Closed MBoaretto25 closed 3 years ago
I'm using the MS-Celeb-1M dataset, downloaded from the link posted in README.md
1 . I converted the data to tfrecords following the steps provided in the documetation for binary images.
`
batch_size: 8 input_size: 112 embd_shape: 128 sub_name: 'arc_mbv2' backbone_type: 'MobileNetV2' # 'ResNet50', 'MobileNetV2' head_type: ArcHead # 'ArcHead', 'NormHead' is_ccrop: False # central-cropping or not
train_dataset: './data/imgs_full.tfrecord' binary_img: True num_classes: 85742 num_samples: 5822653 epochs: 100 base_lr: 0.01 w_decay: !!float 5e-4 save_steps: 100
test_dataset: '.test/' `
But I'm still getting loss=nan. Is is normal for the initial epochs? Is it a tfrecords error?
I'm using the MS-Celeb-1M dataset, downloaded from the link posted in README.md
1 . I converted the data to tfrecords following the steps provided in the documetation for binary images.
`
general
batch_size: 8 input_size: 112 embd_shape: 128 sub_name: 'arc_mbv2' backbone_type: 'MobileNetV2' # 'ResNet50', 'MobileNetV2' head_type: ArcHead # 'ArcHead', 'NormHead' is_ccrop: False # central-cropping or not
train
train_dataset: './data/imgs_full.tfrecord' binary_img: True num_classes: 85742 num_samples: 5822653 epochs: 100 base_lr: 0.01 w_decay: !!float 5e-4 save_steps: 100
test
test_dataset: '.test/'
`
But I'm still getting loss=nan. Is is normal for the initial epochs? Is it a tfrecords error?