def _init_training(self, learningRate, dataset, useDatabase):
# Dataset is COCO
print("Initiating training of Sanitizer MaskGenerator")
print("Loading COCO")
from pycocotools.coco import COCO
from os import path
annFile = topDir + '/annotations/instances_{}.json'.format(dataset)
self.cocoPath = topDir + '/data/{}'.format(dataset)
self.coco = COCO(annFile)
self.personCatID = self.coco.getCatIds(catNms=['person'])[0]
self.cocoImageIds = self.coco.getImgIds(catIds=self.personCatID)
def is_not_crowd(imgId):
annIds = self.coco.getAnnIds(imgIds=imgId,
catIds=self.personCatID,
iscrowd=False)
annotation = self.coco.loadAnns(annIds)[0]
return not annotation["iscrowd"]
self.cocoImageIds = list(filter(is_not_crowd, self.cocoImageIds))
self.cocoOnDisk = path.exists(self.cocoPath)
print("Coco dataset size: {}".format(len(self.cocoImageIds)))
print("Coco images found on disk:", self.cocoOnDisk)
# Init LMDB_helper
if useDatabase:
self.lmdb = LMDBHelper("a")
self.lmdb.verbose = False
# Init loss function and optimizer
self.optimizer = torch.optim.Adam(self.maskGenerator.parameters(),
lr=learningRate,
amsgrad=True)
self.loss_function = torch.nn.BCELoss()
# Init DensePose extractor
self.denseposeExtractor = DensePoseWrapper()
def _initTraining(self, learningRate, dataset, useDatabase):
# Dataset is DeepFashion2
print("Initiating training of DescriptionExtractor")
print("Loading DeepFashion2")
from torchvision import transforms
from torchvision.datasets import CocoDetection
self.annFile = topDir + '/annotations/deepfashion2_{}.json'.format(
dataset)
self.cocoImgPath = topDir + '/data/DeepFashion2/{}'.format(dataset)
self.useDatabase = useDatabase
self.dataset = CocoDetection(
self.cocoImgPath,
self.annFile,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Lambda(lambda x: x.permute(1, 2, 0)),
transforms.Lambda(lambda x: (x * 255).byte().numpy()),
transforms.Lambda(lambda x: x[:, :, ::-1])
]))
# Init LMDB_helper
if useDatabase:
self.lmdb = LMDBHelper("a")
self.lmdb.verbose = False
self.denseposeExtractor = DensePoseWrapper()
self.sanitizer = Sanitizer()
self.sanitizer.load_model(topDir + "/models/Sanitizer.pth")
self.uvMapper = UVMapper()
# PyTorch things
self.optimizer = torch.optim.Adam(self.classifier.parameters(),
lr=learningRate,
amsgrad=True)
self.lossFunction = torch.nn.BCEWithLogitsLoss()
def _initTraining(self, learningRate, datasetName, useLMDB):
self.datasetName = datasetName
from DenseSense.algorithms.DensePoseWrapper import DensePoseWrapper
from DenseSense.algorithms.Sanitizer import Sanitizer
self.denseposeExtractor = DensePoseWrapper()
self.sanitizer = Sanitizer()
self.sanitizer.load_model(topDir + "/models/Sanitizer.pth")
if datasetName in ActionClassifier.COCO_Datasets:
print("Loading COCO dataset: " + datasetName)
from pycocotools.coco import COCO
from os import path
annFile = topDir + '/annotations/instances_{}.json'.format(
datasetName)
self.cocoPath = topDir + '/data/{}'.format(datasetName)
self.coco = COCO(annFile)
personCatID = self.coco.getCatIds(catNms=['person'])[0]
self.dataset = self.coco.getImgIds(catIds=personCatID)
elif datasetName in ActionClassifier.AVA_Datasets:
print("Loading AVA dataset: " + datasetName)
import csv
from collections import defaultdict
from DenseSense.utils.YoutubeLoader import YoutubeLoader
annFile = topDir + "/annotations/{}.csv".format(
datasetName.replace("_predictive", ""))
self.dataset = defaultdict(lambda: defaultdict(defaultdict))
with open(annFile, 'r') as csvFile:
reader = csv.reader(csvFile)
for row in reader:
video, t, x1, y1, x2, y2, action, person = row
actions = {action}
if person in self.dataset[video][t]:
actions = actions.union(
self.dataset[video][t][person]["actions"])
self.dataset[video][t][person] = {
"bbox": (x1, y1, x2, y2),
"actions": actions
}
ordered_data = []
for key, video in self.dataset.items():
ordered_data.append((key, []))
for t, annotation in video.items():
ordered_data[-1][1].append((int(t), annotation))
ordered_data[-1][1].sort(key=lambda x: x[0])
self.dataset = ordered_data
self.youtubeLoader = YoutubeLoader(verbose=False)
for key, video in self.dataset:
self.youtubeLoader.queue_video(key, video[0][0], video[-1][0])
self.current_video_index = 0
self.current_video_frame_index = 0
self.tracker = Tracker()
else:
raise Exception("Unknown dataset")
self.useLMDB = useLMDB
if useLMDB:
self.lmdb = LMDBHelper("a", max_size=1028 * 1028 * 1028 * 32)
self.lmdb.verbose = False
self.optimizer = torch.optim.Adam(self._AE_model.parameters(),
lr=learningRate)
self.loss_function = torch.nn.BCELoss()