First, the original words of the book are quoted as follows, aiming at the concept of Deep Dream: Deep Dream is a highly interesting technology announced by Google in 2015. In a trained [convolutional neural network] , only a few parameters need to be set to generate an image through this technique. The resulting images …
The data downloaded by CIFAR-10 are all [binary] files (1) Introduction to the CIFAR-10 dataset The dataset is divided into 5 training blocks and 1 testing block, each with 10,000 images. The test block contains 1000 images randomly selected from each class. The training blocks contain these images in random order, but some training blocks …
TensorFlow learning – CIFAR-10 (python for data visualization) Read More »
#By @Kevin Xu #kevin28520@gmail.com #Youtube: https://www.youtube.com/channel/UCVCSn4qQXTDAtGWpWAe4Plw # #The aim of this project is to use TensorFlow to process our own data. # – input_data.py: read in data and generate batches # – model: build the model architecture # – training: train # I used Ubuntu with Python 3.5, TensorFlow 1.0*, other OS should also be …
Single Person Pose Detection – Picture I hereby declare that the pictures are not my own. If there is any infringement, please contact me and I will delete them. Install the package used import tensorflow as tf import tensorflow_hub as hub import cv2 from matplotlib import pyplot as plt import numpy as np import bread …
Single-person pose detectiontensorflow singlepose Read More »
Before training your own model, you need to prepare a [data set] . tfrecord is a popular data processing format for tensorflow. We need to create a data source in tfrecord format based on existing image samples. Readers can make their own tfrecord files by calling the following two .py files according to the storage …
The previous article has explained step1: How to convert your original image data into TF-Record format; (please refer to: TF-Record file production ) step2: Then use the files converted into TF-Record format to do model training on [Inception] V3 (please refer to: model fine-tune and retraining of the entire weight file ) Based on these …
In June 2017, Google opened the [TensorFlow] Object Detection API. This project uses TensorFlow to implement most deep learning object detection frameworks, including Faster R-CNN. This series of articles will (1) First introduce how to install TensorFlow Object Detection API ; [Tensorflow Object Detection API installation] First introduce how to install TensorFlow Object Detection API …
TensorFlow Learning – Tensorflow Object Detection API (3. Model Training) Read More »
In June 2017, Google opened the [TensorFlow] Object Detection API. This project uses TensorFlow to implement most deep learning object detection frameworks, including Faster R-CNN. This series of articles will (1) First introduce how to install the TensorFlow Object Detection API ; (2) Introduce how to use the trained model for object detection ; (3) …
TensorFlow Learning – Tensorflow Object Detection API (2. Object Detection) Read More »
In June 2017, Google opened the [TensorFlow] Object Detection API. This project uses TensorFlow to implement most deep learning object detection frameworks, including Faster R-CNN. This series of articles will (1) First introduce how to install the TensorFlow Object Detection API ; (2) Introduce how to use the trained model for object detection ; (3) …
TensorFlow Learning – Tensorflow Object Detection API (1. Installation) Read More »
Foreword: According to the previous article /qq_39432161/article/details/100858656 We can see that after the first training, the variable parameters w1, w2, w3 become 0.10316052, 0.10316006, 0.10315938, indicating that the training worked, and the error loss=61. After the second training, the variable parameters w1, w2, and w3 become 0.10554425, 0.10563005, 0.1056722, 28.884804, and y becomes 28.884804. Does …
Build a neural network to solve the problem of three good students Read More »