SL-CvT / config.json
LamaAldakhil's picture
Training in progress, epoch 1
05db72d
{
"_name_or_path": "microsoft/cvt-13",
"architectures": [
"CvtForImageClassification"
],
"attention_drop_rate": [
0.0,
0.0,
0.0
],
"cls_token": [
false,
false,
true
],
"depth": [
1,
2,
10
],
"drop_path_rate": [
0.0,
0.0,
0.1
],
"drop_rate": [
0.0,
0.0,
0.0
],
"embed_dim": [
64,
192,
384
],
"id2label": {
"0": "akiec",
"1": "bcc",
"2": "bkl",
"3": "df",
"4": "mel",
"5": "nv",
"6": "vasc"
},
"image_size": 224,
"initializer_range": 0.02,
"kernel_qkv": [
3,
3,
3
],
"label2id": {
"akiec": 0,
"bcc": 1,
"bkl": 2,
"df": 3,
"mel": 4,
"nv": 5,
"vasc": 6
},
"layer_norm_eps": 1e-12,
"mlp_ratio": [
4.0,
4.0,
4.0
],
"model_type": "cvt",
"num_channels": 3,
"num_heads": [
1,
3,
6
],
"num_stages": 3,
"padding_kv": [
1,
1,
1
],
"padding_q": [
1,
1,
1
],
"patch_padding": [
2,
1,
1
],
"patch_sizes": [
7,
3,
3
],
"patch_stride": [
4,
2,
2
],
"pos_embed": [
false,
false,
false
],
"problem_type": "single_label_classification",
"qkv_bias": [
true,
true,
true
],
"qkv_projection_method": [
"dw_bn",
"dw_bn",
"dw_bn"
],
"stride_kv": [
2,
2,
2
],
"stride_q": [
1,
1,
1
],
"torch_dtype": "float32",
"transformers_version": "4.29.2"
}