Numpy append sometimes works, sometimes doesn't - python

so I've been working on this facial identification project. It's for my science fair and I'm in the phase where I'm trying to get data graphs, plots, and visualizations. I've got it to work to some extent, but it's not consistent (in terms of execution).
The thing is, sometimes the code works, sometimes it'll give me an error.
For some context, the error is with Numpy append(). I have a variable I want to append data to but when it doesn't work the error is AttributeError: 'numpy.ndarray' object has no attribute 'append'
#Although the results aren't as expected, this can make for a good demo in ISEF
#The whole refresh after a face is detected is cool and can be used to show how different faces cluster
# Numerical computation requirements
import numpy as np
from numpy import linalg, load, expand_dims, asarray, savez_compressed, append
from numpy.linalg import norm
import pandas as pd
# Plotting requirements
import matplotlib
from matplotlib import pyplot as plt
import matplotlib.patheffects as PathEffects
from matplotlib.animation import FuncAnimation as ani
import seaborn as sb
# Clustering requirements
import sklearn
from sklearn.cluster import KMeans
from sklearn.manifold import TSNE
from sklearn.preprocessing import scale
# Miscellaneous requirements
import os
import cv2
from PIL import Image
from mtcnn.mtcnn import MTCNN
from keras.models import load_model
from scipy.spatial.distance import squareform, pdist
# Initialize RNG seed and required size for Facenet
seed = 12345678
size = (160,160)
# Required networks
facenet = load_model('facenet_keras.h5')
fd = MTCNN()
# Initialize Seaborn plots
sb.set_style('darkgrid')
sb.set_palette('muted')
sb.set_context('notebook', font_scale=1.5, rc={'lines.linewidth': 2.5})
# Matplotlib animation requirements?
plt.style.use('fivethirtyeight')
fig = plt.figure()
# Load embeddings
data = load('jerome only npz/jerome embeddings.npz')
Data_1 = data['arr_0']
Dataset = []
for array in Data_1:
Dataset.append(np.expand_dims(array, axis=0))
# Create cluster
cluster = KMeans(n_clusters=2, random_state=0).fit(Data_1)
y = cluster.labels_
z = pd.DataFrame(y.tolist())
faces = list()
def scatter(x,colors):
palette = np.array(sb.color_palette('hls', 26))
plot = plt.figure()
ax = plt.subplot(aspect='equal')
# sc = ax.scatter(x[:,0],x[:,1], lw =0, s=120, c=palette[colors.astype(np.int)])
sc = ax.scatter(x[:,0],x[:,1], lw =0, s=120)
labels = []
return plot , ax, sc, labels
def detembed():
cam = cv2.VideoCapture(0)
_,frame = cam.read()
info = fd.detect_faces(frame)
if info != []:
for i in info:
print("***************** FACE DETECTED *************************************************")
x,yc,w,h = i['box']
x,y = abs(x), abs(yc)
w,h = abs(w), abs(h)
xx, yy = x+w, yc+h
#cv2.rectangle(frame, (x,y), (xx,yy), (0,0,255),2)
face = frame[yc:yy, x:xx]
image = Image.fromarray(face)
image = image.resize(size)
arr = asarray(image)
arr = arr.astype('float32')
mean, std = arr.mean(), arr.std()
arr = (arr - mean) / std
samples = expand_dims(arr, axis=0)
faces.append(samples)
#cv2.imshow('Camera Feed', frame)
while True:
detembed()
embeddings = Dataset
if not faces:
continue
else:
for face in faces:
embeds = facenet.predict(face)
#switch these if conflicts arise
embeddings.append(embeds)
embeddings = asarray(embeddings)
embeddings = embeddings[:,0,:]
cluster = KMeans(n_clusters=2, random_state=0).fit(Data_1)
y = cluster.labels_
points = TSNE(random_state=seed).fit_transform(embeddings)
# here "y" dictates the color of the plots depending on the kmeans algorithm
scatter(points,y)
graph = ani(fig, scatter, interval=20)
fcount = len(embeddings)
plt.text(0,0,'{} points'.format(fcount))
plt.show()
# reset embeddings var to initial dataset
Dataset = np.delete(Dataset, fcount - 1,0)
embeddings = Dataset
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.release()
cv2.destroyAllWindows
Note that I am not a talented programmer; this code was botched from some example I found online. I had to pick up Python as I went along with this project. I do have a background in C, so I would say I get the basics of code logic.
Please help. I'm getting really desperate; the science fair is getting closer and I am a high schooler with no ML mentor. I live on an island (Guam) with no machine learning practitioners (not even in the university), so I turn to Stackoverflow.

