Hello,
I am following your gits and I got train.record file and validation.record file by using face-mesh-generator git with 300w dataset.
And Now I try to train cnn-facial-landmark.
But I can't proceed more..
Could you help me?
But There are some error as like below.
How can I resolve this ?
File "/home/a/anaconda3/envs/ddds/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Feature: label/marks (data type: string) is required but could not be found.
[[{{node ParseSingleExample/ParseExample/ParseExampleV2}}]]
[[IteratorGetNext]] [Op:__inference_train_function_3227]
Hello, I am following your gits and I got train.record file and validation.record file by using face-mesh-generator git with 300w dataset. And Now I try to train cnn-facial-landmark. But I can't proceed more.. Could you help me?
I did like below.
python3 landmark.py --train_record=train_300w.record --val_record=validate_300w.record --batch_size=32 --epochs=10
But There are some error as like below. How can I resolve this ?
File "/home/a/anaconda3/envs/ddds/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute inputs, attrs, num_outputs) tensorflow.python.framework.errors_impl.InvalidArgumentError: Feature: label/marks (data type: string) is required but could not be found. [[{{node ParseSingleExample/ParseExample/ParseExampleV2}}]] [[IteratorGetNext]] [Op:__inference_train_function_3227]
Function call stack: train_function