Yong

Setup your model and training data in code, e.g.: # Create the model with params: model name, person A name, person B name. faceit = FaceIt('fallon_to_oliver', 'fallon', 'oliver') # Add...

Train with custom dataset

9

@rocksyne Thanks for your link and materials, after using the sports1m_finetuning_ucf101.model into the folder, when l train the network, I got the error as following: InvalidArgumentError (see above for traceback):...

Tools/method getting the pre-trained tensorflow weight

1

@hx173149 would you mind sharing the TOOL and method which you got the pre-trained tensorflow's format weight from the original caffemodel? Thanks. Looking forward to any replies

varlist2 = [ weights['out'],biases['out'] ] varlist1 = list( set(weights.values() + biases.values()) - set(varlist2) ) logit = c3d_model.inference_c3d( images_placeholder[gpu_index * FLAGS.batch_size:(gpu_index + 1) * FLAGS.batch_size,:,:,:,:], 0.5, FLAGS.batch_size, weights, biases ) loss_name_scope...

Confused by the apply_fix(self) function. Would mind telling us why you set it?

1

Confused by the apply_fix(self) function. Would mind telling us why you set it? def apply_fix(self): # 1. fix bn # 2. fix conv1 conv2 for param in self.resnet.conv1.parameters(): param.requires_grad =...

how to get the pose coordination and get the AP/map and AR from the heatmap

1

@anatolix @anatolix hi, thanks for your excellent work. And I'm one newbie about the pose estimation and working for train smaller and faster model about the Realtime multi-person pose estimation...

experiments mechanism (eval_mechanism) heatmap, vecmap generated by GT -> post-processing = 60.8% add redundant connection 60.8%->67.7% sigma (7-9) 67.7%->68.8% replace all_peaks with keypoints gt 68.8->78% (influence single or multi?) would...