search

mks0601 / TF-SimpleHumanPose

TensorFlow implementation of "Simple Baselines for Human Pose Estimation and Tracking", ECCV 2018
336 stars 90 forks source link

FileNotFoundError: [Errno 2] No such file or directory: 'tmp_result_0.pkl' and IndexError: list index out of range #36

Closed anhminh3105 closed 5 years ago

anhminh3105 commented 5 years ago

Hello,

I am trying to run the test.py on the provided pre-trained model 256x192_resnet50_coco but I am getting the following errors: Screenshot from 2019-07-22 17-02-53 though I don't really understand what it does yet, I skimmed over the code and you seemed to try to delete it. So as I don't have that pickle file, I tried to bypass those blocks of code by setting argument dump_method=2 in test.py like so MultiGPUFunc = MultiProc(len(args.gpu_ids.split(',')), func, dump_method=2) but then I encountered another error as following: Screenshot from 2019-07-22 17-11-45 the command I used to run the programme is : python test.py --gpu 0 --test_epoch 140 as I have only 1 gpu card. Also I tried to changed argument gpu to 1, 0-1 but the error is still the same.

As an aside, I am not sure which file is right for the dets/human_detection.json and so I used the human_detection_test-dev2017.json of Human detection result on test-dev2017 (57.2 AP on human class) and renamed it to human_detection.json. I wonder if it is the cause to the error?

I need your help.

thanks in advance.

mks0601 commented 5 years ago

The pickle file is a temporal file which is generated and deleted in testing stage. You don't have to prepare pickle files. Can you tell me which dataset are you using? The human detection result should be the one of dataset you want to use.

mks0601 commented 5 years ago

I tested my code and it works in single GPU environment. I think your human detection file is not the same with your dataset.

anhminh3105 commented 5 years ago

I am using the COCO dataset test2017, with annotations from image_info_test2017.zip.

Indeed I don't know where to download the human_detection.json file. Instead, I found the human_detection_test-dev2017.json file and I thought it might be it so I renamed it to human_detection.json and placed it under data/COCO/dets/.The link to that file is this one

Annotation 2019-07-22 204147

mks0601 commented 5 years ago

Did you change testset = 'val' in config.py to testset = 'test'?

anhminh3105 commented 5 years ago

Ah yeah, no I didn't. I will try that as soon as I wake up tomorrow and let you know right then

mks0601 commented 5 years ago

Yes. I'm sure that is the reason. Good night!

anhminh3105 commented 5 years ago

I changed that and it works, it is indeed the reason.

However, the APs and ARs outputs are all -1, maybe something is not right so I will try to create another issue.

Many thanks to you and your great supports, I'm very appreciated ^.^