Hugging Face's logo

RemiHuang
/
perceiver-io-img-clf-mnist

Transformers
PyTorch
perceiver-io-image-classifier
Inference Endpoints
Model card Files Community
perceiver-io-img-clf-mnist
File size: 1,775 Bytes 
2da3395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
{
  "architectures": [
    "PerceiverImageClassifier"
  ],
  "id2label": {
    "0": 0,
    "1": 1,
    "2": 2,
    "3": 3,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 7,
    "8": 8,
    "9": 9
  },
  "label2id": {
    "0": 0,
    "1": 1,
    "2": 2,
    "3": 3,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 7,
    "8": 8,
    "9": 9
  },
  "model_config": {
    "activation_checkpointing": false,
    "activation_offloading": false,
    "decoder": {
      "cross_attention_residual": true,
      "cross_attention_widening_factor": 1,
      "dropout": 0.1,
      "freeze": false,
      "init_scale": 0.1,
      "num_classes": 10,
      "num_cross_attention_heads": 1,
      "num_cross_attention_qk_channels": null,
      "num_cross_attention_v_channels": null,
      "num_output_queries": 1,
      "num_output_query_channels": 128
    },
    "encoder": {
      "cross_attention_widening_factor": 1,
      "dropout": 0.1,
      "first_cross_attention_layer_shared": false,
      "first_self_attention_block_shared": false,
      "freeze": false,
      "image_shape": [
        28,
        28,
        1
      ],
      "init_scale": 0.1,
      "num_cross_attention_heads": 1,
      "num_cross_attention_layers": 2,
      "num_cross_attention_qk_channels": null,
      "num_cross_attention_v_channels": null,
      "num_frequency_bands": 32,
      "num_self_attention_blocks": 3,
      "num_self_attention_heads": 8,
      "num_self_attention_layers_per_block": 3,
      "num_self_attention_qk_channels": null,
      "num_self_attention_v_channels": null,
      "self_attention_widening_factor": 1
    },
    "num_latent_channels": 128,
    "num_latents": 32
  },
  "model_type": "perceiver-io-image-classifier",
  "torch_dtype": "float32",
  "transformers_version": "4.30.2"
}