add initial files

config.json

@@ -0,0 +1,289 @@
+{
+  "architectures": [
+    "FastForSceneTextRecognition"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "batch_norm_eps": 1e-05,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "conv_layer_kernel_sizes": [
+      [
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          3
+        ]
+      ],
+      [
+        [
+          3,
+          3
+        ],
+        [
+          1,
+          3
+        ],
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          1
+        ],
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        [
+          3,
+          3
+        ],
+        [
+          3,
+          1
+        ],
+        [
+          1,
+          3
+        ],
+        [
+          3,
+          3
+        ]
+      ]
+    ],
+    "conv_layer_strides": [
+      [
+        1,
+        2,
+        1
+      ],
+      [
+        2,
+        1,
+        1,
+        1
+      ],
+      [
+        2,
+        1,
+        1,
+        1
+      ],
+      [
+        2,
+        1,
+        1,
+        1
+      ]
+    ],
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      3,
+      4,
+      4,
+      4
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "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_sizes": [
+      64,
+      64,
+      128,
+      256,
+      512
+    ],
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      640,
+      640
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "textnet",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "stem_act_func": "relu",
+    "stem_kernel_size": 3,
+    "stem_num_channels": 3,
+    "stem_out_channels": 64,
+    "stem_stride": 2,
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "bbox_type": "rect",
+  "dilation": null,
+  "head_conv_dilation": 1,
+  "head_conv_groups": 1,
+  "head_conv_in_channels": 512,
+  "head_conv_kernel_size": [
+    3,
+    3
+  ],
+  "head_conv_out_channels": 128,
+  "head_conv_stride": 1,
+  "head_dropout_ratio": 0.1,
+  "head_final_act_func": null,
+  "head_final_bias": false,
+  "head_final_dilation": 1,
+  "head_final_dropout_rate": 0,
+  "head_final_groups": 1,
+  "head_final_has_shuffle": false,
+  "head_final_in_channels": 128,
+  "head_final_kernel_size": 1,
+  "head_final_ops_order": "weight",
+  "head_final_out_channels": 5,
+  "head_final_stride": 1,
+  "head_final_use_bn": false,
+  "head_pooling_size": 9,
+  "initializer_range": 0.02,
+  "loss_bg": false,
+  "min_area": 250,
+  "neck_dilation": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "neck_groups": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "neck_in_channels": [
+    64,
+    128,
+    256,
+    512
+  ],
+  "neck_kernel_size": [
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      3
+    ]
+  ],
+  "neck_out_channels": [
+    128,
+    128,
+    128,
+    128
+  ],
+  "neck_stride": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "num_channels": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "use_pretrained_backbone": null,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235007a70555b296b2a53fda088e072b90bd93093b49b3bd0324ee3e506850e7
+size 54309848

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "bbox_type": "rect",
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "FastImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "min_area": 250,
+  "pooling_size": 9,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 640
+  },
+  "size_divisor": 32
+}

textnet/config.json

@@ -0,0 +1,146 @@
+{
+  "architectures": [
+    "TextNetBackbone"
+  ],
+  "batch_norm_eps": 1e-05,
+  "conv_layer_kernel_sizes": [
+    [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ],
+    [
+      [
+        3,
+        3
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ]
+    ],
+    [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        1,
+        3
+      ]
+    ],
+    [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ]
+  ],
+  "conv_layer_strides": [
+    [
+      1,
+      2,
+      1
+    ],
+    [
+      2,
+      1,
+      1,
+      1
+    ],
+    [
+      2,
+      1,
+      1,
+      1
+    ],
+    [
+      2,
+      1,
+      1,
+      1
+    ]
+  ],
+  "depths": [
+    3,
+    4,
+    4,
+    4
+  ],
+  "hidden_sizes": [
+    64,
+    64,
+    128,
+    256,
+    512
+  ],
+  "image_size": [
+    640,
+    640
+  ],
+  "initializer_range": 0.02,
+  "model_type": "textnet",
+  "out_features": [
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "out_indices": [
+    1,
+    2,
+    3,
+    4
+  ],
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "stem_act_func": "relu",
+  "stem_kernel_size": 3,
+  "stem_num_channels": 3,
+  "stem_out_channels": 64,
+  "stem_stride": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0"
+}

textnet/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203334ca0d2f1a0f8b4dbfe2ad37f73d215ce681c25443ccdc483d845f3435cb
+size 42955744