Image Classification
Transformers
PyTorch
ONNX
Inference Endpoints
frgfm commited on
Commit
e61a995
·
1 Parent(s): 6922ea8

docs: Updated README

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md CHANGED
@@ -1,3 +1,116 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - image-classification
5
+ - pytorch
6
+ - onnx
7
+ datasets:
8
+ - wildfire
9
  ---
10
+
11
+
12
+ # ReXNet-1.0x model
13
+
14
+ Pretrained on a dataset for wildfire binary classification (soon to be shared). The ReXNet architecture was introduced in [this paper](https://arxiv.org/pdf/2007.00992.pdf).
15
+
16
+
17
+ ## Model description
18
+
19
+ The core idea of the author is to add a customized Squeeze-Excitation layer in the residual blocks that will prevent channel redundancy.
20
+
21
+
22
+ ## Installation
23
+
24
+ ### Prerequisites
25
+
26
+ Python 3.6 (or higher) and [pip](https://pip.pypa.io/en/stable/)/[conda](https://docs.conda.io/en/latest/miniconda.html) are required to install PyroVision.
27
+
28
+ ### Latest stable release
29
+
30
+ You can install the last stable release of the package using [pypi](https://pypi.org/project/pyrovision/) as follows:
31
+
32
+ ```shell
33
+ pip install pyrovision
34
+ ```
35
+
36
+ or using [conda](https://anaconda.org/pyronear/pyrovision):
37
+
38
+ ```shell
39
+ conda install -c pyronear pyrovision
40
+ ```
41
+
42
+ ### Developer mode
43
+
44
+ Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source *(install [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) first)*:
45
+
46
+ ```shell
47
+ git clone https://github.com/pyronear/pyro-vision.git
48
+ pip install -e pyro-vision/.
49
+ ```
50
+
51
+
52
+ ## Usage instructions
53
+
54
+ ```python
55
+ from PIL import Image
56
+ from torchvision.transforms import Compose, ConvertImageDtype, Normalize, PILToTensor, Resize
57
+ from torchvision.transforms.functional import InterpolationMode
58
+ from pyrovision.models import model_from_hf_hub
59
+
60
+ model = model_from_hf_hub("pyronear/rexnet1_0x").eval()
61
+
62
+ img = Image.open(path_to_an_image).convert("RGB")
63
+
64
+ # Preprocessing
65
+ config = model.default_cfg
66
+ transform = Compose([
67
+ Resize(config['input_shape'][1:], interpolation=InterpolationMode.BILINEAR),
68
+ PILToTensor(),
69
+ ConvertImageDtype(torch.float32),
70
+ Normalize(config['mean'], config['std'])
71
+ ])
72
+
73
+ input_tensor = transform(img).unsqueeze(0)
74
+
75
+ # Inference
76
+ with torch.inference_mode():
77
+ output = model(input_tensor)
78
+ probs = output.squeeze(0).softmax(dim=0)
79
+ ```
80
+
81
+
82
+ ## Citation
83
+
84
+ Original paper
85
+
86
+ ```bibtex
87
+ @article{DBLP:journals/corr/abs-2007-00992,
88
+ author = {Dongyoon Han and
89
+ Sangdoo Yun and
90
+ Byeongho Heo and
91
+ Young Joon Yoo},
92
+ title = {ReXNet: Diminishing Representational Bottleneck on Convolutional Neural
93
+ Network},
94
+ journal = {CoRR},
95
+ volume = {abs/2007.00992},
96
+ year = {2020},
97
+ url = {https://arxiv.org/abs/2007.00992},
98
+ eprinttype = {arXiv},
99
+ eprint = {2007.00992},
100
+ timestamp = {Mon, 06 Jul 2020 15:26:01 +0200},
101
+ biburl = {https://dblp.org/rec/journals/corr/abs-2007-00992.bib},
102
+ bibsource = {dblp computer science bibliography, https://dblp.org}
103
+ }
104
+ ```
105
+
106
+ Source of this implementation
107
+
108
+ ```bibtex
109
+ @software{Fernandez_Holocron_2020,
110
+ author = {Fernandez, François-Guillaume},
111
+ month = {5},
112
+ title = {{Holocron}},
113
+ url = {https://github.com/frgfm/Holocron},
114
+ year = {2020}
115
+ }
116
+ ```