salihkaragoz

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import datetime

salihkaragoz

def five_convnet(X, model, y=None, reg=0.0):

  W1, b1, W2, b2 = model['W1'], model['b1'], model['W2'], model['b2']
  W3, b3, W4, b4 = model['W3'], model['b3'], model['W4'], model['b4']
  W5, b5, W6, b6 = model['W5'], model['b5'], model['W6'], model['b6']

  conv_filter_height, conv_filter_width = W1.shape[2:]
  assert conv_filter_height == conv_filter_width, 'Conv filter must be square'
  assert conv_filter_height % 2 == 1, 'Conv filter height must be odd'

salihkaragoz

mkdir /truba/home/{username}/python3      
cd python3
wget https://www.python.org/ftp/python/3.5.2/Python-3.5.2.tgz
tar zxfv Python-3.5.2.tgz
cd Python-3.5.2.tgz
./configure --prefix=/truba/home/{username}/python3
make && make install

export PATH=/truba/home/{username}/python3/Python-3.5.2/:$PATH
export PYTHONPATH=/truba/home/{username}/python3/Python-3.5.2

salihkaragoz

import json
data = json.load(open('instances_train2017.json'))

print data.keys()
#OUTPUT :
#  [u'info', u'licenses', u'images', u'annotations', u'categories']

print data['categories']

'''

salihkaragoz

7
2
1
0
4
1
4
9
5
9

salihkaragoz

# Written by MSK
import glob                                                           
import cv2 
pngs = glob('./*.png')

for png in pngs:
    img = cv2.imread(png)
    cv2.imwrite(png[:-3] + 'jpg', img)

salihkaragoz

import numpy as np
from pycocotools.coco import COCO
import os
import math
import keras
from keras.models import Sequential, Model
from keras.layers import Dense, Activation, Input, Flatten, Dropout
from keras.utils import plot_model
import cv2
import matplotlib.pyplot as plt

salihkaragoz

y_true = 2
y_pred = 0.2

if(K.backend()=="tensorflow"):
    import tensorflow as tf
    sess= tf.Session()
    with tf.device('/cpu:0'):
        pt = tf.where(tf.equal(y_true, 1), y_pred, 1 - y_pred)
    print(sess.run(pt))
if(K.backend()=="theano"):

salihkaragoz

##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

salihkaragoz

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name: