I'm working on pedestrian detection with a team. I am trying to figure out an error that keeps showing up that says "TypeError: samples is not a numpy array, neither a scalar" which when appear points to the line of code that is svm.train(X_data, cv2.ml.ROW_SAMPLE, labels12)
i tried following dozens of online guides but i still couldn't solve the problem, and im also very new to this
import cv2
import numpy as np
from skimage import feature
from skimage import exposure
import glob
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
# training
X_data = []
labels1 = []
label = []
files = glob.glob ("new_pos_1/crop*.PNG")
for myFile in files:
# print(myFile)
image = cv2.imread(myFile,)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
X_data.append (image)
labels1.append('Pedestrian')
print('X_data shape:', np.array(X_data).shape)
labels12 = np.array([labels1])
print('labels12 shape:',np.array(labels12).shape)
print('labels shape:', np.array(labels1).shape)
#Testing
Y_data = []
files = glob.glob ("new_pos_1/person*.PNG")
for myFile in files:
# print(myFile)
image = cv2.imread (myFile)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
Y_data.append (image)
label.append('Pedestrian')
print('Y_data shape:', np.array(Y_data).shape)
print('label shape:', np.array(label).shape)
hog_features = []
for image in np.array(X_data):
(fd, hogImage) = feature.hog(image, orientations=9, pixels_per_cell=(8, 8), cells_per_block=(2, 2),
transform_sqrt=True, block_norm="L2-Hys", visualise=True)
hogImage = exposure.rescale_intensity(hogImage, out_range=(0, 255))
hogImage = hogImage.astype("uint8")
hog_features.append(fd)
print("I'm done hogging")
print(hog_features)
svm = cv2.ml.SVM_create()
svm.setKernel(cv2.ml.SVM_LINEAR)
svm.setType(cv2.ml.SVM_C_SVC)
svm.setC(2.67)
svm.setGamma(5.383)
print("Done initializing SVM parameters")
# Train SVM on training data
svm.train(X_data, cv2.ml.ROW_SAMPLE, labels12)
print("Done trainning")
svm.save('svm_data.dat')
print("SAVED.")
#testResponse = svm.predict(testData)[1].ravel()
cv2.waitKey(0)
The line at the beginning that says labels12 = np.array([labels1]) i used to try and fix the error that showed up to no avail.
This is the original website that helped me write this code: https://www.learnopencv.com/handwritten-digits-classification-an-opencv-c-python-tutorial/
you should also do X_data2 = np.array([X_data]) and call svm.train(X_data2, cv2.ml.ROW_SAMPLE, labels12)
Related
I can't understand how to recognize it.
Hope someone can get me out.
import cv2
import numpy as np
import pytesseract
from PIL import Image
image = cv2.imread('b.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Morph open to remove noise and invert image
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
invert = 255 - opening
data = pytesseract.image_to_string(image, lang='eng', config='--psm 10')
print(data)
I am trying to apply random_shear image augmentation from Keras but the images are completely distorted after this.
shape = inputs.shape #(32,512,512,3)
temp = np.empty(shape=(shape[0], shape[1],shape[2], shape[3]))
for i in range(shape[0]):
array_inputs = tf.keras.preprocessing.image.img_to_array(inputs[i])
sheared = tf.keras.preprocessing.image.random_shear(array_inputs, .2,
row_axis=0, col_axis=1,
channel_axis=2)
temp[i]= sheared
return tf.convert_to_tensor(temp)
I am not sure what is wrong here.
Can anybody help me here?
For what is worth, here is the code I tested:
import tensorflow as tf
import numpy as np
from PIL import Image
inputs = [Image.open('./homersimpson.0.0.jpg')]
shape = (1,1400,1400,3)
temp = np.empty(shape=(shape[0], shape[1],shape[2], shape[3]))
for i in range(shape[0]):
array_inputs = tf.keras.preprocessing.image.img_to_array(inputs[i])
sheared = tf.keras.preprocessing.image.random_shear(array_inputs, 50,
row_axis=0, col_axis=1,
channel_axis=2)
temp[i]= sheared
for i in range(shape[0]):
tf.keras.preprocessing.image.array_to_img(temp[i]).show()
Turning this image:
To this:
Below is a code I wrote for Hyperparameter tuning of XGboost using RandomizedSearchCV
from sklearn.model_selection import RandomizedSearchCV
from sklearn.metrics import make_scorer, accuracy_score, precision_score, recall_score, auc
from pprint import pprint
from xgboost import XGBClassifier
import time
# instantiate XGBoost model
clf = XGBClassifier(missing=np.nan, nthreads=-1)
# Define scoring metrics
scorers = {
'accuracy_score': make_scorer(accuracy_score),
'precision_score': make_scorer(precision_score),
'recall_score': make_scorer(recall_score)
}
param_grid_dummy = {
"n_estimators": [25, 250],
"max_depth": [3,5],
"learning_rate": [0.0005, 0,005],
}
def random_search_wrapper(refit_score = 'precision_score'):
"""
fits a RandomizedSearchCV classifier using refit_score for optimization
prints classifier performance metrics
"""
rf_random = RandomizedSearchCV(estimator = clf, param_distributions = param_grid_dummy, n_iter = 3, scoring=scorers, refit = refit_score, cv = 3, return_train_score= True, n_jobs= -1)
rf_random.fit(X_train_df, Y_train)
# make the predictions
Y_pred = rf_random.predict(X_test_df)
print('Best params for {}'.format(refit_score))
print(rf_random.best_params_)
# confusion matrix on test data
print('\nConfusion matrix of Random Forest optimized for {} on the test data: '.format(refit_score))
print(pd.DataFrame(confusion_matrix(Y_test, Y_pred),
columns = ['pred_neg', 'pred_pos'], index = ['neg', 'pos']))
return rf_random
# Optimize classifier for recall score
start = time.time()
rf_random_cl = random_search_wrapper(refit_score='precision_score')
# Print time
end = time.time()
print()
print((end - start)/60, "minutes")
I get a wired warning.
