key_lw

G loss increase during trainning

2

[Epoch 19/100] [Batch 1000/1215] [D loss: 0.293148, acc: 50%] [G loss: 9.813908, adv: 0.785160, recon: 0.088106, id: 0.103994] time: 2:27:21.693716 [Epoch 20/100] [Batch 500/1215] [D loss: 0.236037, acc: 63%] [G...

分词后返回byte字符

3

Python 2.7.13 (default, Dec 18 2016, 07:03:39) [GCC 4.2.1 Compatible Apple LLVM 8.0.0 (clang-800.0.42.1)] on darwin Type "help", "copyright", "credits" or "license" for more information. >>> import thulac >>> thu...

training loss does not go down

1

I trained a model for 20 hours, but the loss did't decrease, anyone could help?

Hi, comparing with the original implementation, what is the corresponding parametes with n_feats, block_feats and patch_size?

tf_pose

1

from tf_pose.estimator import TfPoseEstimator ModuleNotFoundError: No module named 'tf_pose'

validate问题

7

你好，我在训练完一个epoch后进行validata后出错，经查是在 _,predicted = torch.max(soft_output.data, 1) predicted = predicted.to('cpu').detach().numpy() 这里的predicted不是包含0,1的tensor，是一个这样的tensor Tensor: tensor([920, 744, 920, 818, 416, 920, 818, 920, 919, 920, 818, 818, 920, 974, 920, 855, 919, 744, 503, 818,...

Hi, where can I get the graph file? thanks

how to predict a new audio?

1

I finished training and produced a state file. At this point how to predict a new audio file? I tried --mode test, however it request the audio file had been...

what does the training data look like?

1

Hi, the link to the training data repo is dead, could you fix that? I cant run the train.py while I dont know what is in the trainingData.csv

我是在ubuntu下运行insightface的人脸识别，对c++不熟悉，想请问下要怎么运行获取最后的512维向量呢