Upload DPTForDepthEstimation

config.json

@@ -0,0 +1,185 @@
+{
+  "_commit_hash": null,
+  "add_projection": false,
+  "architectures": [
+    "DPTForDepthEstimation"
+  ],
+  "attention_probs_dropout_prob": null,
+  "auxiliary_loss_weight": 0.4,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "add_fpn": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "auxiliary_channels": 256,
+    "auxiliary_concat_input": false,
+    "auxiliary_loss_weight": 0.4,
+    "auxiliary_num_convs": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "layer_scale_init_value": 0.1,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "beit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage6",
+      "stage12",
+      "stage18",
+      "stage24"
+    ],
+    "out_indices": [
+      6,
+      12,
+      18,
+      24
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "pool_scales": [
+      1,
+      2,
+      3,
+      6
+    ],
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "reshape_hidden_states": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "semantic_loss_ignore_index": 255,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12",
+      "stage13",
+      "stage14",
+      "stage15",
+      "stage16",
+      "stage17",
+      "stage18",
+      "stage19",
+      "stage20",
+      "stage21",
+      "stage22",
+      "stage23",
+      "stage24"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.36.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_position_embeddings": false,
+    "use_auxiliary_head": true,
+    "use_bfloat16": false,
+    "use_mask_token": false,
+    "use_mean_pooling": true,
+    "use_relative_position_bias": true,
+    "use_shared_relative_position_bias": false,
+    "vocab_size": 8192
+  },
+  "backbone_featmap_shape": null,
+  "backbone_out_indices": null,
+  "fusion_hidden_size": 256,
+  "head_in_index": -1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": null,
+  "hidden_size": 768,
+  "image_size": null,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "is_hybrid": false,
+  "layer_norm_eps": null,
+  "model_type": "dpt",
+  "neck_hidden_sizes": [
+    256,
+    512,
+    1024,
+    1024
+  ],
+  "neck_ignore_stages": [],
+  "num_attention_heads": null,
+  "num_channels": null,
+  "num_hidden_layers": null,
+  "patch_size": null,
+  "qkv_bias": null,
+  "readout_type": "project",
+  "reassemble_factors": [
+    4,
+    2,
+    1,
+    0.5
+  ],
+  "semantic_classifier_dropout": 0.1,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_auxiliary_head": true,
+  "use_batch_norm_in_fusion_residual": false,
+  "use_bias_in_fusion_residual": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8f53dd5004a5c8f33ddf8998803fcf566bfb40b8d189531ac4946d488a7364
+size 1376012724