pymlstudio commited on
Commit
3353e17
1 Parent(s): 164922b

Push model using huggingface_hub.

Browse files
Files changed (3) hide show
  1. README.md +62 -0
  2. config.json +15 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: segmentation-models-pytorch
3
+ license: mit
4
+ pipeline_tag: image-segmentation
5
+ tags:
6
+ - model_hub_mixin
7
+ - pytorch_model_hub_mixin
8
+ - segmentation-models-pytorch
9
+ - semantic-segmentation
10
+ - pytorch
11
+ languages:
12
+ - python
13
+ ---
14
+ # FPN Model Card
15
+
16
+ Table of Contents:
17
+ - [Load trained model](#load-trained-model)
18
+ - [Model init parameters](#model-init-parameters)
19
+ - [Model metrics](#model-metrics)
20
+ - [Dataset](#dataset)
21
+
22
+ ## Load trained model
23
+ ```python
24
+ import segmentation_models_pytorch as smp
25
+
26
+ model = smp.from_pretrained("<save-directory-or-this-repo>")
27
+ ```
28
+
29
+ ## Model init parameters
30
+ ```python
31
+ model_init_params = {
32
+ "encoder_name": "resnet34",
33
+ "encoder_depth": 5,
34
+ "encoder_weights": "imagenet",
35
+ "decoder_pyramid_channels": 256,
36
+ "decoder_segmentation_channels": 128,
37
+ "decoder_merge_policy": "add",
38
+ "decoder_dropout": 0.2,
39
+ "in_channels": 3,
40
+ "classes": 12,
41
+ "activation": None,
42
+ "upsampling": 4,
43
+ "aux_params": None
44
+ }
45
+ ```
46
+
47
+ ## Model metrics
48
+ ```json
49
+ {
50
+ "test_per_image_iou": 0.7410496473312378,
51
+ "test_dataset_iou": 0.7378937005996704
52
+ }
53
+ ```
54
+
55
+ ## Dataset
56
+ Dataset name: CamVid
57
+
58
+ ## More Information
59
+ - Library: https://github.com/qubvel/segmentation_models.pytorch
60
+ - Docs: https://smp.readthedocs.io/en/latest/
61
+
62
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_model_class": "FPN",
3
+ "activation": null,
4
+ "aux_params": null,
5
+ "classes": 12,
6
+ "decoder_dropout": 0.2,
7
+ "decoder_merge_policy": "add",
8
+ "decoder_pyramid_channels": 256,
9
+ "decoder_segmentation_channels": 128,
10
+ "encoder_depth": 5,
11
+ "encoder_name": "resnet34",
12
+ "encoder_weights": "imagenet",
13
+ "in_channels": 3,
14
+ "upsampling": 4
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385b5b6b109cd3a4051666bb6d771b843fd652cb443fefe3d5a824c25bed713a
3
+ size 92720000