ソンス

Hello, How to choose the stepsize for a given iteration? The default parametrs from the author is step size=13106 for iterations=600000 Thank You

@yw155 @salvador-blanco Can you help me with finetuning the model with custom dataset. I have prepared the custom dataset and annotation file, and i can train the model freshly using...

@mks0601 thank you. Yes my dataset is small but contains many images of a person sitting. The coco model doesn’t give good detection because of lack of sitting images from...

@mks0601 can you give an example command to continue training in tensorflow. Previously I tried caffe version of openpose for training.

@tucan9389 how can we train coco model for multipserson heatmap prediction? I we train the whole image without cropping with single person label for each sample, does the model learn...

also the images and landmark folders are empty right?

@Source82 did you fix this? please help. the augment image and landmarks folder is empty. also when i use the augmented tf records, the inference is very bad, looks like...

thank you. yes i have to use pose estimation methods for detecting multi faces. I want to ask how to train images of 96x96 faces and heatmap labels on 256x256...

oh i see, so you use the face bonding box information from your dataset and crop and feed if for training? all iamges are same size after crop? and what...

you use some face detector to get the boudning box, crop and then feed to predcition network right? thats why you can use any resolution image while testing.