emotions"
+# emotion_embeddings = []
+# emotion_labels = []
+#
+# for emotion in os.listdir(emotions_dir):
+#     emotion_path = os.path.join(emotions_dir, emotion)
+#     if os.path.isdir(emotion_path):
+#         for file in os.listdir(emotion_path):
+#             if file.endswith(".wav") or file.endswith(".WAV"):
+#                 file_path = os.path.join(emotion_path, file)
+#                 print(f"处理情感样本: {file_path}")
+#
+#                 # 加载音频
+#                 audio_data, sample_rate = audio_input.load_from_file(file_path)
+#
+#                 # 预处理音频
+#                 processed_audio = audio_processor.preprocess(audio_data)
+#
+#                 # 准备YAMNet输入
+#                 yamnet_input = audio_processor.prepare_yamnet_input(processed_audio)
+#
+#                 # 提取特征
+#                 features = feature_extractor.process_audio(yamnet_input)
+#
+#                 # 使用平均嵌入向量
+#                 embedding_mean = np.mean(features["embeddings"], axis=0)
+#
+#                 # 添加到训练数据
+#                 emotion_embeddings.append(embedding_mean)
+#                 emotion_labels.append(emotion)
+#
+# # 训练情感分类器
+# print(f"训练情感分类器，样本数: {len(emotion_embeddings)}")
+# emotion_classifier = CatIntentClassifier()
+# emotion_history = emotion_classifier.train(
+#     np.array(emotion_embeddings),
+#     emotion_labels,
+#     epochs=100,
+#     batch_size=16
+# )
+#
+# # 保存情感分类器
+# os.makedirs("./models", exist_ok=True)
+# emotion_paths = emotion_classifier.save_model("./models", "emotions")
+# # phrases_paths = emotion_classifier.save_model("./models", "phrases")
+# print(f"情感分类器已保存: {emotion_paths}")
+
+# 类似地，训练短语分类器
+# ...（重复上述过程，但使用phrases目录）
+
+# aa = "F_BAC01_MC_MN_SIM01_101.wav, F_BAC01_MC_MN_SIM01_102.wav, F_BAC01_MC_MN_SIM01_103.wav, F_BAC01_MC_MN_SIM01_104.wav, F_BAC01_MC_MN_SIM01_105.wav, F_BAC01_MC_MN_SIM01_201.wav, F_BAC01_MC_MN_SIM01_202.wav, F_BAC01_MC_MN_SIM01_203.wav, F_BAC01_MC_MN_SIM01_301.wav, F_BAC01_MC_MN_SIM01_302.wav, F_BAC01_MC_MN_SIM01_303.wav, F_BAC01_MC_MN_SIM01_304.wav, F_BLE01_EU_FN_DEL01_101.wav, F_BLE01_EU_FN_DEL01_102.wav, F_BLE01_EU_FN_DEL01_103.wav, F_BRA01_MC_MN_SIM01_301.wav, F_BRA01_MC_MN_SIM01_302.wav, F_BRI01_MC_FI_SIM01_101.wav, F_BRI01_MC_FI_SIM01_102.wav, F_BRI01_MC_FI_SIM01_103.wav, F_BRI01_MC_FI_SIM01_104.wav, F_BRI01_MC_FI_SIM01_105.wav, F_BRI01_MC_FI_SIM01_106.wav, F_BRI01_MC_FI_SIM01_201.wav, F_BRI01_MC_FI_SIM01_202.wav, F_CAN01_EU_FN_GIA01_201.wav, F_CAN01_EU_FN_GIA01_202.wav, F_DAK01_MC_FN_SIM01_301.wav, F_DAK01_MC_FN_SIM01_302.wav, F_DAK01_MC_FN_SIM01_303.wav, F_DAK01_MC_FN_SIM01_304.wav, F_IND01_EU_FN_ELI01_101.wav, F_IND01_EU_FN_ELI01_102.wav, F_IND01_EU_FN_ELI01_103.wav, F_IND01_EU_FN_ELI01_104.wav, F_IND01_EU_FN_ELI01_201.wav, F_IND01_EU_FN_ELI01_202.wav, F_IND01_EU_FN_ELI01_203.wav, F_IND01_EU_FN_ELI01_301.wav, F_IND01_EU_FN_ELI01_302.wav, F_IND01_EU_FN_ELI01_304.wav, F_LEO01_EU_MI_RIT01_101.wav, F_LEO01_EU_MI_RIT01_102.wav, F_LEO01_EU_MI_RIT01_103.wav, F_LEO01_EU_MI_RIT01_104.wav, F_LEO01_EU_MI_RIT01_105.wav, F_MAG01_EU_FN_FED01_101.wav, F_MAG01_EU_FN_FED01_102.wav, F_MAG01_EU_FN_FED01_103.wav, F_MAG01_EU_FN_FED01_104.wav, F_MAG01_EU_FN_FED01_105.wav, F_MAG01_EU_FN_FED01_106.wav, F_MAG01_EU_FN_FED01_201.wav, F_MAG01_EU_FN_FED01_202.wav, F_MAG01_EU_FN_FED01_203.wav, F_MAG01_EU_FN_FED01_301.wav, F_MAG01_EU_FN_FED01_302.wav, F_MAG01_EU_FN_FED01_303.wav, F_MAG01_EU_FN_FED01_304.wav, F_MAG01_EU_FN_FED01_305.wav, F_MAT01_EU_FN_RIT01_101.wav, F_MAT01_EU_FN_RIT01_102.wav, F_MAT01_EU_FN_RIT01_103.wav, F_MAT01_EU_FN_RIT01_301.wav, F_MAT01_EU_FN_RIT01_302.wav, F_MAT01_EU_FN_RIT01_303.wav, F_MEG01_MC_FI_SIM01_301.wav, F_MEG01_MC_FI_SIM01_302.wav, F_MEG01_MC_FI_SIM01_303.wav, F_MEG01_MC_FI_SIM01_304.wav, F_MIN01_EU_FN_BEN01_101.wav, F_MIN01_EU_FN_BEN01_102.wav, F_MIN01_EU_FN_BEN01_103.wav, F_MIN01_EU_FN_BEN01_104.wav, F_REG01_EU_FN_GIO01_201.wav, F_SPI01_EU_MN_NAI01_101.wav, F_SPI01_EU_MN_NAI01_102.wav, F_SPI01_EU_MN_NAI01_103.wav, F_SPI01_EU_MN_NAI01_104.wav, F_SPI01_EU_MN_NAI01_201.wav, F_SPI01_EU_MN_NAI01_202.wav, F_SPI01_EU_MN_NAI01_203.wav, F_SPI01_EU_MN_NAI01_301.wav, F_WHO01_MC_FI_SIM01_101.wav, F_WHO01_MC_FI_SIM01_102.wav, F_WHO01_MC_FI_SIM01_103.wav, F_WHO01_MC_FI_SIM01_301.wav, F_WHO01_MC_FI_SIM01_302.wav, F_WHO01_MC_FI_SIM01_303.wav, F_WHO01_MC_FI_SIM01_304.wav, F_WHO01_MC_FI_SIM01_306.wav, F_WHO01_MC_FI_SIM01_307.wav"
+#
+#
+#
+# print(
+#     [{
+#         "path": f"./data/is_cat_sound_true/{dd}", "intent": "等待喂食"
+#     }  for dd in aa.split(", ")]
+# )