mkocabas

import torchvision
import os.path as osp
import numpy as np
import cv2
import torch
import time

def get_video_opencv(fname):

    vid_tensor = []

mkocabas

#!/usr/bin/env bash
mkdir coco
cd coco/

wget http://images.cocodataset.org/zips/train2017.zip
wget http://images.cocodataset.org/zips/val2017.zip

unzip train2017.zip
unzip val2017.zip

mkocabas

import os
import subprocess
from multiprocessing import Process

NUM_PROCESS = 1 # define number of processes to speed up

VIDEOS_DIR = 'Videos' # path to Human3.6M videos

def find_files():
    SUBJECTS = [1, 5, 6, 7, 8, 9, 11]

mkocabas

import dgl
import torch
import torch.nn as nn

def build_pose_graph():
    g = dgl.DGLGraph()

    g.add_nodes(16)

    edge_list = [(0, 1), (1, 2), (2, 6), (6, 3), (3, 4),

mkocabas

import numpy as np
import json
import math
import matplotlib.pyplot as plt


def showAnns(jts):
    # c = (np.random.random((1, 3)) * 0.6 + 0.4).tolist()[0]
    c = [0.7, 0.9, 0.8]

mkocabas

import numpy as np
import cv2
import src.data_utils as data_utils
from src.data_utils import load_data, project_to_cameras
import os
import matplotlib.pyplot as plt
from src import cameras, viz


def drawlines(img1,img2,lines,pts1,pts2):

mkocabas

from __future__ import print_function

import torch
import torch.nn as nn
import torch.nn.functional as F


class SoftArgmax(nn.Module):
    def __init__(self):
        super(SoftArgmax, self).__init__()

mkocabas

from __future__ import print_function, absolute_import

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.models as models

class FPN(nn.Module):
    def __init__(self,
                 backbone='resnet50',

mkocabas

import torch
import torch.nn.functional as F
from torch.nn.parameter import Parameter
import numpy as np


class SpatialSoftmax(torch.nn.Module):
	def __init__(self, height, width, channel, temperature=None, data_format='NCHW', unnorm=False):
		super(SpatialSoftmax, self).__init__()
		self.data_format = data_format

mkocabas

import torch

# Original author: Francisco Massa:
# https://github.com/fmassa/object-detection.torch
# Ported to PyTorch by Max deGroot (02/01/2017)
def nms(boxes, scores, overlap=0.5, top_k=200):
    """Apply non-maximum suppression at test time to avoid detecting too many
    overlapping bounding boxes for a given object.
    Args:
        boxes: (tensor) The location preds for the img, Shape: [num_priors,4].