There's no issue with NumPy's append(). Here(3rd statement) you're trying to append a value to Numpy array without using NumPy's np.append().
Dataset.append(np.expand_dims(array, axis=0))
embeddings = Dataset
embeddings.append(embeds)
Since Datasets contain Numpy array after running the first statement, embeddings will also be a NumPy array and hence the operation fails whenever the execution comes here.
A simple fix would be to use this:
np.append(embeddings, embeds)
Or this,
embeddings = list(Dataset)
Hope that helps.

Related

T-distributed Stochastic Neighbor Embedding (t-SNE)

I am trying to run T-distributed Stochastic Neighbor Embedding (t-SNE) in Jupyter but always facing a issue with
ValueError: could not convert string to float: '<Null>'
Code:
enter image description here
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
# Reading the data using pandas
df = pd.read_csv("E:\\Field data\Output\\Pixel values7.csv")
# print first five rows of df
print(df.head(9))
# save the labels into a variable l.
l = df['label']
# Drop the label feature and store the pixel data in d.
d = df.drop("label", axis = 1)
I got error after this line
# Data-preprocessing: Standardizing the data
from sklearn.preprocessing import StandardScaler
standardized_data = StandardScaler().fit_transform(df)
print(standardized_data.shape)
# TSNE
# Picking the top 1000 points as TSNE
# takes a lot of time for 15K points
data_1000 = standardized_data[0:1000, :]
labels_1000 = labels[0:1000]
model = TSNE(n_components = 2, random_state = 0)
# configuring the parameters
# the number of components = 2
# default perplexity = 30
# default learning rate = 200
# default Maximum number of iterations
# for the optimization = 1000
tsne_data = model.fit_transform(data_1000)
# creating a new data frame which
# help us in plotting the result data
tsne_data = np.vstack((tsne_data.T, labels_1000)).T
tsne_df = pd.DataFrame(data = tsne_data,
columns =("Dim_1", "Dim_2", "label"))
# Plotting the result of tsne
sn.FacetGrid(tsne_df, hue ="label", size = 6).map(
plt.scatter, 'Dim_1', 'Dim_2').add_legend()
plt.show()
I got this link from somewhere, I am not expert in python. I request you to kindly help me out.
I am trying to run this program for my data but always getting a error
ValueError: could not convert string to float: '<Null>'
If there is any other code for T-distributed Stochastic Neighbor Embedding (t-SNE). Please let me know.
My data look like this

Convert AxesImage Histogram to Arrays Histogram

Hi everyone my code below here.
import cv2
import numpy as np
import PIL
from matplotlib import pyplot
img1 = cv2.imread('D:/MyProject/SeniorProject/Mushroom Pictures/train/Class A/IMG_9604.jpg')
img2 = cv2.imread('D:/MyProject/SeniorProject/Mushroom Pictures/train/Class A/IMG_9605.jpg')
img1_hsv = cv2.cvtColor(img1,cv2.COLOR_BGR2HSV)
img2_hsv = cv2.cvtColor(img2,cv2.COLOR_BGR2HSV)
h_bins = 18
s_bins = 32
histSize = [h_bins, s_bins]
h_ranges = [0,180]
s_ranges = [0,256]
ranges = h_ranges + s_ranges
channels = [0,1]
hist1c = cv2.calcHist([img1_hsv],channels,None,histSize,ranges,accumulate=False)
hist2c = cv2.calcHist([img2_hsv],[0],None,[180],[0,180],accumulate=False)
pyplot.imshow(hist1c,interpolation = 'nearest')
pyplot.show()
I got hs histogram as AxesImage but I want to convert to arrays for apply to machine learning model train input. Can you help me for that.
Why I didn't use hist1c and hist2c are input of the model because it's not separate H-S each diamention it only keep in the H bins.
Thank you very much :)
Big
Rehsape your histogram data :
np.array(hist1c).reshape(-1, yourDataSize)

