Open angela-zhao opened 6 years ago
I can successfully run the model on a virtual machine with GPUs but am unable to run the same code on my local computer using a CPU.
I am getting the following error: InvalidArgumentError (see above for traceback): /Users/angela.zhao/Documents/Projects/text-similarity/S2V/s2v_models/BS400-W300-S1200-Glove-BC-bidir/train/model.ckpt-114466.data-00000-of-00001; Invalid argument [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, 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/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
Was this the result of loading a checkpoint for evaluation ? Can you share the command that was used ?
I used sh eval.sh. The same command worked on a VM with GPUs.
sh eval.sh
I can successfully run the model on a virtual machine with GPUs but am unable to run the same code on my local computer using a CPU.
I am getting the following error: InvalidArgumentError (see above for traceback): /Users/angela.zhao/Documents/Projects/text-similarity/S2V/s2v_models/BS400-W300-S1200-Glove-BC-bidir/train/model.ckpt-114466.data-00000-of-00001; Invalid argument [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, 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/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]