sejongresearch / LandmarkRetrieval

AI대장 팀, 세종대 인근 랜드마크 검색 (2019)
5 stars 4 forks source link

Test Result2 #42

Open glee1228 opened 5 years ago

glee1228 commented 5 years ago

parameter& Dataset :

[고정 파라미터]

Dataset : Sejong University building( in Seoul ) Image Dataset input image size : ( 128,128,3 ) netVLAD clustering num : 7 training triplet data size : 700 ( 100 * 3 pairs images per class ) optimizer : SGD(learning rate=0.01, decay=1e-6, momentum=0.9, nesterov=True) triplet loss margin : 1e-4

[유동 파라미터]

base model : VGG16( pretrained weights : 'imagenet') total epochs : 15 train batch size : 64 T-SNE Result vgg16_tsne_15_64

base model : VGG16( pretrained weights : 'imagenet') total epochs : 25 train batch size : 64 T-SNE Result vgg16_tsne_25_64

base model : xception( pretrained weights : 'imagenet') total epochs : 15 train batch size : 64 T-SNE Result xception_tsne_15_64

base model : xception( pretrained weights : 'imagenet') total epochs : 15 train batch size : 64 T-SNE Result xception_tsne_25_64

base model : inceptionV3( pretrained weights : 'imagenet') total epochs : 15 train batch size : 64 T-SNE Result inception_v3_tsne_15_64

base model : inceptionV3( pretrained weights : 'imagenet') total epochs : 20 train batch size : 64 T-SNE Result inception_v3_tsne_20_64

base model : densenet121( pretrained weights : 'imagenet') total epochs : 15 train batch size : 64 T-SNE Result densenet121_tsne_15_64

base model : densenet169( pretrained weights : 'imagenet') total epochs : 15 train batch size : 32 T-SNE Result densenet169_tsne_15_32