Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 87386ca

Browse files
Added Traffic Recognition
1 parent 1840c06 commit 87386ca

File tree

5 files changed

+2030
-0
lines changed

5 files changed

+2030
-0
lines changed

‎Traffic_Sign_Detection/README.md

Lines changed: 41 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
# Traffic_Sign_Detection
2+
3+
Using German Traffic Sign Recognition Benchmark, in this script I have used
4+
Data Augmentation and then passed the images to miniVGGNet (VGG 7) a famous architecture of
5+
Convolutional Neural Network (CNN).
6+
7+
It contains 138 Million parameters and is a simplistic application of VGG-16 and VGG-19. In the end
8+
a model with an accuracy of 99.7 percent has been obtained.
9+
10+
## Setup
11+
12+
ALl the requirements can be found in [`requirements.txt`](requirements.txt).
13+
14+
simply use `pip install -r requirements.txt`. You can also install `tensorflow-gpu` depending upon the
15+
tensorflow version of yours, use any search engine for more information as Tensorflow-GPU
16+
is a complex and large topic in itself.
17+
18+
## Model
19+
20+
The [Jupyter Notebook](trafffic_sign_detection.ipynb) contains all the relevant information about the Model.
21+
22+
The final model named **model_final.h5** along with all the models trained can be found
23+
[here](https://drive.google.com/drive/folders/1hWeqDW0U_vxQC684in57o0-H7DZAoNo8?usp=sharing).
24+
25+
A visual flowchart of model here:
26+
27+
![model.png](https://i.postimg.cc/2yx5nypY/model.png)
28+
29+
## Database
30+
31+
I have used German Traffic Sign Recognition Benchmark Dataset or _GTSRB_, it can be downloaded from
32+
[here](https://benchmark.ini.rub.de/).
33+
34+
## Usage
35+
36+
The [Jupyter Notebook](trafffic_sign_detection.ipynb) should be referred for the Usage guidelines, while the Python
37+
[script](traffic_sign_detection.py) for a better understanding of documentation.
38+
39+
## Author
40+
41+
This Script has been prepared by [Vybhav Chaturvedi](https://github.com/vybhav72954)

‎Traffic_Sign_Detection/model_final.h5

373 KB
Binary file not shown.

‎Traffic_Sign_Detection/requirements.txt

Lines changed: 124 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,124 @@
1+
absl-py==0.11.0
2+
appdirs==1.4.4
3+
argon2-cffi==20.1.0
4+
astunparse==1.6.3
5+
async-generator==1.10
6+
attrs==20.3.0
7+
audioread==2.1.9
8+
backcall==0.2.0
9+
bleach==3.2.1
10+
cachetools==4.2.0
11+
certifi==2020年12月5日
12+
cffi==1.14.4
13+
chardet==4.0.0
14+
colorama==0.4.4
15+
cycler==0.10.0
16+
decorator==4.4.2
17+
defusedxml==0.6.0
18+
entrypoints==0.3
19+
flatbuffers==1.12
20+
gast==0.3.3
21+
google-auth==1.24.0
22+
google-auth-oauthlib==0.4.2
23+
google-pasta==0.2.0
24+
grpcio==1.32.0
25+
h5py==2.10.0
26+
idna==2.10
27+
imageio==2.9.0
28+
imgaug==0.4.0
29+
ipykernel==5.4.3
30+
ipython==7.19.0
31+
ipython-genutils==0.2.0
32+
ipywidgets==7.6.3
33+
jedi==0.18.0
34+
Jinja2==2.11.2
35+
joblib==1.0.0
36+
jsonschema==3.2.0
37+
jupyter==1.0.0
38+
jupyter-client==6.1.11
39+
jupyter-console==6.2.0
40+
jupyter-core==4.7.0
41+
jupyter-http-over-ws==0.0.8
42+
jupyterlab-pygments==0.1.2
43+
jupyterlab-widgets==1.0.0
44+
Keras==2.4.3
45+
Keras-Preprocessing==1.1.2
46+
keyboard==0.13.5
47+
kiwisolver==1.3.1
48+
librosa==0.8.0
49+
llvmlite==0.35.0
50+
Markdown==3.3.3
51+
MarkupSafe==1.1.1
52+
matplotlib==3.3.3
53+
mistune==0.8.4
54+
nbclient==0.5.1
55+
nbconvert==6.0.7
56+
nbformat==5.1.2
57+
nest-asyncio==1.4.3
58+
networkx==2.5
59+
notebook==6.2.0
60+
numba==0.52.0
61+
numpy==1.19.5
62+
oauthlib==3.1.0
63+
opencv-python==4.5.1.48
64+
opt-einsum==3.3.0
65+
packaging==20.8
66+
pandas==1.2.0
67+
pandocfilters==1.4.3
68+
parso==0.8.1
69+
pickleshare==0.7.5
70+
Pillow==8.0.1
71+
pooch==1.3.0
72+
prometheus-client==0.9.0
73+
prompt-toolkit==3.0.10
74+
protobuf==3.14.0
75+
pyasn1==0.4.8
76+
pyasn1-modules==0.2.8
77+
pycparser==2.20
78+
pydot==1.4.1
79+
Pygments==2.7.4
80+
pyparsing==2.4.7
81+
PyQt5==5.15.2
82+
PyQt5-sip==12.8.1
83+
pyrsistent==0.17.3
84+
python-dateutil==2.8.1
85+
python-speech-features==0.6
86+
pytz==2020.5
87+
PyWavelets==1.1.1
88+
pywin32==300
89+
pywinpty==0.5.7
90+
PyYAML==5.3.1
91+
pyzmq==21.0.1
92+
qtconsole==5.0.1
93+
QtPy==1.9.0
94+
requests==2.25.1
95+
requests-oauthlib==1.3.0
96+
resampy==0.2.2
97+
rsa==4.7
98+
scikit-image==0.18.1
99+
scikit-learn==0.24.0
100+
scipy==1.6.0
101+
Send2Trash==1.5.0
102+
Shapely==1.7.1
103+
six==1.15.0
104+
SoundFile==0.10.3.post1
105+
tensorboard==2.4.1
106+
tensorboard-plugin-wit==1.7.0
107+
tensorflow==2.4.1
108+
tensorflow-estimator==2.4.0
109+
tensorflow-gpu==2.4.1
110+
termcolor==1.1.0
111+
terminado==0.9.2
112+
testpath==0.4.4
113+
threadpoolctl==2.1.0
114+
tifffile==2021年2月1日
115+
tornado==6.1
116+
tqdm==4.56.0
117+
traitlets==5.0.5
118+
typing-extensions==3.7.4.3
119+
urllib3==1.26.2
120+
wcwidth==0.2.5
121+
webencodings==0.5.1
122+
Werkzeug==1.0.1
123+
widgetsnbextension==3.5.1
124+
wrapt==1.12.1

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /