search

auroua / InsightFace_TF

Insight Face on TensorFlow
MIT License
697 stars 253 forks source link

Pre-training model #14

Open Drsea123 opened 6 years ago

Drsea123 commented 6 years ago

when I load the resnet_v1_50,ckpt in my model,there is the error in my pycharm: NotFoundError (see above for traceback): Tensor name "arcface_loss/embedding_weights" not found in checkpoint files ./output/ckpt/resnet_v1_50.ckpt [[Node: save_1/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_INT32, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_1/Const_0_0, save_1/RestoreV2/tensor_names, save_1/RestoreV2/shape_and_slices)]]

what should I do ? please?

Drsea123 commented 6 years ago

@auroua

auroua commented 6 years ago

I have uploaded two new model, you can test with the new ckpt file.

Drsea123 commented 6 years ago

@auroua The new model is the resnet_v1_50? I want to test it, please?

auroua commented 6 years ago

It's using resnet in L_Resnet_E_IR.py.

Drsea123 commented 6 years ago

I'm so sorry because I'm a new player.If I want to use the pre-training model that is the resnet_v1_50 pretrained model download link. I have loaded it.I revised "# restore_saver.restore(sess, '/home/aurora/workspaces2018/InsightFace_TF/output/ckpt/InsightFace_iter_1110000.ckpt') " to " restore_saver.restore(sess, 'home/user//InsightFace_TF/output/ckpt/resnet_v1_50)",But it can't use. can you help me? @auroua

LJXLJXLJX commented 5 years ago

Have you solved it？ I tried to load the pretrained resnet50.

restore_saver = tf.train.Saver()
restore_saver.restore(sess, './models/resnet_v1_50.ckpt')

And I met the same problem.

xiaqing10 commented 4 years ago

and I meet the same error, no Tensor name "arcface_loss/embedding_weights" not found. I use the newest model and project.