Das deutsche Python-Forum

Code: Alles auswählen

import pickle

import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


data_dict = pickle.load(open('./data.pickle', 'rb'))

data = np.asarray(data_dict['data'])
labels = np.asarray(data_dict['labels'])

model = RandomForestClassifier()

model.fit(x_train, y_train)

y_predict = model.predict(x_test)

score = accuracy_score(y_predict, y_test)

print('{}% of samples were classified correctly !'.format(score * 100))

f = open('model.p', 'wb')
pickle.dump({'model': model}, f)
f.close()

Code: Alles auswählen

/home/PycharmProjects/SignLanguage/train_classifier.py:13: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
  data = np.asarray(data_dict['data'])
TypeError: float() argument must be a string or a real number, not 'list'

The above exception was the direct cause of the following exception:


Traceback (most recent call last):
  File "/home/PycharmProjects/SignLanguage/train_classifier.py", line 21, in <module>
    model.fit(x_train, y_train)
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/base.py", line 1151, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/ensemble/_forest.py", line 348, in fit
    X, y = self._validate_data(
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/base.py", line 621, in _validate_data
    X, y = check_X_y(X, y, **check_params)
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/utils/validation.py", line 1147, in check_X_y
    X = check_array(
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/utils/validation.py", line 917, in check_array
    array = _asarray_with_order(array, order=order, dtype=dtype, xp=xp)
  File "/home/PycharmProjects/SignLanguage/venv/lib/python3.10/site-packages/sklearn/utils/_array_api.py", line 380, in _asarray_with_order
    array = numpy.asarray(array, order=order, dtype=dtype)
ValueError: setting an array element with a sequence.

Process finished with exit code 1

Code: Alles auswählen

data =  np.asarray([np.asarray(d) for d in data_dict['data']]) # doesn't work 

Code: Alles auswählen

data =  np.asarray(data_dict['data'], dtype=float)

Code: Alles auswählen

ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2912,) + inhomogeneous part.

Code: Alles auswählen

import mediapipe as mp
import cv2
import os
import pickle
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt

mp_hands = mp.solutions.hands
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles

hands = mp_hands.Hands(static_image_mode=True, min_detection_confidence=0.3)

DATA_DIR = "./data"

data = []
labels = []

for dir_ in os.listdir(DATA_DIR):
    for img_path in os.listdir(os.path.join(DATA_DIR, dir_)):
        data_aux = []

        img = cv2.imread(os.path.join(DATA_DIR, dir_, img_path))
        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

        results = hands.process(img_rgb)
        if results.multi_hand_landmarks:
            for hand_landmarks in results.multi_hand_landmarks:
                for i in range(len(hand_landmarks.landmark)):
                    x = hand_landmarks.landmark[i].x
                    y = hand_landmarks.landmark[i].y
                    data_aux.append(x)
                    data_aux.append(y)

            data.append(data_aux)
            labels.append(dir_)

f = open('data.pickle', 'wb')
pickle.dump({'data': data, 'labels': labels}, f)
f.close()

Code: Alles auswählen

np.array(data) bevor pickle.dump() 

Code: Alles auswählen

VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
  np.array(data)

Code: Alles auswählen

print([np.asarray(d).shape for d in data_dict['data']]

Code: Alles auswählen

[(42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,), (42,)]
Traceback (most recent call last):
  File "/home/PycharmProjects/SignLanguage/train_classifier.py", line 16, in <module>
    data =  np.asarray(data_dict['data'], dtype=float)
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2912,) + inhomogeneous part.

Code: Alles auswählen

#!/usr/bin/env python3
import os
import pickle
from pathlib import Path

import cv2
from mediapipe.solutions.hands import Hands

DATA_PATH = Path("data")


def main():
    hands = Hands(static_image_mode=True, min_detection_confidence=0.3)
    data = []
    labels = []
    for sub_path in (path for path in DATA_PATH.iterdir() if path.is_dir()):
        for image_path in (
            path for path in sub_path.iterdir() if path.is_file()
        ):
            data_aux = []
            results = hands.process(
                cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)
            )
            if results.multi_hand_landmarks:
                for hand_landmarks in results.multi_hand_landmarks:
                    for coordinate in hand_landmarks.landmark:
                        data_aux.append(coordinate.x)
                        data_aux.append(coordinate.y)

                data.append(data_aux)
                labels.append(sub_path)

    with open("data.pickle", "wb") as file:
        pickle.dump({"data": data, "labels": labels}, file)


if __name__ == "__main__":
    main()

Code: Alles auswählen

#!/usr/bin/env python3
import os
import pickle
from pathlib import Path

import cv2
from mediapipe.solutions.hands import Hands

DATA_PATH = Path("data")


def main():
    hands = Hands(static_image_mode=True, min_detection_confidence=0.3)
    data_and_labels = []
    for sub_path in (path for path in DATA_PATH.iterdir() if path.is_dir()):
        for image_path in (
            path for path in sub_path.iterdir() if path.is_file()
        ):
            data_aux = []
            results = hands.process(
                cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)
            )
            if results.multi_hand_landmarks:
                data_aux.extend(
                    (coordinate.x, coordinate.y)
                    for hand_landmarks in results.multi_hand_landmarks
                    for coordinate in hand_landmarks.landmark
                )
                data_and_labels.append((data_aux, sub_path))

    with open("data.pickle", "wb") as file:
        pickle.dump(data_and_labels, file)


if __name__ == "__main__":
    main()

Code: Alles auswählen

#!/usr/bin/env python3
import os
import pickle
from pathlib import Path

import cv2
from mediapipe.solutions.hands import Hands

DATA_PATH = Path("data")


def main():
    hands = Hands(static_image_mode=True, min_detection_confidence=0.3)
    data_and_labels = []
    for sub_path in (path for path in DATA_PATH.iterdir() if path.is_dir()):
        for image_path in (
            path for path in sub_path.iterdir() if path.is_file()
        ):
            results = hands.process(
                cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)
            )
            if results.multi_hand_landmarks:
                data_and_labels.append(
                    (
                        [
                            (coordinate.x, coordinate.y)
                            for hand_landmarks in results.multi_hand_landmarks
                            for coordinate in hand_landmarks.landmark
                        ],
                        sub_path,
                    )
                )

    with open("data.pickle", "wb") as file:
        pickle.dump(data_and_labels, file)


if __name__ == "__main__":
    main()

Code: Alles auswählen

[..., ([(0.3775956332683563, 0.5386132597923279), (0.4242878258228302, 0.5439502596855164), (0.45684775710105896, 0.5842125415802002), (0.4652678668498993, 0.6323069334030151), (0.466773122549057, 0.6693066954612732), (0.47439640760421753, 0.5882108211517334), (0.5042067170143127, 0.6475873589515686), (0.5086818337440491, 0.6876282691955566), (0.5048747062683105, 0.7186694145202637), (0.4496690034866333, 0.5951089262962341), (0.4633995294570923, 0.6819579005241394), (0.4674365520477295, 0.7289001941680908), (0.4705360233783722, 0.7637642621994019), (0.42224380373954773, 0.6048421263694763), (0.4277583956718445, 0.6780377626419067), (0.42316964268684387, 0.6603876352310181), (0.42096760869026184, 0.6366013288497925), (0.39536792039871216, 0.6151334643363953), (0.4052458107471466, 0.6753289103507996), (0.40337082743644714, 0.6603569388389587), (0.40039676427841187, 0.6392402052879333)], PosixPath('data/16'))]