I have a facedetection training code. It gives me some issues and i have no clue why.
I am using a MAC and seems like there is missing something. Can you please advise what should i do?
Thank you in advance
OpenCV(3.4.1) Error: Assertion failed (!empty()) in detectMultiScale, file /tmp/opencv-20180426-73279-16a912g/opencv-3.4.1/modules/objdetect/src/cascadedetect.cpp, line 1698
Traceback (most recent call last):
File "/Users/Desktop/OpenCV-Python-Series-master/src/faces-train.py", line 36, in <module>
faces = face_cascade.detectMultiScale(image_array, scaleFactor=1.5, minNeighbors=5)
cv2.error: OpenCV(3.4.1) /tmp/opencv-20180426-73279-16a912g/opencv-3.4.1/modules/objdetect/src/cascadedetect.cpp:1698: error: (-215) !empty() in function detectMultiScale
[Finished in 0.421s]
And my code is below.
import cv2
import os
import numpy as np
from PIL import Image
import pickle
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
image_dir = os.path.join(BASE_DIR, "images")
face_cascade = cv2.CascadeClassifier('cascades/data/haarcascade_frontalface_alt2.xml')
recognizer = cv2.face.LBPHFaceRecognizer_create()
current_id = 0
label_ids = {}
y_labels = []
x_train = []
for root, dirs, files in os.walk(image_dir):
for file in files:
if file.endswith("png") or file.endswith("jpg"):
path = os.path.join(root, file)
label = os.path.basename(root).replace(" ", "-").lower()
#print(label, path)
if not label in label_ids:
label_ids[label] = current_id
current_id += 1
id_ = label_ids[label]
#print(label_ids)
#y_labels.append(label) # some number
#x_train.append(path) # verify this image, turn into a NUMPY arrray, GRAY
pil_image = Image.open(path).convert("L") # grayscale
size = (550, 550)
final_image = pil_image.resize(size, Image.ANTIALIAS)
image_array = np.array(final_image, "uint8")
#print(image_array)
faces = face_cascade.detectMultiScale(image_array, scaleFactor=1.5, minNeighbors=5)
for (x,y,w,h) in faces:
roi = image_array[y:y+h, x:x+w]
x_train.append(roi)
y_labels.append(id_)
#print(y_labels)
#print(x_train)
with open("pickles/face-labels.pickle", 'wb') as f:
pickle.dump(label_ids, f)
recognizer.train(x_train, np.array(y_labels))
recognizer.save("recognizers/face-trainner.yml")
The assertion which fails indicates that your cascade is not loaded correctly. You can verify it by calling face_cascade.empty() just after the constructor. Please make sure that the path you provided ('cascades/data/haarcascade_frontalface_alt2.xml') is correct. When it points to a not existing file then there is no exception thrown by the constructor so you can easily miss it without calling empty() explicitly.
Related
I am trying to solve the problem statement Jigsaw-multilingual-toxic-comment-classification but when I tried to preprocess the entire file ,I got the [Errorno 30].
I also tried to solve it by:
!cp -r /kaggle/input/jigsaw-multilingual-toxic-comment-classification /kaggle/working
Even then I am not able to solve the error.
Can someone please help me out solve this error?
The first code block defines the global variables.
!cp -r /kaggle/input/jigsaw-multilingual-toxic-comment-classification /kaggle/working
SEQUENCE_LENGTH = 128
DATA_PATH = "/kaggle/working/jigsaw-multilingual-toxic-comment-classification"
BERT_PATH = "../input/bert-multi"
BERT_PATH_SAVEDMODEL = os.path.join(BERT_PATH, "/kaggle/input/bert-multi/bert_multi_from_tfhub")
OUTPUT_PATH = "/kaggle/working"
The below code block is the block afer which I am getting the error
def preprocess_and_save_dataset(unprocessed_filename, text_label='comment_text',
seq_length=SEQUENCE_LENGTH, verbose=True):
"""Preprocess a CSV to the expected TF Dataset form for multilingual BERT,
and save the result."""
