-
`class TextCNN(nn.Module):
def __init__(self):
super(TextCNN, self).__init__()
self.num_filters_total = num_filters * len(filter_sizes)
self.W = nn.Parameter(torch.em…
-
x2paddle 支持textCNN、bi-lstm-crf模型tf2pd吗
-
When I did the experiment on RCV1, while textcnn reach the similar result in your paper. The performance of the BERT model got a big gap, about 10% lower, comparing with another unpublished paper's re…
-
Dear developers,
I was optimizing a TextCNN model with TVM on intel x86.
I wrote my own Conv1D NCWc schedule based on Conv2D
, (102…
-
In section 3 of readme, the table shows the reuslt of hierarchical vs flat. Here does hierarchical mean that model has hierarchical regularization or just mean the evaluation value is the value with i…
-
### 1. Network define
```
import pathlib
from concurrent.futures import ProcessPoolExecutor
import gensim
import numpy as np
import tensorflow as tf
from absl import app
from absl import fla…
-
以下模型的推理速度、内存占用等均在‘CPU’上考察
【TextCNN、pytorch_bert、tensorflow_bert、ERNIE文本分类任务性能对比】
【以下性能考察结果均经过多次测试】
推理时的数据最长文本有75万中文字符，利用100个文本进行测试。
从内存占用及推理速度指标来看，四种算法中，TextCNN均是最优的。
由于bert及ERNIE并未经过多次fine-tun…
-
Hi there, is there any way I can only extract the feature vectors for urls? Can you point to me where I should start to take a look?
thanks