{ "_name_or_path": "google/mobilenet_v2_1.0_224", "architectures": [ "MobileNetV2ForImageClassification" ], "classifier_dropout_prob": 0.2, "depth_divisible_by": 8, "depth_multiplier": 1.0, "expand_ratio": 6, "finegrained_output": true, "first_layer_is_expansion": true, "hidden_act": "relu6", "id2label": { "0": "calling", "1": "clapping", "10": "running", "11": "sitting", "12": "sleeping", "13": "texting", "14": "using_laptop", "2": "cycling", "3": "dancing", "4": "drinking", "5": "eating", "6": "fighting", "7": "hugging", "8": "laughing", "9": "listening_to_music" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "calling": "0", "clapping": "1", "cycling": "2", "dancing": "3", "drinking": "4", "eating": "5", "fighting": "6", "hugging": "7", "laughing": "8", "listening_to_music": "9", "running": "10", "sitting": "11", "sleeping": "12", "texting": "13", "using_laptop": "14" }, "layer_norm_eps": 0.001, "min_depth": 8, "model_type": "mobilenet_v2", "num_channels": 3, "output_stride": 32, "problem_type": "single_label_classification", "semantic_loss_ignore_index": 255, "tf_padding": true, "torch_dtype": "float32", "transformers_version": "4.41.2" }