Commit
•
908e387
1
Parent(s):
400a65f
Upload 5 files
Browse files- README.md +9 -3
- config.json +52 -0
- model.safetensors +3 -0
- preprocessor_config.json +39 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: vikp/line_detector_3
|
| 3 |
+
model-index:
|
| 4 |
+
- name: line_detector_3
|
| 5 |
+
results: []
|
| 6 |
+
license: cc-by-nc-sa-4.0
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
Text detection model for [surya](https://www.github.com/VikParuchuri/surya)
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vikp/line_detector_3",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"EfficientViTForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.0,
|
| 8 |
+
"decoder_hidden_size": 512,
|
| 9 |
+
"decoder_layer_hidden_size": 128,
|
| 10 |
+
"depths": [
|
| 11 |
+
1,
|
| 12 |
+
1,
|
| 13 |
+
1,
|
| 14 |
+
6,
|
| 15 |
+
6
|
| 16 |
+
],
|
| 17 |
+
"head_dim": 32,
|
| 18 |
+
"hidden_dropout_prob": 0.0,
|
| 19 |
+
"hidden_sizes": [
|
| 20 |
+
32,
|
| 21 |
+
64,
|
| 22 |
+
160,
|
| 23 |
+
256
|
| 24 |
+
],
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"layer_norm_eps": 1e-06,
|
| 27 |
+
"model_type": "efficientvit",
|
| 28 |
+
"num_channels": 3,
|
| 29 |
+
"num_classes": 2,
|
| 30 |
+
"num_stages": 4,
|
| 31 |
+
"patch_size": [
|
| 32 |
+
7,
|
| 33 |
+
7
|
| 34 |
+
],
|
| 35 |
+
"semantic_loss_ignore_index": -1,
|
| 36 |
+
"strides": [
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2
|
| 42 |
+
],
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.42.3",
|
| 45 |
+
"widths": [
|
| 46 |
+
32,
|
| 47 |
+
64,
|
| 48 |
+
128,
|
| 49 |
+
256,
|
| 50 |
+
512
|
| 51 |
+
]
|
| 52 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a2a74e413345541b7ca0db0cb1d41785649eb99fe6a1b5166aa8bd7c0a8881d
|
| 3 |
+
size 153827656
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"segmentation_maps",
|
| 5 |
+
"do_resize",
|
| 6 |
+
"size",
|
| 7 |
+
"resample",
|
| 8 |
+
"do_rescale",
|
| 9 |
+
"rescale_factor",
|
| 10 |
+
"do_normalize",
|
| 11 |
+
"image_mean",
|
| 12 |
+
"image_std",
|
| 13 |
+
"do_reduce_labels",
|
| 14 |
+
"return_tensors",
|
| 15 |
+
"data_format",
|
| 16 |
+
"input_data_format"
|
| 17 |
+
],
|
| 18 |
+
"do_normalize": true,
|
| 19 |
+
"do_reduce_labels": true,
|
| 20 |
+
"do_rescale": true,
|
| 21 |
+
"do_resize": true,
|
| 22 |
+
"image_mean": [
|
| 23 |
+
0.485,
|
| 24 |
+
0.456,
|
| 25 |
+
0.406
|
| 26 |
+
],
|
| 27 |
+
"image_processor_type": "SegformerImageProcessor",
|
| 28 |
+
"image_std": [
|
| 29 |
+
0.229,
|
| 30 |
+
0.224,
|
| 31 |
+
0.225
|
| 32 |
+
],
|
| 33 |
+
"resample": 2,
|
| 34 |
+
"rescale_factor": 0.00392156862745098,
|
| 35 |
+
"size": {
|
| 36 |
+
"height": 1200,
|
| 37 |
+
"width": 1200
|
| 38 |
+
}
|
| 39 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d76255a802ec614336406c974998559b5cae01b112b47ec7eab1ed39b5fdb4c
|
| 3 |
+
size 5112
|