If following the codelabs for Retrain an Image Classifier for New Categories (CNN network) – retrein.py (https://github.com/tensorflow/hub/raw/master/examples/image_retraining/retrain.py) training worked fine but when you runned the script label_image.py (https://github.com/tensorflow/tensorflow/raw/master/tensorflow/examples/label_image/label_image.py) to evaluate a image: python -m scripts.label_image \ –graph=tf_files/retrained_graph.pb \ –image=tf_files/flower_photos/daisy/21652746_cc379e0eea_m.jpg and You’ve got the following error: The name ‘import/input’ refers to an Operation not in the […]Read More Solved: Tensorflow’s bug: label_image.py returns error during classification
The pharmaceutical industry has recently begun using deep-learning techniques to detect drugs and predict the effects of new toxins, and the analyzes carried out prove that these methods far outweigh the effectiveness of traditional screening tests https://www.frontiersin.org/articles/10.3389/fenvs.2015.00080/fullRead More Toxicity Prediction using Deep Learning
FPGA processor: Deep Learning for security barrier camera sample to perform vehicle detection, vehicle attributes and license-plate recognition tasks.
The demo illustrates my own solution for security barrier camera sample with pre-trained models to perform vehicle detection, vehicle attributes and license-plate recognition tasks. Solution bases on Intel and dedicated for mainly FPGA, but also works on CPU, GPU processors. Software written in low-level C/C++. Please pay attention that solution extracts region of country (i.e. […]Read More FPGA processor: Deep Learning for security barrier camera sample to perform vehicle detection, vehicle attributes and license-plate recognition tasks.
Artificial Intelligence in practice – my own system to detect and recognize stuff (goods) in real time. Notice that system recognises very good also parts of used things for tests e.g. part of people body etc. Very good for detecting deficiencies(a damage of goods) on the production line in factories. Solution bases on Deep Machine […]Read More Deep Learning in practice – detection and recognising stuff (goods) in real time
Gentle Introduction to the Adam Optimization Algorithm for Deep LearningRead More Gentle Introduction to the Adam Optimization Algorithm for Deep Learning
Convolutional neural networks are indeed fascinating. Over a short period of time, they become a disruptive technology, breaking all the state-of-the-art results in multiple domains, from text, to video, to speech going well beyond the initial image processing domain where they were originally conceived https://cs231n.github.io/convolutional-networks/  – text comes from book “Deep Learning with Keras […]Read More Convolutional Neural Networks (CNNs / ConvNets)