dataframe = pd.read_csv(os.path.join(DATA_PATH, unprocessed_filename),
index_col='id')
processed_filename = (unprocessed_filename.rstrip('.csv') +
"-processed-seqlen{}.csv".format(SEQUENCE_LENGTH))
pos = 0
start = time.time()
while pos < len(dataframe):
processed_df = dataframe[pos:pos + 10000].copy()
processed_df['input_word_ids'], processed_df['input_mask'], processed_df['all_segment_id'] = (
zip(*processed_df[text_label].apply(preprocess_sentence)))
if pos == 0:
processed_df.to_csv(processed_filename, index_label='id', mode='w')
else:
processed_df.to_csv(processed_filename, index_label='id', mode='a',
header=False)
if verbose:
print('Processed {} examples in {}'.format(
pos + 10000, time.time() - start))
pos += 10000
return
# Process the training dataset.
preprocess_and_save_dataset(wiki_toxic_comment_data)
I tried to move the directory to the Kaggle working folder.
My application is to switch on cam on the client-side, take the frame, perform the ML process on it in the backend and throw it back to the client.
This part of the code (in bold) is throwing error - PngImageFile' object has no attribute 'shape'.
This code line has a problem - frame = imutils.resize(pimg, width=700)
I guess some processing is not in the right format. Please guide
#socketio.on('image')
def image(data_image):
sbuf = io.StringIO()
sbuf.write(data_image)
# decode and convert into image
b = io.BytesIO(base64.b64decode(data_image))
pimg = Image.open(b)
# Process the image frame
frame = imutils.resize(**pimg,** width=700)
frame = cv2.flip(frame, 1)
imgencode = cv2.imencode('.jpg', frame)[1]
# base64 encode
stringData = base64.b64encode(imgencode).decode('utf-8')
b64_src = 'data:image/jpg;base64,'
stringData = b64_src + stringData
# emit the frame back
emit('response_back', stringData)
The problem is that pimg is in PIL image format. While imutils.resize function expects the image in Numpy array format. So, after pimg = Image.open(b) line you need to convert the PIL image to Numpy array like below:
pimg = np.array(pimg)
For this you have to import numpy library like below:
import numpy as np
Try this out. This helped for a similar problem for me.
img_arr = np.array(img.convert("RGB"))
The problem was in the mode of the image. I had to convert it from 'P' to 'RGB'.
print(img)
>> <PIL.PngImagePlugin.PngImageFile image mode=P size=500x281 at 0x7FE836909C10>
I have been coding on ML via Scikit-learn from few months.
but a update has came on scikit object of preprocessing which is OneHotEncoder.
here was a parameter categorical_features which is now changed to categories and now i am not understanding how to writes is values
The code which I am writing is :
from sklearn.preprocessing import LabelEncoder , OneHotEncoder
le = LabelEncoder()
X[:,0] = le.fit_transform(X[:,0])
ohe = OneHotEncoder(categories = X[:,0].all())
X = ohe.fit_transform(X).toarray()
and is showing this error
runcell(0, 'C:/Mobile Videos/OPencv/opencv-master/samples/data/untitled2.py')
Traceback (most recent call last):
File "C:\Mobile Videos\OPencv\opencv-master\samples\data\untitled2.py", line 25, in
X = ohe.fit_transform(X).toarray()
File "C:\Users\Harshit\Anaconda3\lib\site-packages\sklearn\preprocessing_encoders.py", line 372, in fit_transform
return super().fit_transform(X, y)
File "C:\Users\Harshit\Anaconda3\lib\site-packages\sklearn\base.py", line 571, in fit_transform
*return self.fit(X, **fit_params).transform(X)*
File "C:\Users\Harshit\Anaconda3\lib\site-packages\sklearn\preprocessing_encoders.py", line 347, in fit
self._fit(X, handle_unknown=self.handle_unknown)
File "C:\Users\Harshit\Anaconda3\lib\site-packages\sklearn\preprocessing_encoders.py", line 77, in _fit
if len(self.categories) != n_features:
TypeError: object of type 'int' has no len()
And if I am making the parameter auto then it is changing the whole data set into code like while changing the Label to code
Could you please help me out from this problem?????
