Vision Deep-Learning using Tensorflow, Keras.

Related tags

Deep Learning python docker computer-vision deep-learning tensorflow detection keras python3 image-classification image-dataset-augmentation
Overview

Welcome!

I am a computer vision deep learning developer working in Korea.
This is my blog, and you can see everything I've studied here. https://www.notion.so/pervin0527

Repository configuration

Source

The codes here are generally required to use Image Classification or Object Detection API.
If there are any improvements to the code, please feel free to write them down in the Issues.

1. Image Data Augmentations

2. Image Classification

3. Object Detection

4. Competitions

5. 3D

DL_Note

It summarizes the details of machine learning and deep learning that are easier to understand.

  1. Simple Linear Regression
  2. How to minimize cost?
  3. Multi variable linear regression
  4. Logistic Regression
  5. Softmax
  6. learning rate decay, overfitting
  7. Dataset, Learning method
  8. Neural Network, XOR gate
  9. ReLU activation func
  10. weight initialization, dropout, batch normalization
  11. Convolutional Neural Network
  12. Recurrent Neural Network
You might also like...
Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Custom Keras ML block example for Edge Impulse This repository is an example on

Edge Impulse 8 Nov 2, 2022
Classification models 1D Zoo - Keras and TF.Keras

Classification models 1D Zoo - Keras and TF.Keras This repository contains 1D variants of popular CNN models for classification like ResNets, DenseNet

Roman Solovyev 12 Jan 6, 2023
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks

Amazon Forest Computer Vision Satellite Image tagging code using PyTorch / Keras Here is a sample of images we had to work with Source: https://www.ka

Mamy Ratsimbazafy 360 Dec 10, 2022
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks

Amazon Forest Computer Vision Satellite Image tagging code using PyTorch / Keras Here is a sample of images we had to work with Source: https://www.ka

Mamy Ratsimbazafy 359 Jan 5, 2023
Human head pose estimation using Keras over TensorFlow.
Human head pose estimation using Keras over TensorFlow.

RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild.

Rafael Berral Soler 71 Jan 5, 2023
Face Mask Detection on Image and Video using tensorflow and keras
Face Mask Detection on Image and Video using tensorflow and keras

Face-Mask-Detection Face Mask Detection on Image and Video using tensorflow and keras Train Neural Network on face-mask dataset using tensorflow and k

Nahid Ebrahimian 12 Nov 11, 2022
Indonesian Car License Plate Character Recognition using Tensorflow, Keras and OpenCV.

Monopol Indonesian Car License Plate (Indonesia Mobil Nomor Polisi) Character Recognition using Tensorflow, Keras and OpenCV. Background This applicat

Jayaku Briliantio 3 Apr 7, 2022
Keras like implementation of Deep Learning architectures from scratch using numpy.

Mini-Keras Keras like implementation of Deep Learning architectures from scratch using numpy. How to contribute? The project contains implementations

MANU S PILLAI 5 Oct 10, 2021
Graph Neural Networks with Keras and Tensorflow 2.

Welcome to Spektral Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The main goal of this project is to

Daniele Grattarola 2.2k Jan 8, 2023
Comments
  • detection_data_augmentation——bbox_original__IndexError: list index out of range

    detection_data_augmentation——bbox_original__IndexError: list index out of range

    A.Rotate(limit=(-90,90), border_mode=4, p=1.0),

    Traceback (most recent call last):
  File "f:/hello/a6.py", line 252, in <module>
    augmentation(image_list, xml_list, output_shape, visual)
  File "f:/hello/a6.py", line 200, in augmentation
    modify_coordinate(output_path, transformed, xml, x, output_shape)
  File "f:/hello/a6.py", line 122, in modify_coordinate
    bbox_original.find('xmin').text = str(int(bbox_mod[x][0]))
IndexError: list index out of range