Grad-cam not working properly in keras with inceptionv3

I am using visualise cam from keras-vis for creating guided-gradcam images.
The grad-cam is working perfectly well with vgg16. but when i used the same code for inceptionv3 it is not working properly.
from keras.applications.inception_v3 import InceptionV3
from vis.utils import utils
from keras.preprocessing import image
import numpy as np
from keras import activations
from matplotlib import pyplot as plt
%matplotlib inline
from vis.visualization import visualize_cam,overlay
#build the inceptionv3 model with imagenet weights
model = InceptionV3(weights='imagenet',include_top=True)
# Utility to search for layer index by name
layer_idx = utils.find_layer_idx(model,'predictions')
#swap with softmax with linear classifier for the reasons mentioned above
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)
from vis.utils import utils
from matplotlib import pyplot as plt
%matplotlib inline
plt.rcParams['figure.figsize']=(18,6)
img1 = utils.load_img('images/ouzel1.jpg',target_size=(299,299))
img2 = utils.load_img('images/ouzel2.jpg',target_size=(299,299))
f, ax = plt.subplots(1,2)
ax[0].imshow(img1)
ax[1].imshow(img2)
plt.show()
from vis.visualization import visualize_cam
for modifier in [None, 'guided', 'relu']:
plt.figure()
f, ax = plt.subplots(1, 2)
plt.suptitle("vanilla" if modifier is None else modifier)
for i, img in enumerate([img1, img2]):
# 20 is the imagenet index corresponding to `ouzel`
heatmap = visualize_cam(model, layer_idx, filter_indices=20,
seed_input=img, backprop_modifier=modifier,
#penultimate_layer_idx = 299 # corresponding to "conv2d_94"
)
# Lets overlay the heatmap onto original image.
ax[i].imshow(overlay(img, heatmap))
by commenting out the line #penultimate_layer also I am getting the same output which is not correct. can someone tell me what is the problem? The guided-grad cam result is given , followed by the original image is given.
The problem is the heatmap must be on the bird (ouzel).
I hit the very same problem, but then I discovered that InceptionV3 mis-classifies these images. Check:
>>> model.predict(np.stack([img1, img2], 0)).argmax(axis=1)
array([110, 725])
While with VGG it's:
>>> model.predict(np.stack([img1, img2], 0)).argmax(axis=1)
array([20, 20])

opencv knn TypeError: only length-1 arrays can be converted to Python scalars

I am trying to follow the tutorial http://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_ml/py_knn/py_knn_opencv/py_knn_opencv.html and replaced KNearest with cv2.m1.KNearest_create() but i am getting TypeError: only length-1 arrays can be converted to Python scalars
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('digits.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Now we split the image to 5000 cells, each 20x20 size
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]
# Make it into a Numpy array. It size will be (50,100,20,20)
x = np.array(cells)
# Now we prepare train_data and test_data.
train = x[:,:50].reshape(-1,400).astype(np.float32) # Size = (2500,400)
test = x[:,50:100].reshape(-1,400).astype(np.float32) # Size = (2500,400)
# Create labels for train and test data
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
test_labels = train_labels.copy()
# Initiate kNN, train the data, then test it with test data for k=1
cv2.m1.KNearest_create()
knn.train(train,train_labels)
ret,result,neighbours,dist = knn.find_nearest(test,k=5)
# Now we check the accuracy of classification
# For that, compare the result with test_labels and check which are wrong
matches = result==test_labels
correct = np.count_nonzero(matches)
accuracy = correct*100.0/result.size
print accuracy
(i am using a raspberry pi and followed this tutorial to install open cv http://www.pyimagesearch.com/2015/10/26/how-to-install-opencv-3-on-raspbian-jessie/ subsequently i pip installed matplotlib)
parameter cv2.ml.ROW_SAMPLE is missing and change knn.find_nearest(test,k=5) to below code.This is new in openCv3, please refer to openCv official site http://docs.opencv.org/3.0.0/dd/de1/classcv_1_1ml_1_1KNearest.html
` knn.train(train, cv2.ml.ROW_SAMPLE, train_labels)
ret, result, neighbours, dist = knn.findNearest(test, k=5)`
You're just missing one parameter, but I notice that a lot of people have questions about this section of the tutorial, so here's the whole final section adjusted to work with python3 and the modern openCV library.
knn = cv2.ml.KNearest_create()
knn.train(trainData, cv2.ml.ROW_SAMPLE, responses)
ret, results, neighbours, dist = knn.findNearest(newcomer, k=5)
print("result: ", results,"\n")
print("neighbours: ", neighbours,"\n")
print("distance: ", dist)
plt.show()
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('digits.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Now we split the image to 5000 cells, each 20x20 size
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]
# Make it into a Numpy array. It size will be (50,100,20,20)
x = np.array(cells)
# Now we prepare train_data and test_data.
train = x[:,:50].reshape(-1,400).astype(np.float32) # Size = (2500,400)
test = x[:,50:100].reshape(-1,400).astype(np.float32) # Size = (2500,400)
# Create labels for train and test data
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
test_labels = train_labels.copy()
# Initiate kNN, train the data, then test it with test data for k=1
knn = cv2.ml.KNearest_create()
knn.train(train, cv2.ml.ROW_SAMPLE, train_labels)
ret, results, neighbours, dist = knn.findNearest(test, k=5)
#print("result: ", results,"\n")
#print("neighbours: ", neighbours,"\n")
#print("distance: ", dist)
matches = result=test_labels
correct = np.count_nonzero(matches)
accuracy = correct*100.0/result.size
print(accuracy)
doc of opencv said that:
findNearest(...) | findNearest(samples, k[, results[,
neighborResponses[, dist]]]) -> retval, results, neighborResponses,
...
not knn.find_nearest(test,k=5)
you can run
help(cv2.ml.KNearest_create())
then you will see.
by the way ,there are losts erros on opencv website

