Joll123
Joll123
Hello. Thanks for your works. I used your project in my own environment and found that the intrinsic reward is very close to 0.001, and the external reward is 0....
when I running the prepro.py, it is terminating at spm.SentencePieceTrainer.Train(train).And I get no any information. Has anyone encountered this problem? how to deal with it? INFO:root:# Train a joint BPE...
Could the algorithm be used on DDPG? And in case action is continuious, how to calculate the loss function of the forward model? Thanks.
I trained the inception_resnet_v1 + cbam model for face recogniton and the accuracy was low.Why?
terminate called after throwing an instance of 'cv::Exception' what(): OpenCV(4.1.1-pre) /home/jhl/opencv/modules/dnn/src/caffe/caffe_io.cpp:1121: error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "./reg.prototxt" in function 'ReadProtoFromTextFile'
Could the algorithm be used on reinforced learning algorithms with experience reply?
你好， actor_network输出线速度[0,1]角速度时[-1,1],但是在agent_stage_1.py中用 a[0] = np.clip(np.random.normal(a[0], var), 0., 1.) a[1] = np.clip(np.random.normal(a[1], var), -0.5, 0.5)，角速度这样处理时为什么。 最后一层是否用batch_norm有影响吗？
when I used librosa to load audio file of VCTK_Corpus, the following errors occurs. Has anyone encountered the same situation? File "/anaconda3/envs/tf/lib/python3.6/site-packages/librosa/core/audio.py", line 112, in load with audioread.audio_open(os.path.realpath(path)) as input_file:...
When action dimension = 2 action will be saturate(can't navigation) I also meet this problem。
I have some question about network structure after studying your paper. (1) In paper, the attention network is used at the localization subnet, however, it is used at the backbone...