tensorflow

一文回顾 Google I/O大会

由 ╄→尐↘猪︶ㄣ 提交于 2020-12-12 09:39:30
北京时间2018年5月9日凌晨， Google I/O 2018大会在美国加州山景城拉开帷幕。当天有近 7000人来到现场。 在今天的 Keynote 中，谷歌 CEO 桑德尔·皮查伊等人介绍了谷歌一年来的多方面 AI 研究成果，例如深度学习医疗、TPU3.0、Google Duplex 等，也展示了 AI 如何全方位地融入了谷歌每一条产品线，从安卓到 Google Lens 和 Waymo。在本文中，机器之心对 Keynote 的核心内容进行了整理。 让我们看一下有哪些精彩的展示： TPU 3.0 现在正式推出TPU 3.0，相比去年发布的2.0版本，性能提升8倍，高达100 petaflops，而且由于芯片太强大，Google第一次引入液体冷却方法——对于希望为机器学习创建定制硬件的公司来说，散热越来越成为一个难题。 Google Assistant Google Assistant将提供超过13万儿童故事，新加入了针对儿童的Pretty please功能，鼓励小孩对Google Assistant进行礼貌提问。 GoogleMap GoogleMap加入了全新的AR 导航系统，当你去一些路口较多的地方，可以开启相机进行实景导航。 Google News Google News也开始和AI结合，以精准判断用户感兴趣的新闻。 根据用户的阅读偏好，Google News 还可以在

Understanding the values of summary() (Output Shape, Param#)?

由 混江龙づ霸主 提交于 2020-12-12 09:10:30
问题 I'm checking the output of summary function and don't understand all the printed values. For example, look on this simple code: x = [1, 2, 3, 4, 5] y = [1.2, 1.8, 3.5, 3.7, 5.3] model = Sequential() model.add(Dense(10, input_dim=1, activation='relu')) model.add(Dense(30, input_dim=1, activation='relu')) model.add(Dense(10, input_dim=1, activation='relu')) model.add(Dense(1)) model.summary() The output: Model: "sequential" _________________________________________________________________ Layer

Stylegan2 model with flask API is generating weird results after first request

由 时光总嘲笑我的痴心妄想 提交于 2020-12-12 08:51:29
问题 So here's whats happening. I have been using the StyleGAN2 model for a while now and I decided to make a website that will allow the user to input the arguments for the model to generate the images. The model has been trained using tensorflow v1.15 and the code works perfectly fine and generates all the required outputs when I run the model directly on my machine through the command line. The problem arises when I am now using a flask API to do the same thing. Here is all the code for

Stylegan2 model with flask API is generating weird results after first request

由 喜你入骨 提交于 2020-12-12 08:50:29
问题 So here's whats happening. I have been using the StyleGAN2 model for a while now and I decided to make a website that will allow the user to input the arguments for the model to generate the images. The model has been trained using tensorflow v1.15 and the code works perfectly fine and generates all the required outputs when I run the model directly on my machine through the command line. The problem arises when I am now using a flask API to do the same thing. Here is all the code for

Which version of python is supported in Tensorflow?

由 与世无争的帅哥 提交于 2020-12-12 08:42:55
问题 I tried to setup tensorflow for python version 3.7.1 which was not supported and ended up wasting half Sunday. I want to know which versions of python does tensorflow supports? 回答1: From the official website: Requires Python 3.4, 3.5, or 3.6 Edit: It looks like Python 3.7 is now supported with TensorFlow 1.13+ Therefore, requires Python 3.4+ for TensorFlow 1.13+ 回答2: Tensorflow, for now only works with Python 3.6, 3.7 support is still in active development, make sure to install python 3.6 and

招聘信息 | 眼控科技3个岗位招聘，AI气象研究员（30-60K·14薪）

由 家住魔仙堡 提交于 2020-12-12 07:15:59
介绍 上海眼控科技股份有限公司成立于 2009 年，是一家集计算机视觉识别与深度学习技术研发应用于一体的全球性人工智能科技企业。经过多年的极致追求与打磨，推出了一系列人工智能技术，包括：人脸识别、目标检测与识别、OCR、人体关键点检测& 姿态识别、场景语义理解、模型压缩与蒸馏、车辆与行人 ReID 和追踪等。眼控科技已成为中国领先的 AI 智慧交通、智慧气象领域解决方案提供商。 眼控科技汇聚了来自美国斯坦福大学、纽约大学、香港科技大学等国内外知名大学的顶尖 AI 人才 100 余名，先后在道路交通领域，联合公安部交通管理科学研究所、上海交大人工智能研究院建立全国首家 AI+ 道路安全监管创新中心。同时，联合华东空管局气象中心、上海交大人工智能研究院建立全国首家航空智慧气象创新中心。眼控科技在智慧道路交通、智慧航空气象垂直领域的市场占有率已位居行业领先地位，产品覆盖北京、上海、天津、河北、山东等 30 多个省市。 使命：用人工智能提供更安全更高效的交通安全解决方案 愿景：成为全球AI领域最具创新活力的企业 价值观：敬业、创新、协作、自信 眼控科技大事记： 2009年，眼控科技成立，深度探索人工智能技术； 2013年，与上海交大、公安部无锡所成立道路交通联合实验室； 2015年，探索航空气象领域AI技术研究； 2017年，道路交通安全智能监管领域市场占有率第一； 2018年

ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0',

由 荒凉一梦 提交于 2020-12-12 05:38:28
问题 System information Colab tensorflow 2.2.0 Describe the current behavior: I faced this error when i tried to solve my own data issues, which is multiple label semantic segmentations. Below is the code import tensorflow as tf import tensorflow.keras.backend as K IMG_WIDTH = 512 IMG_HEIGHT = 512 IMG_CHANNELS = 3 # batch_shape=(512,512,3) # inputs = Input(batch_shape=(4, 512, 512, 3)) #Build the model inputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS)) #s = tf.keras.layers

ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0',

由 馋奶兔 提交于 2020-12-12 05:38:20
问题 System information Colab tensorflow 2.2.0 Describe the current behavior: I faced this error when i tried to solve my own data issues, which is multiple label semantic segmentations. Below is the code import tensorflow as tf import tensorflow.keras.backend as K IMG_WIDTH = 512 IMG_HEIGHT = 512 IMG_CHANNELS = 3 # batch_shape=(512,512,3) # inputs = Input(batch_shape=(4, 512, 512, 3)) #Build the model inputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS)) #s = tf.keras.layers

Unable to understand the behavior of method `build` in tensorflow keras layers (tf.keras.layers.Layer)

由 拈花ヽ惹草 提交于 2020-12-12 04:36:18
问题 Layers in tensorflow keras have a method build that is used to defer the weights creation to a time when you have seen what the input is going to be. a layer's build method I have a few questions i have not been able to find the answer of: here it is said that If you assign a Layer instance as attribute of another Layer, the outer layer will start tracking the weights of the inner layer. What does it mean to track the weights of a layer? The same link also mentions that We recommend creating

TensorFlow model serving on Google AI Platform online prediction too slow with instance batches

由 可紊 提交于 2020-12-12 02:54:46
问题 I'm trying to deploy a TensorFlow model to Google AI Platform for Online Prediction. I'm having latency and throughput issues . The model runs on my machine in less than 1 second (with only an Intel Core I7 4790K CPU) for a single image. I deployed it to AI Platform on a machine with 8 cores and an NVIDIA T4 GPU. When running the model on AI Platform on the mentioned configuration, it takes a little less than a second when sending only one image. If I start sending many requests, each with
订阅 tensorflow