    Image Size

    2048*1500

    XML

    <annotation>
	<folder>20481500NG</folder>
	<filename>NG_16.JPG</filename>
	<path>D:\hello\NG_16.JPG</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>2048</width>
		<height>1500</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>Hei</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>581</xmin>
			<ymin>467</ymin>
			<xmax>606</xmax>
			<ymax>494</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hei</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>574</xmin>
			<ymin>490</ymin>
			<xmax>580</xmax>
			<ymax>499</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1734</xmin>
			<ymin>397</ymin>
			<xmax>1743</xmax>
			<ymax>405</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hei</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1707</xmin>
			<ymin>380</ymin>
			<xmax>1717</xmax>
			<ymax>393</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hei</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1882</xmin>
			<ymin>450</ymin>
			<xmax>1893</xmax>
			<ymax>462</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1805</xmin>
			<ymin>512</ymin>
			<xmax>1814</xmax>
			<ymax>523</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1735</xmin>
			<ymin>489</ymin>
			<xmax>1745</xmax>
			<ymax>504</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1594</xmin>
			<ymin>473</ymin>
			<xmax>1605</xmax>
			<ymax>484</ymax>
		</bndbox>
	</object>
	<object>
		<name>TuCeng</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1520</xmin>
			<ymin>464</ymin>
			<xmax>1534</xmax>
			<ymax>480</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1473</xmin>
			<ymin>441</ymin>
			<xmax>1483</xmax>
			<ymax>454</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1338</xmin>
			<ymin>426</ymin>
			<xmax>1350</xmax>
			<ymax>444</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1298</xmin>
			<ymin>530</ymin>
			<xmax>1309</xmax>
			<ymax>542</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1296</xmin>
			<ymin>428</ymin>
			<xmax>1308</xmax>
			<ymax>444</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1236</xmin>
			<ymin>445</ymin>
			<xmax>1249</xmax>
			<ymax>465</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1185</xmin>
			<ymin>444</ymin>
			<xmax>1197</xmax>
			<ymax>462</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1176</xmin>
			<ymin>499</ymin>
			<xmax>1189</xmax>
			<ymax>517</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1093</xmin>
			<ymin>497</ymin>
			<xmax>1104</xmax>
			<ymax>513</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hei</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1135</xmin>
			<ymin>529</ymin>
			<xmax>1144</xmax>
			<ymax>542</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1017</xmin>
			<ymin>409</ymin>
			<xmax>1027</xmax>
			<ymax>421</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1092</xmin>
			<ymin>524</ymin>
			<xmax>1100</xmax>
			<ymax>535</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1080</xmin>
			<ymin>508</ymin>
			<xmax>1089</xmax>
			<ymax>518</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1100</xmin>
			<ymin>436</ymin>
			<xmax>1108</xmax>
			<ymax>448</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1169</xmin>
			<ymin>409</ymin>
			<xmax>1177</xmax>
			<ymax>420</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>969</xmin>
			<ymin>519</ymin>
			<xmax>979</xmax>
			<ymax>535</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>946</xmin>
			<ymin>408</ymin>
			<xmax>956</xmax>
			<ymax>418</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>957</xmin>
			<ymin>436</ymin>
			<xmax>970</xmax>
			<ymax>448</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>894</xmin>
			<ymin>402</ymin>
			<xmax>904</xmax>
			<ymax>415</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>887</xmin>
			<ymin>468</ymin>
			<xmax>897</xmax>
			<ymax>481</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>904</xmin>
			<ymin>510</ymin>
			<xmax>920</xmax>
			<ymax>521</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>784</xmin>
			<ymin>502</ymin>
			<xmax>795</xmax>
			<ymax>518</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>803</xmin>
			<ymin>449</ymin>
			<xmax>818</xmax>
			<ymax>463</ymax>
		</bndbox>
	</object>
	<object>
		<name>TuCeng</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>744</xmin>
			<ymin>415</ymin>
			<xmax>801</xmax>
			<ymax>456</ymax>
		</bndbox>
	</object>
	<object>
		<name>TuCeng</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>738</xmin>
			<ymin>482</ymin>
			<xmax>752</xmax>
			<ymax>507</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>692</xmin>
			<ymin>474</ymin>
			<xmax>705</xmax>
			<ymax>486</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>704</xmin>
			<ymin>512</ymin>
			<xmax>716</xmax>
			<ymax>525</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>687</xmin>
			<ymin>521</ymin>
			<xmax>695</xmax>
			<ymax>532</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>694</xmin>
			<ymin>537</ymin>
			<xmax>702</xmax>
			<ymax>546</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>620</xmin>
			<ymin>424</ymin>
			<xmax>632</xmax>
			<ymax>437</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>615</xmin>
			<ymin>459</ymin>
			<xmax>623</xmax>
			<ymax>472</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>509</xmin>
			<ymin>438</ymin>
			<xmax>521</xmax>
			<ymax>455</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>427</xmin>
			<ymin>497</ymin>
			<xmax>440</xmax>
			<ymax>508</ymax>
		</bndbox>
	</object>
	<object>
		<name>Dian</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>466</xmin>
			<ymin>496</ymin>
			<xmax>475</xmax>
			<ymax>506</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>381</xmin>
			<ymin>414</ymin>
			<xmax>401</xmax>
			<ymax>439</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>238</xmin>
			<ymin>426</ymin>
			<xmax>253</xmax>
			<ymax>442</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>225</xmin>
			<ymin>486</ymin>
			<xmax>234</xmax>
			<ymax>497</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>247</xmin>
			<ymin>488</ymin>
			<xmax>253</xmax>
			<ymax>498</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>204</xmin>
			<ymin>521</ymin>
			<xmax>215</xmax>
			<ymax>532</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>221</xmin>
			<ymin>524</ymin>
			<xmax>236</xmax>
			<ymax>541</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>246</xmin>
			<ymin>508</ymin>
			<xmax>257</xmax>
			<ymax>520</ymax>
		</bndbox>
	</object>
	<object>
		<name>TuCeng</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>318</xmin>
			<ymin>463</ymin>
			<xmax>335</xmax>
			<ymax>485</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>327</xmin>
			<ymin>526</ymin>
			<xmax>340</xmax>
			<ymax>540</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>293</xmin>
			<ymin>528</ymin>
			<xmax>309</xmax>
			<ymax>544</ymax>
		</bndbox>
	</object>
	<object>
		<name>Hui</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>489</xmin>
			<ymin>554</ymin>
			<xmax>498</xmax>
			<ymax>567</ymax>
		</bndbox>
	</object>
</annotation>
    opened by monkeycc 1
  • detection_data_augmentation——This file does not contain objects

