config.json

{
  "_name_or_path": "deepmind/vision-perceiver-learned",
  "architectures": [
    "PerceiverForImageClassificationLearned"
  ],
  "attention_probs_dropout_prob": 0.1,
  "audio_samples_per_frame": 1920,
  "cross_attention_shape_for_attention": "kv",
  "cross_attention_widening_factor": 1,
  "d_latents": 64,
  "d_model": 256,
  "hidden_act": "gelu",
  "id2label": {
    "0": "AnnualCrop",
    "1": "Forest",
    "2": "HerbaceousVegetation",
    "3": "Highway",
    "4": "Industrial",
    "5": "Pasture",
    "6": "PermanentCrop",
    "7": "Residential",
    "8": "River",
    "9": "SeaLake"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "AnnualCrop": 0,
    "Forest": 1,
    "HerbaceousVegetation": 2,
    "Highway": 3,
    "Industrial": 4,
    "Pasture": 5,
    "PermanentCrop": 6,
    "Residential": 7,
    "River": 8,
    "SeaLake": 9
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 2048,
  "model_type": "perceiver",
  "num_blocks": 8,
  "num_cross_attention_heads": 1,
  "num_frames": 16,
  "num_latents": 128,
  "num_self_attends_per_block": 4,
  "num_self_attention_heads": 8,
  "output_shape": [
    1,
    16,
    224,
    224
  ],
  "problem_type": "single_label_classification",
  "qk_channels": 64,
  "samples_per_patch": 16,
  "self_attention_widening_factor": 1,
  "torch_dtype": "float32",
  "train_size": [
    368,
    496
  ],
  "transformers_version": "4.18.0",
  "use_query_residual": true,
  "v_channels": null,
  "vocab_size": 262
}