Intelligent Robot

If you have Docker 19.03 or later, a typical command to launch the container is: $ docker run --gpus all -it --rm -v local_dir:container_dir nvcr.io/nvidia/tensorflow:xx.xx-tfx-py3 If you have Docker 19.02 or earlier, a typical command to launch the container is: $ nvidia-docker run -it --rm -v local_dir:container_dir nvcr.io/nvidia/tensorflow:xx.xx-tfx-py3 https://catalog.ngc.nvidia.com/orgs/nv..

Table of Contents 1. TensorRT Overview 2. Pulling A Container 3. Running TensorRT 4. TensorRT Release 21.12 5. TensorRT Release 21.11 6. TensorRT Release 21.10 7. TensorRT Release 21.09 8. TensorRT Release 21.08 9. TensorRT Release 21.07 10. TensorRT Release 21.06 11. TensorRT Release 21.05 12. TensorRT Release 21.04 13. TensorRT Release 21.03 14. TensorRT Release 21.02 15. TensorRT Release 21.0..

tensorflow2.4.1-gpu 도커 버전에서 모델의 FPS를 체크할 때 발견한 이상현상 (2.7.0-gpu에서도 확인함) data.py 파일 안에 DataGenerator를 상속하여 만든 커스텀 클래스는 아래와 같다 import os import numpy as np from PIL import Image import tensorflow as tf class DataGenerator(tf.keras.utils.Sequence): 'Generates data for Keras' def __init__(self, img_dir, lbl_dir, batch_size=32, shuffle=False): 'Initialization' self.IDs = os.listdir(img_dir) self.IDs.s..

Implementation of neural networks - ASL Data preparation import pandas as pd import numpy as np train_df = pd.read_csv("data/sign_mnist_train.csv") valid_df = pd.read_csv("data/sign_mnist_valid.csv") train_df.head() y_train = train_df['label'] y_valid = valid_df['label'] del train_df['label'] del valid_df['label'] x_train = train_df.values x_valid = valid_df.values print(x_train.shape) print(x_v..

Implementation of neural network - MNIST Test on Google colab import torch from torch.utils.data import Dataset from torchvision import datasets from torchvision.transforms import ToTensor import matplotlib.pyplot as plt device = torch.device("cuda:0") Data preparation train_data = datasets.MNIST(root="data", train=True, download=True, transform=ToTensor()) test_data = datasets.MNIST(root="data"..

펭귄브로의 3분 딥러닝, 파이토치맛 PyTorch 코드로 맛보는 CNN, GAN, RNN, DQN, Autoencoder, ResNet, Seq2Seq, Adversarial Attack 저자: 김건우, 염상준 파이토치 코드로 맛보는 딥러닝 핵심 개념! 이 책은 파이토치로 인공지능을 구현하는 방법을 알려줍니다. 인공지능 입문자를 위한 기초 지식과 최신 인공지능 구현 방법인 인공신경망 기술을 사례를 통해 알아봅니다. 지도학습 방식의 ANN, DNN, CNN, RNN을 비롯해, 비지도학습 방식의 AE와 GAN 그리고 강화학습 DQN을 직접 구현합니다. 딥러닝의 약점을 이용해서 해킹하는 방법을 배우는 등 각 장에서 소개한 신경망으로 재미있는 응용 예제를 다룹니다. 네이버책, yes24, 교보문고, 알라딘, 영..

Tensorflow Tutorials using Jupyter Notebook TensorFlow tutorials written in Python (of course) with Jupyter Notebook. Tried to explain as kindly as possible, as these tutorials are intended for TensorFlow beginners. Hope these tutorials to be a useful recipe book for your deep learning projects. Enjoy coding! :) Contents Basics of TensorFlow / MNIST / Numpy / Image Processing / Generating Custom..

1강 Deep Learning & PyTorch 파이썬 기초 프레임워크 비교 파이토치 기본 사용법 2강 Linear Regression & Neural Network Automatic Gradient Calculation 시각화 툴 Visdom 소개 선형회귀모델 선형회귀모델의 한계 인공신경망 모델 - 2차함수근사 인공신경망 모델 - 3차함수근사 인공신경망 모델 - 2D데이터 3강 Convolutional Neural Network - Basic CNN 기본 모듈 NN으로 MNIST 풀어보기 CNN으로 MNIST 풀어보기 CNN으로 CIFAR10 풀어보기 4강 Convolutional Neural Network - Advanced Custom Data 불러오기 VGGNet 구현해보기 GoogLeNet 구현..

Advanced Deep Learning with TensorFlow 2 and Keras (Updated for 2nd Edition) This is the code repository for Advanced Deep Learning with TensorFlow 2 and Keras, published by Packt. It contains all the supporting project files necessary to work through the book from start to finish. Please note that the code examples have been updated to support TensorFlow 2.0 Keras API only. About the Book Advan..

Categorization of machine learning Supervised Learning Given a set of labeled example, D={(xt,yt)}Nt=1 , learn a mapping f:X→Y which minimizes L(Y^=f(X),Y) Classification The desired outputs yt are discrete class labels (categorical information) The goal is to classify new inputs correctly Regression The desired outputs yt are continuous values The goal is to predict the output values for new in..