KNN train() in cv2 with opencv 3.0

I'm trying to run k-nearest neighbours using cv2 (python 2.7) and opencv 3.0. I've replicated the same error message using code like http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_ml/py_knn/py_knn_understanding/py_knn_understanding.html:
import cv2
import numpy as np
import matplotlib.pyplot as plt
# Feature set containing (x,y) values of 25 known/training data
trainData = np.random.randint(0,100,(25,2)).astype(np.float32)
# Labels each one either Red or Blue with numbers 0 and 1
responses = np.random.randint(0,2,(25,1)).astype(np.float32)
# Take Red families and plot them
red = trainData[responses.ravel()==0]
plt.scatter(red[:,0],red[:,1],80,'r','^')
# Take Blue families and plot them
blue = trainData[responses.ravel()==1]
plt.scatter(blue[:,0],blue[:,1],80,'b','s')
plt.show()
newcomer = np.random.randint(0,100,(1,2)).astype(np.float32)
plt.scatter(newcomer[:,0],newcomer[:,1],80,'g','o')
#The following line is modified for OpenCV 3.0
knn = cv2.ml.KNearest_create()
knn.train(trainData,responses)
ret, results, neighbours ,dist = knn.find_nearest(newcomer, 3)
print "result: ", results,"\n"
print "neighbours: ", neighbours,"\n"
print "distance: ", dist
plt.show()
I modified the line knn = cv2.ml.KNearest_create() for OpenCV 3, but the subsequent line produces an error "TypeError: only length-1 arrays can be converted to Python scalars" and I can't figure out what I should be using for the train function.
You are passing wrong length of array for KNN algorithm....glancing at your code, i found that you have missed the cv2.ml.ROW_SAMPLE parameter in knn.train function, passing this parameter considers the length of array as 1 for entire row. thus your corrected code would be as below:
import cv2
import numpy as np
import matplotlib.pyplot as plt
trainData = np.random.randint(0,100,(51,2)).astype(np.float32)
responses = np.random.randint(0,2,(51,1)).astype(np.float32)
red = trainData[responses.ravel()==0]
plt.scatter(red[:,0],red[:,1],80,'r','^')
blue = trainData[responses.ravel()==1]
plt.scatter(blue[:,0],blue[:,1],80,'b','s')
newcomer = np.random.randint(0,100,(5,2)).astype(np.float32)
plt.scatter(newcomer[:,0],newcomer[:,1],80,'g','o')
knn = cv2.ml.KNearest_create()
knn.train(trainData,cv2.ml.ROW_SAMPLE,responses)
ret, results, neighbours, dist = knn.findNearest(newcomer, 3)
print ("results: ", results,"\n")
print ("neighbours: ", neighbours,"\n")
print ("distances: ", dist)
plt.show()
Here is the result which i got from it....

Categories