I have trained CIFAR QUICK using caffe, but when I test the cifar10_quick_iter_5000.caffemodel.h5 using a python wrapper I get an accuracy around 52-54% whereas it should be 75%. I do not understand why I am geting such a low accuracy, because when I test Lenet MNIST I get the expected accuracy as per the MNIST example in caffe website. To verify if my method is right or wrong I have tried the cifar trained model file from Clasificador_Cifar-10 and I get and accuracy of 68%.
Please let me know if I am missing something when I test the model.
import sys
import caffe
import cv2
import Image
import matplotlib
import numpy as np
import lmdb
caffe_root = '/home/fred/CIFAR_QUICK/caffe'
MODEL_FILE = '/home/fred/CIFAR_QUICK/caffe/examples/cifar10/cifar10.prototxt'
PRETRAINED = '/home/fred/CIFAR_QUICK/caffe/examples/cifar10/cifar10_60000.caffemodel.h5'
net = caffe.Net(MODEL_FILE, PRETRAINED,caffe.TEST)
caffe.set_mode_cpu()
db_path = '/home/fred/CIFAR_QUICK/caffe/examples/cifar10/cifar10_test_lmdb'
lmdb_env = lmdb.open(db_path)
lmdb_txn = lmdb_env.begin()
lmdb_cursor = lmdb_txn.cursor()
count = 0
correct = 0
for key, value in lmdb_cursor:
print "Count:"
print count
count = count + 1
datum = caffe.proto.caffe_pb2.Datum()
datum.ParseFromString(value)
label = int(datum.label)
image = caffe.io.datum_to_array(datum)
image = image.astype(np.uint8)
out = net.forward_all(data=np.asarray([image]))
predicted_label = out['prob'][0].argmax(axis=0)
print out['prob']
if label == predicted_label:
correct = correct + 1
print("Label is class " + str(label) + ", predicted class is " + str(predicted_label))
print(str(correct) + " out of " + str(count) + " were classified correctly")
See my answer here. You are not subtracting the mean which results in low accuracy. The link to the code, posted above, takes care of that. Apart from this there's nothing wrong with your approach.
Related
I am trying to recreate the following graph in plotnine. It's asking me for more details but I don't want to distract from the example. I think it's pretty obvious what I'm trying to do. I have been given a function by a colleague. I'm not interested in rewriting the function. I want to take sm and use plotnine to plot it instead of matplotlib. I plot lots of dataframes with plotnine but I'm not sure how to use it in this case. I have tried on my own to figure it out and I keep getting lost. I hope that for someone more experienced I am overlooking something simple.
import matplotlib.pyplot as plt
def getSuccess(y,x):
return((y*(-x))*.5+.5)
steps = 100
stepSize = 1/steps
sm = []
for y in range(steps*2+1):
sm.append([getSuccess((y-steps)*stepSize,(x-steps)*stepSize) for x in range(steps*2+1)])
plt.imshow(sm)
plt.ylim(-1, 1)
plt.colorbar()
plt.yticks([0,steps,steps*2],[str(y) for y in [-1.0,0.0,1.0]])
plt.xticks([0,steps,steps*2],[str(x) for x in [-1.0,0.0,1.0]])
plt.show()
You could try geom_raster.
I have taken your synthetic data sm and converted to a dataframe as plotnine will need this.
import pandas as pd
import numpy as np
from plotnine import *
df = pd.DataFrame(sm).melt()
df.rename(columns={'variable':'x','value':'density'}, inplace=True)
df.insert(1,'y',df.index % 201)
p = (ggplot(df, aes('x','y'))
+ geom_raster(aes(fill='density'), interpolate=True)
+ labs(x=None,y=None)
+ scale_x_continuous(expand=(0,0), breaks=[0,100,200], labels=[-1,0,1])
+ scale_y_continuous(expand=(0,0), breaks=[0,100,200], labels=[-1,0,1])
+ theme_matplotlib()
+ theme(
text = element_text(family="Calibri", size=9),
legend_title = element_blank(),
axis_ticks = element_blank(),
legend_key_height = 29.6,
legend_key_width = 6,
)
)
p.save(filename='C:\\Users\\BRB\\geom_raster.png', height=10, width=10, units = 'cm', dpi=400)
This result is:
I would like to test the trained built-in VGG16 network in MxNet. The experiment is to feed the network with an image from ImageNet. Then, I would like to see whether the result is correct.
