search

pse-ecn / pose-sensitive-embedding

Pose Sensitive Embedding for Person Re-Identification (PSE)
112 stars 36 forks source link

InvalidArgumentError when predict features #16

Closed THHHomas closed 6 years ago

THHHomas commented 6 years ago

Dear authors: thanks to your excellent work, but i have some problems when predict the features. I download the pretrained model and use the command "python predictor_preid.py --model-dir=./models --data=./Data/Market-1501-v15.09.15 --dataset-name=market1501 --batch-size=128 --network-name=resnet_v1_50_views" more, I write my checkpoint file like this: model_checkpoint_path: "model.ckpt-104801" all_model_checkpoint_paths: "model.ckpt-104801"

and I encounter the following error: tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [7,7,3,64] rhs shape= [7,7,17,64] [[Node: save/Assign_382 = Assign[T=DT_FLOAT, _class=["loc:@resnet_v1_50/conv1/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](resnet_v1_50/conv1/weights, save/RestoreV2/_777)]]

THHHomas commented 6 years ago

how could I get 17 channels to calculate the features of a image? thanks.