smidm

yolox_pose/configs/yolox-pose_l_4xb64-300e_coco.py:    init_cfg=dict(checkpoint='https://download.openmmlab.com/mmyolo/v0/yolox/'
yolox_pose/configs/yolox-pose_l_4xb64-300e_coco.py-                  'yolox_l_fast_8xb8-300e_coco/yolox_l_fast_8xb8-300e_'
--
uniformer/configs/td-hm_uniformer-s-8xb64-210e_coco-448x320.py:            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'
uniformer/configs/td-hm_uniformer-s-8xb64-210e_coco-448x320.py-            'uniformer/uniformer_small_in1k.pth')))
--
yolox_pose/configs/py_yolox_pose_s_8xb32_300e_coco.py:        checkpoint='https://download.openmmlab.com/mmyolo/v0/yolox/'
yolox_pose/configs/py_yolox_pose_s_8xb32_300e_coco.py-        'yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_'
--
uniformer/configs/td-hm_uniformer-b-8xb128-210e_coco-256x192.py:            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'

smidm

wholebody_2d_keypoint/topdown_heatmap/coco-wholebody/td-hm_hrnet-w32_8xb64-210e_coco-wholebody-384x288.py:            checkpoint='https://download.openmmlab.com/mmpose/'
wholebody_2d_keypoint/topdown_heatmap/coco-wholebody/td-hm_hrnet-w32_8xb64-210e_coco-wholebody-384x288.py-            'pretrain_models/hrnet_w32-36af842e.pth'),
--
wholebody_2d_keypoint/rtmpose/ubody/rtmpose-m_8xb64-270e_coco-ubody-wholebody-256x192.py:            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'
wholebody_2d_keypoint/rtmpose/ubody/rtmpose-m_8xb64-270e_coco-ubody-wholebody-256x192.py-            'rtmpose/cspnext-m_udp-aic-coco_210e-256x192-f2f7d6f6_20230130.pth'  # noqa: E501
--
wholebody_2d_keypoint/topdown_heatmap/coco-wholebody/td-hm_hrnet-w32_dark-8xb64-210e_coco-wholebody-256x192.py:            checkpoint='https://download.openmmlab.com/mmpose/'
wholebody_2d_keypoint/topdown_heatmap/coco-wholebody/td-hm_hrnet-w32_dark-8xb64-210e_coco-wholebody-256x192.py-            'pretrain_models/hrnet_w32-36af842e.pth')

smidm

smidm

from pyflann import *
import numpy as np

dataset = np.array(
    [[1., 1, 1, 2, 3],
     [10, 10, 10, 3, 2],
     [100, 100, 2, 30, 1]
     ])
testset = np.array(
    [[1., 1, 1, 1, 1],

smidm

import numpy as np
import scipy.optimize

a = np.array([[0, 0], [1, 1], [2, 2]])
b = np.array([[0, 1], [2, 2.2], [1, 1.2], [0, 0]])

indices = np.indices((len(a), len(b)))
# array([[[0, 0, 0, 0],
#         [1, 1, 1, 1],
#         [2, 2, 2, 2]],

smidm

import pandas as pd
import errno
import numpy as np
import sys
import warnings


def save_mot(filename, df):
    df.to_csv(filename, header=False, index=False)

smidm

smidm

import matplotlib.pylab as plt
import numpy as np

fig = plt.figure()
closed = False

def handle_close(evt):
    global closed
    closed = True

smidm

Množiny. Teorie matic. Soustavy lineárních rovnic.
	Gaussova eliminace
	Diskriminant
	Invertibilni matice, singularni matice
	Linearni zobrazeni, eigenvalues

Základy matematické analýzy. Metody aproximace funkcí. Metoda nejmenších čtverců. Aplikace pro hledání modelů z naměřených reálných dat.
	Lagrangeho multiplikatory
	Newtonova metoda
	Linearni regrese

smidm

#!/usr/bin/env python

from PySide.QtCore import *
from PySide.QtGui import *
import cv2
import sys

class MainApp(QWidget):

    def __init__(self):