    detection_data_augmentation——This file does not contain objects

    공유해 주셔서 감사합니다. 작은 문제가 발생했습니다.

    D:/hello/
├── Annotations
│ ├── xxx1.xml
│ ├── xxx2.xml
│ ├── xxx3.xml
│ | ...
├── JPEGImages
│ ├── xxx1.jpg
│ ├── xxx2.jpg
│ ├── xxx3.jpg

    if __name__ == "__main__":
    # parser = argparse.ArgumentParser(description='Detection dataset augmentation')
    # parser.add_argument('--image_path', type=str)
    # parser.add_argument('--xml_path', type=str)
    # parser.add_argument('--outpath', type=str)
    # parser.add_argument('--outshape', type=str) # split or merge
    # parser.add_argument('--num_aug', type=str, default=5)
    # parser.add_argument('--visual', type=str2bool, default=False)
    # args = parser.parse_args()

    image_set_path = "D:/hello/JPEGImages/*.jpg"
    image_list = sorted(glob.glob(image_set_path))

    xml_set_path = "D:/hello/Annotations/*.xml"
    xml_list = sorted(glob.glob(xml_set_path))
    print(len(image_list), len(xml_list))

    output_shape = "merge"
    output_path = "D:/hello/VOC/"
    aug_num = "10"
    visual = False

    
26 26
  0%|                                                                                                                                                                                | 0/26 [00:00<?, ?it/s]0 Annotations\NG_1.xml  This file does not contain objects.
1 Annotations\NG_10.xml  This file does not contain objects.
2 Annotations\NG_100.xml  This file does not contain objects.
 12%|███████████████████▍                                                                                                                                                    | 3/26 [00:00<00:00, 23.44it/s]3 Annotations\NG_101.xml  This file does not contain objects.
4 Annotations\NG_102.xml  This file does not contain objects.
5 Annotations\NG_103.xml  This file does not contain objects.
 23%|██████████████████████████████████████▊                                                                                                                                 | 6/26 [00:00<00:00, 24.69it/s]6 Annotations\NG_104.xml  This file does not contain objects.
7 Annotations\NG_105.xml  This file does not contain objects.
8 Annotations\NG_11.xml  This file does not contain objects.
 35%|██████████████████████████████████████████████████████████▏                                                                                                             | 9/26 [00:00<00:00, 25.21it/s]9 Annotations\NG_12.xml  This file does not contain objects.
10 Annotations\NG_13.xml  This file does not contain objects.
11 Annotations\NG_14.xml  This file does not contain objects.
 46%|█████████████████████████████████████████████████████████████████████████████                                                                                          | 12/26 [00:00<00:00, 25.63it/s]12 Annotations\NG_15.xml  This file does not contain objects.
13 Annotations\NG_16.xml  This file does not contain objects.
14 Annotations\NG_2.xml  This file does not contain objects.
 58%|████████████████████████████████████████████████████████████████████████████████████████████████▎                                                                      | 15/26 [00:00<00:00, 24.95it/s]15 Annotations\NG_3.xml  This file does not contain objects.
16 Annotations\NG_4.xml  This file does not contain objects.
17 Annotations\NG_5.xml  This file does not contain objects.
 69%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌                                                   | 18/26 [00:00<00:00, 25.54it/s]18 Annotations\NG_6.xml  This file does not contain objects.
19 Annotations\NG_7.xml  This file does not contain objects.
20 Annotations\NG_8.xml  This file does not contain objects.
 81%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉                                | 21/26 [00:00<00:00, 25.94it/s]21 Annotations\NG_9.xml  This file does not contain objects.
22 Annotations\OK_1.xml  This file does not contain objects.
23 Annotations\OK_2.xml  This file does not contain objects.
 92%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏            | 24/26 [00:00<00:00, 26.12it/s]24 Annotations\OK_3.xml  This file does not contain objects.
25 Annotations\OK_5.xml  This file does not contain objects.
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 26/26 [00:01<00:00, 25.66it/s] 

