chenyilun95 / tf-cpn

Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018)

chenyilun95/tf-cpn Issues

> @dagongji10 Excuse me, can I ask you a question? Must I provide bbox of pictures when I test a picture?Could you please give me a script which can visualize test results like what you show? Thank you very much
Updated 3 years ago3
is it possible to add new joint in the skel and retrain the model
Updated 3 years ago
How to decrease Batch size
Updated 4 years ago4
About detect single person
Updated 4 years ago16
Using just GlobalNet
Updated 4 years ago
just global net with OHKM
Updated 4 years ago1
Batch size
Updated 4 years ago3
where is ”person_detection_minival411_human553.json“
Updated 4 years ago2
No module named 'lib_kernel.lib_nms.nms.gpu_nms
Updated 4 years ago7
How to apply inference on own dataset without GT_bbox(.json)?
Updated 5 years ago
labels = [label15, label11, label9, label7]
Closed 5 years ago
coco dataset? which year?
Closed 5 years ago
train train
Closed 5 years ago
from nets.basemodel import resnet50, resnet_arg_scope, resnet_v1
Closed 5 years ago
"read none image" during training?
Closed 5 years ago1
strange results
Updated 5 years ago
why? gk15 = (23, 23) gk11 = (17, 17) gk9 = (13, 13) gk7 = (9, 9)
Updated 5 years ago
global_loss += tf.reduce_mean(tf.square(global_out - global_label)) / len(labels); global_loss /= 2;.so damn hard to understand
Updated 5 years ago
An error occurred after I executed： `python3 mptest.py -d 0-1 -m log/model_dump/snapshot_350.ckpt`
Closed 5 years ago
About code running environment
Closed 5 years ago
bbox is necessary in Test?
Closed 5 years ago2
detect one single image using tf-cpn
Updated 5 years ago2
ImportError: dlopen: cannot load any more object with static TLS
Updated 5 years ago1
How do I test with pictures?
Updated 5 years ago
Strange results
Updated 5 years ago1
Has anyone tested on the MPII dataset?
Updated 5 years ago
can you provide really parameter
Updated 5 years ago
Data augmentation
Updated 5 years ago
can anyone give a net structure pic, thanks
Updated 5 years ago
crop_size = min(crop_size, objcenter[0] / width * min_shape * 2. - 1.) so damn hard to understand.
Updated 5 years ago2
using dataset COCO2017
Updated 5 years ago1
memoryview underlying buffer is no c-contiguous
Closed 5 years ago3
run the code in python3 ?
Updated 5 years ago
about the test result
Updated 5 years ago
Is human detection boxes results after NMS?
Updated 5 years ago1
Ensembled models of CPN with different ground truth heatmaps.
Updated 5 years ago1
ImportError: libcudart.so.8.0: cannot open shared object file: No such file or directory
Updated 5 years ago2
Which dataset should I download from "http://cocodataset.org/#download" for trainvalminusminival and minival ?
Closed 5 years ago6
UnicodeDecodeError
Closed 6 years ago
UnicodeDecodeError
Closed 6 years ago
error ：no default __reduce__ due to non-trivial __cinit__
Closed 6 years ago4
about the object detector FPN code
Updated 6 years ago1
something about continue_train
Closed 6 years ago4
where is the test-dev dataset?
Closed 6 years ago
Data set choice
Updated 6 years ago
Is there a label for each joint prediction to tell us whether it's hard or easy?
Updated 6 years ago
train refine_loss question.
Closed 6 years ago
Loss evaluations
Closed 6 years ago
FileNotFoundError: [Errno 2] No such file or directory: '.../data/COCO/dets/person_detection_minival411_human553.json'
Closed 6 years ago2
how much fps?
Updated 6 years ago