Upload 4 files

config.json

@@ -2,202 +2,294 @@
   "architectures": [
     "FastForSceneTextRecognition"
   ],
-  "backbone_act_func": "relu",
-  "backbone_bias": false,
-  "backbone_dilation": 1,
-  "backbone_dropout_rate": 0,
-  "backbone_groups": 1,
-  "backbone_has_shuffle": false,
-  "backbone_in_channels": 3,
-  "backbone_kernel_size": 3,
-  "backbone_ops_order": "weight_bn_act",
-  "backbone_out_channels": 64,
-  "backbone_stage1_dilation": [
-    1,
-    1,
-    1
-  ],
-  "backbone_stage1_groups": [
-    1,
-    1,
-    1
-  ],
-  "backbone_stage1_in_channels": [
-    64,
-    64,
-    64
-  ],
-  "backbone_stage1_kernel_size": [
-    [
+  "backbone": null,
+  "backbone_config": {
+    "_name_or_path": "",
+    "act_func": "relu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bias": false,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
       3,
-      3
+      4,
+      4,
+      4
     ],
-    [
-      3,
-      3
+    "dilation": 1,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0,
+    "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,
+    "groups": 1,
+    "has_shuffle": false,
+    "hidden_sizes": [
+      64,
+      64,
+      128,
+      256,
+      512
     ],
-    [
-      3,
-      3
-    ]
-  ],
-  "backbone_stage1_out_channels": [
-    64,
-    64,
-    64
-  ],
-  "backbone_stage1_stride": [
-    1,
-    2,
-    1
-  ],
-  "backbone_stage2_dilation": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage2_groups": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage2_in_channels": [
-    64,
-    128,
-    128,
-    128
-  ],
-  "backbone_stage2_kernel_size": [
-    [
-      3,
-      3
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kernel_size": 3,
+    "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,
+    "ops_order": "weight_bn_act",
+    "out_channels": 64,
+    "out_features": [
+      "stage4"
     ],
-    [
+    "out_indices": [
+      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,
+    "stage1_dilation": [
       1,
-      3
+      1,
+      1
     ],
-    [
-      3,
-      3
+    "stage1_groups": [
+      1,
+      1,
+      1
     ],
-    [
-      3,
+    "stage1_in_channels": [
+      64,
+      64,
+      64
+    ],
+    "stage1_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ],
+    "stage1_out_channels": [
+      64,
+      64,
+      64
+    ],
+    "stage1_stride": [
+      1,
+      2,
       1
-    ]
-  ],
-  "backbone_stage2_out_channels": [
-    128,
-    128,
-    128,
-    128
-  ],
-  "backbone_stage2_stride": [
-    2,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage3_dilation": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage3_groups": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage3_in_channels": [
-    128,
-    256,
-    256,
-    256
-  ],
-  "backbone_stage3_kernel_size": [
-    [
-      3,
-      3
     ],
-    [
-      3,
-      3
+    "stage2_dilation": [
+      1,
+      1,
+      1,
+      1
     ],
-    [
-      3,
+    "stage2_groups": [
+      1,
+      1,
+      1,
       1
     ],
-    [
+    "stage2_in_channels": [
+      64,
+      128,
+      128,
+      128
+    ],
+    "stage2_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ]
+    ],
+    "stage2_out_channels": [
+      128,
+      128,
+      128,
+      128
+    ],
+    "stage2_stride": [
+      2,
       1,
-      3
-    ]
-  ],
-  "backbone_stage3_out_channels": [
-    256,
-    256,
-    256,
-    256
-  ],
-  "backbone_stage3_stride": [
-    2,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage4_dilation": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage4_groups": [
-    1,
-    1,
-    1,
-    1
-  ],
-  "backbone_stage4_in_channels": [
-    256,
-    512,
-    512,
-    512
-  ],
-  "backbone_stage4_kernel_size": [
-    [
-      3,
-      3
+      1,
+      1
     ],
-    [
-      3,
+    "stage3_dilation": [
+      1,
+      1,
+      1,
       1
     ],
-    [
+    "stage3_groups": [
       1,
-      3
+      1,
+      1,
+      1
     ],
-    [
-      3,
-      3
-    ]
-  ],
-  "backbone_stage4_out_channels": [
-    512,
-    512,
-    512,
-    512
-  ],
-  "backbone_stage4_stride": [
-    2,
-    1,
-    1,
-    1
-  ],
-  "backbone_stride": 2,
-  "backbone_use_bn": true,
+    "stage3_in_channels": [
+      128,
+      256,
+      256,
+      256
+    ],
+    "stage3_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        1,
+        3
+      ]
+    ],
+    "stage3_out_channels": [
+      256,
+      256,
+      256,
+      256
+    ],
+    "stage3_stride": [
+      2,
+      1,
+      1,
+      1
+    ],
+    "stage4_dilation": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "stage4_groups": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "stage4_in_channels": [
+      256,
+      512,
+      512,
+      512
+    ],
+    "stage4_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ],
+    "stage4_out_channels": [
+      512,
+      512,
+      512,
+      512
+    ],
+    "stage4_stride": [
+      2,
+      1,
+      1,
+      1
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "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,
+    "use_bn": true
+  },
   "bbox_type": "rect",
+  "dilation": null,
   "head_conv_dilation": 1,
   "head_conv_groups": 1,
   "head_conv_in_channels": 512,
@@ -272,6 +364,9 @@
     1,
     1
   ],
+  "num_channels": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0.dev0"
+  "transformers_version": "4.35.0.dev0",
+  "use_pretrained_backbone": null,
+  "use_timm_backbone": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd629ea5f65d50d52fe8390961e50e91b4956d3317aef1cb96d421bf200684f0
-size 54302648
+oid sha256:e1e25393d1a31a8b57dbb218f81b0b930fc7de741da73d20e31e8afc10dd20ee
+size 54305008