Downloads · 30 days
14
5% of all-time downloads
KNTU-VC-4022-License-Plate-Recognition
AlirezaF138/KNTU-VC-4022-License-Plate-Recognition
KNTU-VC-4022-License-Plate-Recognition is a machine learning model from AlirezaF138. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for keras.
- Model: "functional1" - Layer (type) ┃ Output Shape ┃ Param ┃ - inputlayer (InputLayer) │ (None, 256, 256, 3) │ 0 │ - conv2d (Conv2D) │ (None, 256, 256, 32) │ 4,736 │ - conv2d1 (Conv2D) │ (None, 256, 256, 32) │ 50,208 │
All-time downloads
255
Public
Repo size
225 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.keras225 MB · 100%
At a glance
- Library
- keras
- Access
- Public
- Created
- Jul 15, 2024
- Updated
- Jul 15, 2024
- SHA
- 1a86e6ce
Model card
From the Hugging Face model README
- Model: "functional_1"
- Layer (type) ┃ Output Shape ┃ Param # ┃
- input_layer (InputLayer) │ (None, 256, 256, 3) │ 0 │
- conv2d (Conv2D) │ (None, 256, 256, 32) │ 4,736 │
- conv2d_1 (Conv2D) │ (None, 256, 256, 32) │ 50,208 │
- max_pooling2d (MaxPooling2D) │ (None, 64, 64, 32) │ 0 │
- conv2d_2 (Conv2D) │ (None, 64, 64, 64) │ 51,264 │
- conv2d_3 (Conv2D) │ (None, 64, 64, 64) │ 102,464 │
- max_pooling2d_1 (MaxPooling2D) │ (None, 32, 32, 64) │ 0 │
- conv2d_4 (Conv2D) │ (None, 32, 32, 128) │ 73,856 │
- conv2d_5 (Conv2D) │ (None, 32, 32, 128) │ 147,584 │
- max_pooling2d_2 (MaxPooling2D) │ (None, 16, 16, 128) │ 0 │
- conv2d_6 (Conv2D) │ (None, 16, 16, 256) │ 295,168 │
- conv2d_7 (Conv2D) │ (None, 16, 16, 256) │ 590,080 │
- max_pooling2d_3 (MaxPooling2D) │ (None, 8, 8, 256) │ 0 │
- flatten (Flatten) │ (None, 16384) │ 0 │
- dense (Dense) │ (None, 1024) │ 16,778,240 │
- dense_1 (Dense) │ (None, 512) │ 524,800 │
- dense_2 (Dense) │ (None, 256) │ 131,328 │
- dense_3 (Dense) │ (None, 128) │ 32,896 │
- dense_4 (Dense) │ (None, 8) │ 1,032 │
- Total params: 56,350,970 (214.96 MB)
- Trainable params: 18,783,656 (71.65 MB)
- Non-trainable params: 0 (0.00 B)
- Optimizer params: 37,567,314 (143.31 MB)
Test Loss: 0.001258564880117774, Test MAE: 0.018795978277921677
- Library
- keras
- Created
- Jul 15, 2024
- Updated
- Jul 15, 2024