Tengchao Lv
Tengchao Lv
> 按照示例中我们有的是三维的: > `[n_seqs, n_sequencd_length, lstm_num_units]` > 现在要变成二维的: > `[n_seqs * n_sequencd_length, lstm_num_units]` > 是不是应该在第0维度上进行拼接？axis=0而不是axis=1？ > > 比如我有下面的数据： > `t1 = [ [[0,1],[2,3],[3,4],[4,5]], [[5,6],[6,7],[7,8],[8,9]], [[9,10],[10,11],[11,12],[12,13]] ] t2=tf.concat(t1,axis=0) with tf.Session() as...
Hi @wlhgtc, as mentioned above, the Chinese version of layoutlmv3 uses XLMRobertaTokenizer, it is the difference between layoutlmv3-zh and layoutlmv3-en. [This code](https://github.com/microsoft/unilm/blob/44273d47ac0971cd0ebe05335eb1e0043883b898/layoutlmft/examples/run_funsd.py#L178) provides an example of how to process bbox...
same problem. they only consider the cnn/dm...
@tamirhassan hi, I still meet this error. has this problem been solved?
hi 方便具体描述一下吗？
hi @imadcat , Could you please try installing PyTorch >= 1.8.1 and the latest Transformers, and then let me know if there is any error message?
hi @SuXuping , I think it is a good idea to reproduce the score of layoutlmv3-Chinese on the SER task first to make sure you use the layoutlmv3-Chinese rightly. If...
Hi @rogerdehe, because the xfund does not have the dev set, we choose the best score from the test set. I find your log output F1=91.6 during evaluation. So maybe...
Could you run the following command instead and let me know if it was successful or failed: ~~~bash pip install pybind11 conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 -c pytorch pip install...
same question