mnist-mobilevit / config.json
akahana's picture
mnist-mobilevit
5ae3b1c verified
{
"_name_or_path": "apple/mobilevit-xx-small",
"architectures": [
"MobileViTForImageClassification"
],
"aspp_dropout_prob": 0.1,
"aspp_out_channels": 256,
"atrous_rates": [
6,
12,
18
],
"attention_probs_dropout_prob": 0.0,
"classifier_dropout_prob": 0.1,
"conv_kernel_size": 3,
"expand_ratio": 2.0,
"hidden_act": "silu",
"hidden_dropout_prob": 0.05,
"hidden_sizes": [
64,
80,
96
],
"id2label": {
"0": "0",
"1": "1",
"2": "2",
"3": "3",
"4": "4",
"5": "5",
"6": "6",
"7": "7",
"8": "8",
"9": "9"
},
"image_size": 28,
"initializer_range": 0.02,
"label2id": {
"0": "0",
"1": "1",
"2": "2",
"3": "3",
"4": "4",
"5": "5",
"6": "6",
"7": "7",
"8": "8",
"9": "9"
},
"layer_norm_eps": 1e-05,
"mlp_ratio": 2.0,
"model_type": "mobilevit",
"neck_hidden_sizes": [
16,
16,
24,
48,
64,
80,
320
],
"num_attention_heads": 4,
"num_channels": 1,
"output_stride": 32,
"patch_size": 2,
"problem_type": "single_label_classification",
"qkv_bias": true,
"semantic_loss_ignore_index": 255,
"torch_dtype": "float32",
"transformers_version": "4.42.4"
}