Junxuan Huang

I already cropped image to 256*176,but still get dimension error , please help

3

python test.py --dataroot ./dataset --name fashion_PATN --model PATN --phase test --dataset_mode keypoint --norm instance --batchSize 1 --resize_or_crop no --gpu_ids 0 --BP_input_nc 18 --no_flip --which_model_netG PATN --checkpoints_dir ./checkpoints/DeepFashion/ --pairLst ./dataset/pair.csv --which_epoch...

tf_nndistance_so.so: undefined symbo when running demo.py

6

I'm using CUDA10.0 tensorflow 1.13 and python 3.7 and compile of pc_distance is successful but when I run demo.py tensorflow.python.framework.errors_impl.NotFoundError: /media/roman/storage/pcn/pc_distance/tf_nndistance_so.so: undefined symbol: _ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringEv is there anything to be change...

What could be the reason if I get high recall but low 3D AP ?

2

During my test my mode get result in VAL data 2019-07-26 13:22:38,981 INFO 2019-07-26 13:22:38.981755 2019-07-26 13:22:38,981 INFO final average detections: 22.273 2019-07-26 13:22:38,981 INFO final average rpn_iou refined: 0.000...

Can't run City_car test script

1

Exception in user code: ------------------------------------------------------------ Traceback (most recent call last): File "/usr/lib/python3/dist-packages/urllib3/connection.py", line 141, in _new_conn (self.host, self.port), self.timeout, **extra_kw) File "/usr/lib/python3/dist-packages/urllib3/util/connection.py", line 83, in create_connection raise err File "/usr/lib/python3/dist-packages/urllib3/util/connection.py",...

would you like to give us more examples showing how did imu data translate to text or videos in applications? Thanks

How to create motion clip file (.npz) from other dataset

3

Great Work! It is amazing , May I ask what is the data structure of motion clip file. If I have some skeleton coordinates for each frame, how should I...

How convert motion file (.mot) to mujoco?

3

Great works! But is it possible to create MJCF motion file from the opensim motion (.mot ) ?

frames are different in radar feature and 3D pose label

4

I try to use subject{i}_featuremap.npy as training data and 3D pose label as label to training , just like MARS dataset . But I found the frames in each subject{i}_featuremap.npy...

How to visualize the 3D pose?

2

May I ask how to visualize the 3D pose like demo , and in results of mmWave Radar like "random_split_protocol1.npy" is that pose prediction result ? Which pretraned model should...

Pretrained weights not available

2

Hi, I tired the pretrained weights but the prediction was very bad , the values for XYZ are in [-600,1000]. So I trained the model from scratch. but still get...