linchuang

discussion!

11

Thanks for your work! I am a post student interested in lipreading!!!! Based on your code ，I have achieved a rather good result as follow: [Epoch 66] Out of 256...

accuarcy

2

hello,when i use your pre-trained model(rgb_0.946) to test ucf-101 split1, its accuracy is around 0.91!

when i try to preload /data/checkpoints/rgb_scratch_kin600 NotFoundError (see above for traceback): Key RGB/inception_i3d/Conv3d_1a_7x7/batch_norm/beta not found in checkpoint [[Node: save/RestoreV2 = RestoreV2[dtypes=[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_188/_87 = _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",...

affine_matrix = cv2.getAffineTransform(dst_pts.astype(np.float32), src_pts.astype(np.float32))？ According Opencv,"def getAffineTransform(src, dst): " ,source dst shuould be placed first?

something about X

1

"X = tf.placeholder(tf.float32, shape=[128, 32, 32, 64])" Would you please explain about X? I infer that 32,32means width and height, how about 128 and 64? Thanks a lot !