| ./data_viz_easy/raw/tut1.ipynb: "\n", | |
| ./data_viz_easy/raw/tut1.ipynb: "\n", | |
| ./data_viz_easy/raw/tut1.ipynb: "\n", | |
| ./data_viz_easy/raw/tut3.ipynb: "\n", | |
| ./data_viz_easy/raw/ex2.ipynb: "\n", | |
| ./data_viz_easy/raw/ex6.ipynb: "\n", | |
| ./data_viz_easy/raw/ex6.ipynb: "\n", | |
| ./data_viz_easy/raw/ex6.ipynb: "\n", | |
| ./data_viz_easy/raw/ex6.ipynb: "\n", | |
| ./data_viz_easy/raw/tut7.ipynb: "\n", |
| import os | |
| import re | |
| import requests | |
| import shutil | |
| def get_url_and_fname(line): | |
| if 'i.imgur.com/' in line: | |
| regex = r"(https?://i.imgur.com/(.*.png))" |
| from sklearn.datasets import fetch_20newsgroups | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.linear_model import LogisticRegression | |
| from sklearn.pipeline import Pipeline | |
| import pandas as pd | |
| import numpy as np | |
| # Grab just two categories from the 20 newsgroups dataset | |
| categories=['sci.space', 'rec.autos'] |
| from sklearn.datasets import fetch_20newsgroups | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.linear_model import LogisticRegression | |
| # A pipeline "stitches together" the various steps of a modeling process into a single piece. You should either try to get a separate explanation of this, or try to do without it. | |
| # In general pipelines are pretty cool. But, one more thing to learn. | |
| from sklearn.pipeline import Pipeline | |
| import pandas as pd | |
| import numpy as np |
| from keras.applications.resnet50 import ResNet50, preprocess_input | |
| from keras.preprocessing.image import load_img, img_to_array | |
| import numpy as np | |
| from os import listdir | |
| from os.path import join | |
| import pandas as pd | |
| def featurize(fpath, model, img_size): | |
| '''Use trained model to convert image to vector describing content |
| Determining if the function dgettext exists failed with the following output: | |
| Change Dir: /home/powersju/Madeline_2.0_PDE/CMakeFiles/CMakeTmp | |
| Run Build Command:"/usr/bin/make.exe" "cmTC_872e9/fast" | |
| /usr/bin/make -f CMakeFiles/cmTC_872e9.dir/build.make CMakeFiles/cmTC_872e9.dir/build | |
| make[1]: Entering directory '/home/powersju/Madeline_2.0_PDE/CMakeFiles/CMakeTmp' | |
| Building C object CMakeFiles/cmTC_872e9.dir/CheckFunctionExists.c.o | |
| /usr/bin/cc -DCHECK_FUNCTION_EXISTS=dgettext -o CMakeFiles/cmTC_872e9.dir/CheckFunctionExists.c.o -c /usr/share/cmake-3.6.2/Modules/CheckFunctionExists.c | |
| <command-line>:0:23: warning: conflicting types for built-in function ‘dgettext’ | |
| /usr/share/cmake-3.6.2/Modules/CheckFunctionExists.c:7:3: note: in expansion of macro ‘CHECK_FUNCTION_EXISTS’ |
| $ cat CMakeFiles/CMakeOutput.log | |
| The system is: CYGWIN - 2.6.0(0.304/5/3) - x86_64 | |
| Compiling the C compiler identification source file "CMakeCCompilerId.c" succeeded. | |
| Compiler: /usr/bin/cc | |
| Build flags: | |
| Id flags: | |
| The output was: | |
| 0 |
| from keras.layers import Input, Dense, merge, Flatten | |
| from keras.layers.convolutional import Convolution2D | |
| from keras.models import Model, model_from_json | |
| from keras import backend as K | |
| def make_model(img_edge_size): | |
| img_shape = (3, img_edge_size, img_edge_size) | |
| mask_shape = (1, img_edge_size, img_edge_size) |
##VGG16 model for Keras
This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
| import numpy as np | |
| from keras.models import Model | |
| from keras.layers import Input, Dense | |
| input_size = 1000 | |
| n_obs = 200 | |
| encoding_size = 50 | |
| x = Input(shape=(input_size,)) | |
| z = Dense(encoding_size, activation='sigmoid', name='z')(x) |