However, the results are always error! Hi, how stupid the network is! Well, that cannot be true. I must do something wrong.
from mxnet.gluon.model_zoo.vision import vgg16
from mxnet.image import color_normalize
import mxnet as mx
import numpy as np
import cv2
path=‘http://data.mxnet.io/models/imagenet-11k/’
data_dir = ‘F:/Temps/Models_tmp/’
k = ‘synset.txt’
#gluon.utils.download(path+k, data_dir+k)
img_dir = ‘F:/Temps/DataSets/ImageNet/’
img = cv2.imread(img_dir + ‘cat.jpg’)
img = mx.nd.array(img)
img,_ = mx.image.center_crop(img,(224,224))
img = img/255
img = color_normalize(img,mean=mx.nd.array([0.485, 0.456, 0.406]),std=mx.nd.array([0.229, 0.224, 0.225]))
img = mx.nd.transpose(img, axes=(2, 0, 1))
img = img.expand_dims(axis=0)
with open(data_dir + ‘synset.txt’, ‘r’) as f:
labels = [l.rstrip() for l in f]
aVGG = vgg16(pretrained=True,root=‘F:/Temps/Models_tmp/’)
features = aVGG.forward(img)
features = mx.ndarray.softmax(features)
features = features.asnumpy()
features = np.squeeze(features)
a = np.argsort(features)[::-1]
for i in a[0:5]:
print(‘probability=%f, class=%s’ %(features[i], labels[i]))
The outputs from color_normalize seems not right for the absolute values of some numbers are greater than one.
This is my figure of cat which is downloaded from the ImageNet.
These are my outputs.
probability=0.218258, class=n01519563 cassowary probability=0.172373,
class=n01519873 emu, Dromaius novaehollandiae, Emu novaehollandiae
probability=0.128973, class=n01521399 rhea, Rhea americana
probability=0.105253, class=n01518878 ostrich, Struthio camelus
probability=0.051424, class=n01517565 ratite, ratite bird, flightless
bird
Reading your code:
path=‘http://data.mxnet.io/models/imagenet-11k/’
I think you might be using the synset of the ImageNet 11k (11000 classes) rather than the 1k (1000) classes. That would explain the mismatch.
The correct synset is here: http://data.mxnet.io/models/imagenet/synset.txt
I am trying to solve the titanic machine learning challenge from kaggle using a neural network. I removed most of the irrelevant data and converted the useful data into a 2D numpy array while the survival is converted into a 1D numpy array. For some reason it throws an error saying dimension 0 in both shape must be equal, I've been trying to solve it for quite a while and I hope that you guys can help out.
TensorFlowNumpy.py
import tensorflow as tf
def numpy2tensor(numpy):
sess = tf.Session()
with sess.as_default():
return tf.constant(numpy)
def tensor2numpy(tensor):
sess = tf.Session()
with sess.as_default():
return tensor.eval()
Dataset.py
import pandas
import numpy as np
dataset = pandas.read_csv('train.csv')
dataset2= dataset.drop(['PassengerId','Survived','Name','Ticket','Fare','Cabin','Embarked'],axis=1)
dataset3= dataset2.fillna(0)
survive = pandas.read_csv('train.csv')
survival = np.float32(survive.Survived)
dataset4 = np.float32(dataset3)
MainCode.py
import tensorflow as tf
import numpy
from dataset import dataset4,survival
from sklearn.model_selection import train_test_split
from TensorFlowNumpy import numpy2tensor
train_x,test_x,train_y,test_y = train_test_split(dataset4,survival,test_size
= 0.2)
tensor_train_x = numpy2tensor(train_x)
tensor_train_y = numpy2tensor(train_y)
tensor_test_x = numpy2tensor(test_x)
tensor_test_y = numpy2tensor(test_y)
n_nodes_hl1 = 10
n_nodes_hl2 = 10
n_classes = 2
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([5,
n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1,
n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2,
n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes]))}
l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']),
hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']),
hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
output = tf.matmul(l2,output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
cost =
tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,
labels=tensor_train_y))
optimizer1 = tf.train.GradientDescentOptimizer(0.001).minimize(cost)
hm_epochs = 100
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
_, c = sess.run([optimizer1, cost], feed_dict={x:tensor_train_x,
y:tensor_train_y})
epoch_loss += c
print('Epoch', epoch+1, 'completed out
of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:test_x, y:test_y}))
train_neural_network(tensor_train_x)
I have faced this error several times, problem is obviously in our code. I didn't look through your code thoroughly as i am leaving for the day, but i smell that your dependent variable/ output variable shape is [1,712] which should be [712,1] so some where in the code try to fix it. Basically what it meant is you are having one row with 712 columns but it should be 712 rows with 1 column(output). Please mark this as answer if it helps. Ping me tomorrow if problem still exists. I will take a look at it.
