{ | |
"_name_or_path": "Visual-Attention-Network/van-base", | |
"architectures": [ | |
"VanForImageClassification" | |
], | |
"depths": [ | |
3, | |
3, | |
12, | |
3 | |
], | |
"drop_path_rate": 0.0, | |
"dropout_rate": 0.0, | |
"hidden_act": "gelu", | |
"hidden_sizes": [ | |
64, | |
128, | |
320, | |
512 | |
], | |
"id2label": { | |
"0": "event", | |
"1": "no_event" | |
}, | |
"image_size": 224, | |
"initializer_range": 0.02, | |
"label2id": { | |
"event": 0, | |
"no_event": 1 | |
}, | |
"layer_norm_eps": 1e-06, | |
"layer_scale_init_value": 0.01, | |
"mlp_ratios": [ | |
8, | |
8, | |
4, | |
4 | |
], | |
"model_type": "van", | |
"num_channels": 3, | |
"patch_sizes": [ | |
7, | |
3, | |
3, | |
3 | |
], | |
"problem_type": "single_label_classification", | |
"strides": [ | |
4, | |
2, | |
2, | |
2 | |
], | |
"torch_dtype": "float32", | |
"transformers_version": "4.23.1" | |
} | |