    
26 26
  0%|                                                                                                                                                                                | 0/26 [00:00<?, ?it/s]xml_name Annotations\NG_10010000.xml
  0%|                                                                                                                                                                                | 0/26 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "E:\anaconda3\envs\hello\lib\xml\etree\ElementTree.py", line 786, in _get_writer
    write = file_or_filename.write
AttributeError: 'str' object has no attribute 'write'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "f:/Intsoft_AI/a6.py", line 247, in <module>
    augmentation(image_list, xml_list, output_shape, visual)
  File "f:/Intsoft_AI/a6.py", line 185, in augmentation
    modify_coordinate(output_path, transformed, xml, x, output_shape)
  File "f:/Intsoft_AI/a6.py", line 132, in modify_coordinate
    tree.write(f"{output_path}/{str(idx)}/annotations/{filename}_{str(idx)}.xml")
  File "E:\anaconda3\envs\hello\lib\xml\etree\ElementTree.py", line 756, in write
    with _get_writer(file_or_filename, enc_lower) as write:
  File "E:\anaconda3\envs\hello\lib\contextlib.py", line 113, in __enter__
    return next(self.gen)
  File "E:\anaconda3\envs\hello\lib\xml\etree\ElementTree.py", line 792, in _get_writer
    file = open(file_or_filename, "w", encoding=encoding,
FileNotFoundError: [Errno 2] No such file or directory: 'D:/hello/VOC//0/annotations/Annotations\\NG_10010000_0.xml'
    opened by monkeycc 1
Owner
kimminjun
kimminjun
GitHub https://www.notion.so/pervin0527/Always-awake-932d8e6e02b243f5991078c7f890c479
Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV

Realtime Face Anti-Spoofing Detection ?? Realtime Face Anti Spoofing Detection with Face Detector to detect real and fake faces Please star this repo

Prem Kumar 86 Aug 3, 2022
QKeras: a quantization deep learning library for Tensorflow Keras

QKeras github.com/google/qkeras QKeras 0.8 highlights: Automatic quantization using QKeras; Stochastic behavior (including stochastic rouding) is disa

Google 437 Jan 3, 2023
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

MMdnn MMdnn is a comprehensive and cross-framework tool to convert, visualize and diagnose deep learning (DL) models. The "MM" stands for model manage

Microsoft 5.7k Jan 9, 2023
Advanced Deep Learning with TensorFlow 2 and Keras (Updated for 2nd Edition)

Advanced Deep Learning with TensorFlow 2 and Keras (Updated for 2nd Edition)

Packt 1.5k Jan 3, 2023
A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Convolutional Neural Network (CNN). This repository contains a source code of a deep learning network built with TensorFlow and Keras to classify gend

Pawel Dziemiach 1 Dec 18, 2021
A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Convolutional Neural Network (CNN). This repository contains a source code of a deep learning network built with TensorFlow and Keras to classify gend

Pawel Dziemiach 1 Dec 19, 2021
Keras udrl - Keras implementation of Upside Down Reinforcement Learning

keras_udrl Keras implementation of Upside Down Reinforcement Learning This is me

Eder Santana 7 Jan 24, 2022
Deep GPs built on top of TensorFlow/Keras and GPflow

GPflux Documentation | Tutorials | API reference | Slack What does GPflux do? GPflux is a toolbox dedicated to Deep Gaussian processes (DGP), the hier

Secondmind Labs 107 Nov 2, 2022
This source code is implemented using keras library based on "Automatic ocular artifacts removal in EEG using deep learning"

CSP_Deep_EEG This source code is implemented using keras library based on "Automatic ocular artifacts removal in EEG using deep learning" {https://www

Seyed Mahdi Roostaiyan 2 Nov 8, 2022
This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras)

Yogi-Optimizer_Keras This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras) The NeurIPS-Paper can be found here: http://papers.nips.c

null 14 Sep 13, 2022