TensorFlow has been used before, but once Keras is used, it immediately encircles it, and Keras is very refined in the encapsulation of functions.Code first import module import numpy as np import keras from keras.models import Sequential from keras.layers import Dense, Dropout, Flatten from keras.layers import Conv2D, MaxPooling2D from keras.preprocessing.image import ImageDataGenerator from keras.callbacks import ReduceLROnPlateau from keras.callbacks import TensorBoard from keras.callbacks import ModelCheckpoint from keras.models import load_model import os
1. Keras has two types of Models, Sequential model and functional model. Functional model is more widely used. sequential model is a special case of functional model. Some methods are the same for the two types of models: · model.summary (): print out the overview of the model, which actually calls keras.utils.print_summary -model. get _ config (): returns a Python dictionary containing model configuration information.The model can also be reconstructed
use model.save(filepath) to save the Keras model and weights in an HDF5 file that will contain: model structure to reconstruct the model model weight training configuration (loss function, optimizer, etc.) The state of the optimizer to start where the last training was interrupted. Use Keras. Models. Load _ Model (FilePath) to re-instantiate your model. If the training configuration is stored in the file, the function will also compile the model
Python machine learning library scikit-learn practice
Machine learning algorithms have become "well known" under the influence of big data in recent years. Even if you don't know each algorithm theory and call you one or two famous algorithms, you can blurt it out with your head held high.Of course, although the forest of algorithms is large, there are still limited means.
Starting from this part, I mainly share the basic experience and main harvest of learning sklearn library. 1. Basic Usage of Datasets Take the use of handwritten data sets as an example use fromsklearn.datasetimportload _ digits to load datasets parameters return_X_y: the default is false, which means all the information (data and target) of the data is returned in the form of a dictionary;If True, the data is returned as
task Congratulations on your successful internship in a financial company.
On your first day at work, you are still excited.At this moment, the supervisor called you over and showed you a document.
The contents of the file look like this:
The supervisor said this is the company's valuable data asset.I urge you to read carefully and find out the rules from the figures so as to make a wise Foreign currency loans.
Visio Skills SummaryWhen drawing the organization chart: file-new-business-organization chart, you can quickly draw what the template needs.1. when Visio draws a picture, when two straight lines cross, there will always be a cross-line mark by default, which is very uncomfortable. the removal method is: select the line, and then menu format-> behavior-> connecting line-> cross-line-> add-> never.2. Add connection points.There is a drop-down button next to the button of the connection line.
configuration Recommended Configuration If you are a college student or senior researcher, and your laboratory or personal funds are abundant, it is recommended that you adopt the following configuration: Motherboard: X299 or Z270 Central Processor: i7-6950x or i7-7700K and above memory: brand memory, with a total capacity of more than 32G, which consists of 4 channels or 8 channels according to the motherboard. SSD: brand solid-state disk, with a capacity