So I am trying to read a txt file, process it by taking out the stop words, and then output that result into a new file. However, I keep getting the following error:
TypeError: expected a string or other character buffer object
This is my code:
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
f=open('tess1.txt','rU')
stop_words = set(stopwords.words('english'))
raw=f.read()
word_tokens = word_tokenize(raw)
text = nltk.Text(word_tokens)
filtered_sentence = [w for w in word_tokens if not w in stop_words]
if w not in stop_words:
filtered_sentence.append(w)
K = open("tess12.txt", "w")
K.write(filtered_sentence)
K.close()
print(filtered_sentence)
The solution's to write a string inside the buffer:
K.write(str(filtered_sentence))
I'm completely new to opencv and tesseract.
I spent all day trying to make code that would parse game duration from images like that: original image (game duration is in the top left corner)
I came to code that manages to recognize the duration sometimes (about 40% of all cases). Here it is:
try:
from PIL import Image
except ImportError:
import Image
import os
import cv2
import pytesseract
import re
import json
def non_digit_split(s):
return filter(None, re.split(r'(\d+)', s))
def time_to_sec(min, sec):
return (int(min) * 60 + int(sec)).__str__()
def process_img(image_url):
img = cv2.resize(cv2.imread('./images/' + image_url), None, fx=5, fy=5, interpolation=cv2.INTER_CUBIC)
str = pytesseract.image_to_string(img)
if "WIN " in str:
time = list(non_digit_split(str.split("WIN ",1)[1][0:6].strip()))
str = time_to_sec(time[0], time[2])
else:
str = 'Not recognized'
return str
res = {}
img_list = os.listdir('./images')
print(img_list)
for i in img_list:
res[i] = process_img(i)
with open('output.txt', 'w') as file:
file.write(json.dumps(res))
Don't even ask how I came to resizing image, but it helped a little.
I also tried to crop image first like that:
cropped image
but tesseract couldn't find any text here.
I'm sure that the issue I'm trying to solve is pretty easy. Can you please point me the right direction? How should I preprocess it so tesseract will parse it right?
Thanks to #DmitriiZ comment I managed to produce working piece of code.
I made a preprocessor that outputs something like that:
Preprocessed image
Tesseract handles it just fine.
Here is the full code:
try:
from PIL import Image
except ImportError:
import Image
import os
import pytesseract
import json
def is_dark(image):
pixels = image.getdata()
black_thresh = 100
nblack = 0
for pixel in pixels:
if (sum(pixel) / 3) < black_thresh:
nblack += 1
n = len(pixels)
if (nblack / float(n)) > 0.5:
return True
else:
return False
def preprocess(img):
basewidth = 500
wpercent = (basewidth/float(img.size[0]))
hsize = int((float(img.size[1])*float(wpercent)))
#Enlarging image
img = img.resize((basewidth,hsize), Image.ANTIALIAS)
#Converting image to black and white
img = img.convert("1", dither=Image.NONE)
return img
def process_img(image_url):
img = Image.open('./images/' + image_url)
#Area we need to crop can be found in one of two different areas,
#depending on which team won. You can replace that block and is_dark()
#function by just img.crop().
top_area = (287, 15, 332, 32)
crop = img.crop(top_area)
if is_dark(crop):
bot_area = (287, 373, 332, 390)
crop = img.crop(bot_area)
img = preprocess(crop)
str = pytesseract.image_to_string(img)
return str
res = {}
img_list = os.listdir('./images')
print(img_list)
for i in img_list:
res[i] = process_img(i)
with open('output.txt', 'w') as file:
file.write(json.dumps(res))