xiaoxin05

Hi, I haven't made any changes to your open source (virtual-walk) (only the output folder path has been modified in "download_models.py") But, I had a problem which is shown in the...

Hi， You can see the attached file (two images) by dragging down the current page of the email. My problem is that  missing  （such as group1-shard1of23.bin） .bin file when I...

Thank you for your letter. I will put the image on Github as soon as possible. I will describe my problem as follows: Firstly, My environment is Windows and others...

> of course it doesn't . hourglass network just regress heatmap not coordinate hi, So I want to ask you a question, how do I change this loss function from...

hi, I meet the same problem, Can you share the related code of MSE loss? Thank you @dongzhuoyao @Crazod

I tried to use the sigmoid cross entropy set by this project in the open data set MPII, but I found that there were some problems: I find it incredible...

HI，I wrote a copy myself, can you check if it's correct def JointMSELoss(self,out_single,groudtruth_heatmap,target): target_mask = tf.reshape(target,[16,1,1,1,16])  #batchsize为16, 16为关键点个数 loss_mse = tf.reduce_mean(tf.square(out_single - groudtruth_heatmap) * target_mask) return loss_mse loss = 0...

hi, I have a problem ,please. the function _trainin in hourglass_tiny , I find a fault, as follows: self.resume['err'].append(np.sum(accuracy_array) / len(accuracy_array))

> I encountered an error in generating heatmaps from inference.py Later on I found out that, in the definition of predictHM(self, img) function at line 125 in inference.py, > self.predict.pred(...

> @luohuan2uestc To test on single image, you can change hpeWebcam function in predictClass.py as follow: > `rootdir = './images_lip/' > images = os.listdir(rootdir) > count = 0 > for...