I am new to TensorFlow. Today I tried to implement my first model in TF but it returned strange results. I know that I am missing something here but I was not able to figure it out. Here is the story.
Model
I have a simple Multilayer Perceptron model with only a single hidden layer applied on MNIST databse. Layers are defined like [input(784) , hidden_layer(470) , output_layer(10)] with tanh as non-linearity for hidden layer and softmax as the loss for output layer. The optimizer I am using is Gradient Descent Algorithm with learning rate of 0.01. My mini batch size is 1 (I am training model with samples one by one).
My implementations :
First I implemented my model in C++ and got around 96% accuracy.Here is the repository : https://github.com/amin2ros/Artificog
I implemented the exact model in TensorFlow but surprisingly the model didn't converge at all. Here is the code.
Code:
import sys
import input_data
import matplotlib.pyplot as plt
from pylab import *
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import tensorflow as tf
# Parameters
learning_rate = 0.1
training_epochs = 1
batch_size = 1
display_step = 1
# Network Parameters
n_hidden_1 = 470 # 1st layer num features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
# Create model
def multilayer_perceptron(_X, _weights, _biases):
layer_1 = tf.tanh(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1']))
return tf.matmul(layer_1, _weights['out']) + _biases['out']
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax(pred)) # Softmax loss
optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cost) #
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
m= 0
total_batch = int(mnist.train.num_examples/batch_size)
counter=0
#print 'count = ' , total_batch
#sys.stdin.read(1)
# Loop over all batches
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
label = tf.argmax(batch_ys,1).eval()[0]
counter+=1
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})
wrong_prediction = tf.not_equal(tf.argmax(pred, 1), tf.argmax(y, 1))
missed=tf.cast(wrong_prediction, "float")
m += missed.eval({x: batch_xs, y: batch_ys})[0]
print "Sample #", counter , " - Label : " , label , " - Prediction :" , tf.argmax(pred, 1).eval({x: batch_xs, y: batch_ys})[0] ,\
"- Missed = " , m , " - Error Rate = " , 100 * float(m)/counter
print "Optimization Finished!"
I am very curious why this happens. Any help is appreciated.
Edit:
As commented below definition of cost function was incorrect so it should be like
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred,y))
Now model converges :)
I am currently working on a project where I must analyze data and find a period for the graph. The data contains outliers. I need a function that will make a line of best fit for the function.
I attempted to simply get a sin graph on the plot, but I could not even do that. Can anyone give me a starting hint?
import os
import pyfits as fits
import numpy as np
import pylab
import random
import scipy.optimize
import scipy.signal
from numpy import arange
from matplotlib import pyplot
from scipy.optimize import curve_fit
filename = 'C:\Users\Ken Preiser\Desktop\Space thing\Snapshots\BAT_70m_snapshot_SWIFT_J1647.9-4511B.lc'
namePortion = filename[-39:]
hdulist = fits.open(filename, 'readonly', None, False) #{unpacks file) name, mode, memorymap, savebackup
data = hdulist[1].data
datapoints = 23310
def sinfunc(a, b, c): #I tried graphing a sinfunction, but it did not work...
return a*np.sin(bx-c)
time = data.field('TIME')
time = time / 86400.0
timeViewingThreshold = 10
rateViewingThreshold = .01
rate = np.sum(data['RATE'][:,:4], axis=1)
average = np.sum(rate)/23310
error = data.field('ERROR')
error = np.sqrt(np.sum(data['ERROR'][:,:4]**2, axis=1))
print rate.size,(", rate")
print time.size,(", time")
fig = pylab.figure()
ax = fig.add_subplot(111)
ax.set_xlabel('Time')
ax.set_ylabel('Rate')
ax.set_title('Rate vs Time graph: ' + namePortion)
pylab.plot(time, rate, 'o')
pyplot.xlim(min(time) - timeViewingThreshold, max(time) + timeViewingThreshold)
pyplot.ylim(min(rate) - rateViewingThreshold, max(rate) + rateViewingThreshold)
ax.errorbar(time, rate, xerr=0, yerr=error)
pylab.show()
(the outputs)
http://imgur.com/jbfuxOA
You're trying to fit points to the model: y = sin(ax + b). Since you're using linear regression, you need a linear model. So one way to do that is compute arcsin for each point and now compute the linear regression. The model is now: arcsin(y) = ax + b. The regression model gives you a and b which is what you're after. You should be able to test this out pretty quickly in excel, then code it up once the nuances are figured out.