bugczw
bugczw
As I have say in #12 , when I re-extract the features to train the network, the f1 score of the model is only about 0.3. Is this normal? Has...
In the loss function 'neuralNDCG', the input 'y_pred' is the prediction from the model, and it's shape is '[batch_size, slate_length]'. What does the 'slate_length' mean? Is each element in 'y_pred'...
Generally speaking, the shape of audio input data is always [batch_size, time_stamps, mel_bins]. But this model parameter, like input_axis, is different in audio. When using for training audio, how do...
Hello，most of the data sets mentioned in the papers can no longer find the download link. How can I get these data sets, such as MSVD data sets?
The BertCapModel uses two BertModel as encoder and decoder. However, in the config about BertModel, it sets max_position_embeddings = 17 in decoder, which leads to tensor size not matching, like...
你好，我是中科院计算所的一名研究生，最近在研究因果事件抽取的方面的工作，看到你参加了这个类似的比赛，想问一下，可以加个好友详细聊一下细节吗？qq：1024302486
In the file 'torch_audioset/data/torch_input_processing.py', I only find function called 'VGGishLogMelSpectrogram'. But I can't find the way to process audio feature for yamnet. Can you can give me an example to...
The data you used in the experiment is stored in the h5py file instead of the original video data. Is there any documentation or code for the generation of h5py...