search

seasonSH / Probabilistic-Face-Embeddings

(ICCV 2019) Uncertainty-aware Face Representation and Recognition
MIT License
340 stars 58 forks source link

ValueError: Dimension 0 in both shapes must be equal, but are 0 and 512 #16

Open jordanmeallier1 opened 3 years ago

jordanmeallier1 commented 3 years ago

Hi , I try to run the PFE model. It works well when I run eval_lfw with tensorflow 2.1 and tensorflow 1.x but when I tried to run it with tensorflow 2.2 and more I have this error : ValueError: Node 'gradients/UncertaintyModule/fc_log_sigma_sq/BatchNorm/cond/FusedBatchNorm_1_grad/FusedBatchNormGrad' has an _output_shapes attribute inconsistent with the GraphDef for output #3: Dimension 0 in both shapes must be equal, but are 0 and 512. Shapes are [0] and [512] It happens when the model is loading when it does saver = tf.compat.v1.train.import_meta_graph(meta_file, clear_devices=True, import_scope=scope) to import the meta file of the PFE_sphere64_msarcface_am model Capture du 2021-06-28 10-49-40 Capture du 2021-06-28 10-43-59 To reproduce the error : download https://drive.google.com/drive/folders/10RnChjxtSAUc1lv7jbm3xkkmhFYyZrHP?usp=sharing and run eval_lfw with parameters --model_dir pretrained/PFE_sphere64_msarcface_am --dataset_path data/Dataset --protocol_path ./proto/pairs_dataset.txt

Thank you for your help

romakail commented 3 years ago

+1

tanpengshi commented 3 years ago

Same issue for me! Can the creator make the code compatible with Tensorflow 2?