from __future__ import division
from __future__ import print_function
import os
import time
from utils.utils import *
from config import parse_opts
from torch.utils.data import DataLoader
import factory.model_factory as model_factory
from transforms.target_transforms import ClassLabel
from factory.data_factory import get_validation_set
from transforms.temporal_transforms import TemporalCenterCrop
from transforms.spatial_transforms import Compose, Normalize, ToTensor, CenterCrop
os.environ["CUDA_VISIBLE_DEVICES"] = '1' # 运行环境
config = parse_opts() # 配置解析
config = prepare_output_dirs(config) # 输出文件夹初始化
config = init_cropping_scales(config) # 裁剪配置
config = set_lr_scheduling_policy(config) # 学习率配置
# 均值和方差设置
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
# 设置转换函数
norm_method = Normalize(mean, std)
validation_transforms = {
'spatial':
Compose([CenterCrop(config.spatial_size),
ToTensor(255), norm_method]),
'temporal':
TemporalCenterCrop(config.sample_duration),
'target':
text_file.close()
####################################################################
####################################################################
if __name__ == "__main__":
count = 0
while count < len(song_list):
print('=' * 60)
print(song_list[count])
selected_music = song_list[count]
count += 1
config = parse_opts()
config = prepare_walter_dirs(config, selected_music)
audio_url = os.path.join(config.walter_ip, selected_music, 'audio',
'input_audio.wav')
video_url = os.path.join(config.walter_ip, selected_music,
'input_resize_480_360.mp4')
audio_file = os.path.join(config.video_path, 'audio',
'input_audio.wav')
input_video = os.path.join(config.video_path,
'input_resize_480_360.mp4')
out_audio_dir = os.path.join(config.video_path, 'audio')
out_gif_dir = os.path.join(config.video_path, 'gif')
max_freq_csv = os.path.join(config.video_path, 'max_freq.csv')
logging.basicConfig(format = '%(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logger = logging.getLogger(__name__)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
labels = ["A", "L", "H", "C", "R", "U", "P", "D", "F", "E", "N", "S", "G"]
# labels = ["A", "L", "H", "C", "R", "U", "P", "D", "F", "E", "N", "T", "S", "G"]
label2index = {}
for label in labels:
label2index[label] = len(label2index)
opts = parse_opts()
seed = opts.seed
debugging = opts.debugging
testing_phase = opts.testing
use_embedding = opts.use_embedding
reading_data = opts.reading_data
use_lowercase = opts.use_lowercase
unroll = opts.unroll
replace_digits = opts.replace_digits
predict_remote = opts.predict_remote
logger.info("using seed %d" % seed)
logger.info("is debugging: %s" % debugging)
logger.info("testing: %s" % testing_phase)
logger.info("predict remote edges: %s" % predict_remote)
import os
import time
import numpy as np
from collections import defaultdict
from sklearn.metrics import average_precision_score
import torch
from torch import nn, optim
from torch.utils.data import DataLoader
import torch.backends.cudnn as cudnn
from lib.dataset import VideoDataset
from lib import slowfastnet
from tensorboardX import SummaryWriter
from config import parse_opts
# TODO: remove from being global
params = parse_opts()
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self):
self.reset()
def reset(self):
self.val = 0
self.avg = 0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
video_features.append(outputs.cpu().data)
video_features = torch.cat(video_features)
elif opt.feature_type == 'OF':
# preprocess
transforms = Compose([Scale(opt.sample_size),
CenterCrop(opt.sample_size),
ToTensor(),
Normalize(opt.mean, [1, 1, 1])])
frames = [transforms(img) for img in frames]
frames = torch.stack(frames, 0).permute(1, 0, 2, 3)
video_feature = get_OF_feature(frames)
feats.append(video_feature)
return feats
def get_OF_feature(frames, opt):
video_features = []
return video_features
if __name__ == "__main__":
# test
opt = parse_opts()
opt.frame_root = "/home/qianyu/task_video/data/ucf/ucf101-frames/"
opt.sample_size = 16
feats = feature_extract(opt)
print(len(feats))
