Upload ViTForImageClassification
Browse files- config.json +7 -48
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,15 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"add_fpn": false,
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
"attention_probs_dropout_prob": 0.0,
|
8 |
-
"
|
9 |
-
"auxiliary_concat_input": false,
|
10 |
-
"auxiliary_loss_weight": 0.4,
|
11 |
-
"auxiliary_num_convs": 1,
|
12 |
-
"drop_path_rate": 0.1,
|
13 |
"hidden_act": "gelu",
|
14 |
"hidden_dropout_prob": 0.0,
|
15 |
"hidden_size": 768,
|
@@ -17,49 +12,13 @@
|
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 3072,
|
19 |
"layer_norm_eps": 1e-12,
|
20 |
-
"
|
21 |
-
"model_type": "beit",
|
22 |
"num_attention_heads": 12,
|
23 |
"num_channels": 3,
|
24 |
"num_hidden_layers": 12,
|
25 |
-
"
|
26 |
-
"stage12"
|
27 |
-
],
|
28 |
-
"out_indices": [
|
29 |
-
12
|
30 |
-
],
|
31 |
-
"patch_size": 16,
|
32 |
-
"pool_scales": [
|
33 |
-
1,
|
34 |
-
2,
|
35 |
-
3,
|
36 |
-
6
|
37 |
-
],
|
38 |
"problem_type": "single_label_classification",
|
39 |
-
"
|
40 |
-
"semantic_loss_ignore_index": 255,
|
41 |
-
"stage_names": [
|
42 |
-
"stem",
|
43 |
-
"stage1",
|
44 |
-
"stage2",
|
45 |
-
"stage3",
|
46 |
-
"stage4",
|
47 |
-
"stage5",
|
48 |
-
"stage6",
|
49 |
-
"stage7",
|
50 |
-
"stage8",
|
51 |
-
"stage9",
|
52 |
-
"stage10",
|
53 |
-
"stage11",
|
54 |
-
"stage12"
|
55 |
-
],
|
56 |
"torch_dtype": "float32",
|
57 |
-
"transformers_version": "4.44.2"
|
58 |
-
"use_absolute_position_embeddings": false,
|
59 |
-
"use_auxiliary_head": true,
|
60 |
-
"use_mask_token": true,
|
61 |
-
"use_mean_pooling": true,
|
62 |
-
"use_relative_position_bias": false,
|
63 |
-
"use_shared_relative_position_bias": true,
|
64 |
-
"vocab_size": 8192
|
65 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/vit-base-patch32-224-in21k",
|
|
|
3 |
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
|
|
|
|
|
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.0,
|
10 |
"hidden_size": 768,
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
+
"model_type": "vit",
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_channels": 3,
|
18 |
"num_hidden_layers": 12,
|
19 |
+
"patch_size": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"problem_type": "single_label_classification",
|
21 |
+
"qkv_bias": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.2"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f2d99e1cc6319b09f4b651b17ee63e570c40465a4a6d0e0c19256b8dd4fe11
|
3 |
+
size 349850288
|