/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/label.py:151: DeprecationWarning: The truth value of an empty array is ambiguous. Returning False, but in future this will result in an error. Use `array.size > 0` to check that an array is not empty.
if diff:
Can someone pls help me understand what wrong am I doing here?
when I do simple clf.fit(X_train_df, Y_train). It works perfectly fine
This is an issue with sklearn version. few versions < 0.20.1 throw this this error
Code is correct.
I am currently sitting on an task in which I need to plot DICOM slices into one 3D model using NumPy, Matplotlib, (Marchingcubes, Triangulation or Volumemodel)
I have tried the method from this website :
https://www.raddq.com/dicom-processing-segmentation-visualization-in-python/
but unfortunately it didn't worked out for me
import pydicom
import numpy as np
import os
import matplotlib.pyplot as plt
import ipywidgets as widgets
from ipywidgets import interact, fixed
filesNew = []
datenSatz = []
output_path = './Head/'
print()
def load_scan(path):
slices = [pydicom.read_file(path + '/' + s) for s in os.listdir(path)]
slices.sort(key = lambda x: int(x.InstanceNumber))
try:
slice_thickness = np.abs(slices[0].ImagePositionPatient[2] - slices[1].ImagePositionPatient[2])
except:
slice_thickness = np.abs(slices[0].SliceLocation - slices[1].SliceLocation)
for s in slices:
s.SliceThickness = slice_thickness
return slices
for s in load_scan('./Head/'):
h = s.pixel_array
datenSatz.append(s) #dataSet from the patient
filesNew.append(h) #pixel_array
def show_image(image_stack, sliceNumber):
pxl_ar = image_stack[sliceNumber]
#print(np.array_equal(pxl_ar,filesNew[sliceNumber]))
plt.imshow(pxl_ar, cmap= plt.cm.gray)
plt.show()
slider = widgets.IntSlider(min=0,max=len(filesNew)-1,step=1,value = 0, continuous_update=False)
interact(show_image, image_stack = fixed(filesNew), sliceNumber = slider);
DICOM slices visualized
There is an example of loading a set of 2D CT slices and building a 3D array.
https://github.com/pydicom/pydicom/blob/master/examples/image_processing/reslice.py
It does not go on to construct the surface, but it should solve the first half of your problem.
Learning how to use tensorflow, first tutorial code on mandelbrot set below
# Import libraries for simulation
import tensorflow as tf
import numpy as np
# Imports for visualization
import PIL.Image
from io import BytesIO
from IPython.display import Image, display
def DisplayFractal(a, fmt='jpeg'):
"""Display an array of iteration counts as a
colorful picture of a fractal."""
a_cyclic = (6.28*a/20.0).reshape(list(a.shape)+[1])
img = np.concatenate([10+20*np.cos(a_cyclic),
30+50*np.sin(a_cyclic),
155-80*np.cos(a_cyclic)], 2)
img[a==a.max()] = 0
a = img
a = np.uint8(np.clip(a, 0, 255))
f = BytesIO()
PIL.Image.fromarray(a).save(f, fmt)
display(Image(data=f.getvalue()))
sess = tf.InteractiveSession()
# Use NumPy to create a 2D array of complex numbers
Y, X = np.mgrid[-1.3:1.3:0.005, -2:1:0.005]
Z = X+1j*Y
xs = tf.constant(Z.astype(np.complex64))
zs = tf.Variable(xs)
ns = tf.Variable(tf.zeros_like(xs, tf.float32))
tf.global_variables_initializer().run()
# Compute the new values of z: z^2 + x
zs_ = zs*zs + xs
# Have we diverged with this new value?
not_diverged = tf.abs(zs_) < 4
# Operation to update the zs and the iteration count.
#
# Note: We keep computing zs after they diverge! This
# is very wasteful! There are better, if a little
# less simple, ways to do this.
#
step = tf.group(
zs.assign(zs_),
ns.assign_add(tf.cast(not_diverged, tf.float32))
)
for i in range(200): step.run()
DisplayFractal(ns.eval())
returns this on shell
<IPython.core.display.Image at 0x7fcdee1da810>
It doesn't display the image and I'd prefer if it saved the image.
How can I save the result as an image?
Scipy has an easy image save function! https://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.misc.imsave.html
You should try this:
import scipy.misc
scipy.misc.imsave('mandelbrot.png',ns.eval())
I hope this works! Regardless, let me know!