search

DenisTome / Lifting-from-the-Deep-release

Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"
https://denistome.github.io/papers/lifting-from-the-deep
GNU General Public License v3.0
450 stars 133 forks source link

I can't run the demo.py. #30

Closed Ssrzbao closed 5 years ago

Ssrzbao commented 5 years ago

A problem has occurred when I run the demo.py. OutOfRangeError (see above for traceback): Read less bytes than requested [[{{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)]] [[{{node save/RestoreV2/_301}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_306_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]] I have changed the Batch_Size=1, but the operation is invalid. My environment is ubuntu16.04 python=2.7 tensorflow=1.11

DenisTome commented 5 years ago

you should be able to run it with batch_size 1.

Regardless, that is a range error. Have you checked that there are actually detections?

NguyenDangBinh commented 5 years ago

dear Dr, I am a master student about Mechatronic. Can you send me a full code about CNN? I need them for learning. Thank you so much

DenisTome commented 5 years ago

The public code is only what we are going to release so far.

In the future we might provide the whole framework for training the model as well.