liuxiaobei6667

InvalidArgumentError: indices[3] = [3, -1] does not index into param shape [6,175,768] [[{{node lambda_2/GatherNd}}]]我也遇到了

Plugin failed to install. Error: net::ERR_CONNECTION_REFUSED

> RuntimeError: Error(s) in loading state_dict for Model: Unexpected key(s) in state_dict: "conv_region.weight", "conv_region.bias", "conv.weight", "conv.bias". size mismatch for fc.weight: copying a param with shape torch.Size([10, 250]) from checkpoint, the...

> ```java > import torch > from importlib import import_module > > key = { > 0: 'finance', > 1: 'realty', > 2: 'stocks', > 3: 'education', > 4: 'science',...

预测结果太离谱

> py2neo v4 doesn't has 'find_one' function. In the place of find_one please change to NodeMatcher. > > For example: self.graph.find_one(label=self.invoice_name, property_key='name', property_value=df_data['name'][m]) change to: from py2neo import Graph, NodeMatcher...

> 这不是刻录了呗，是人家2080ti，用你很好的数据，或者说数据试试。 怎么解决

> 前面的显个步骤比较正常占用占用，锻炼，损失，然后会突然出现，然后会爆掉，正常报地方都显存占用 ~~ > > 文件“/home/anaconda3/envs/python2.7/lib/python2.7/site-packages/torch/nn/modules/module.py”，第 532 行，**调用** 结果 = self.forward(*input, ** kwargs） 文件“/home/embed.py”，第 84 行，向前 text_encoded_layer，_ = self.bert_model(text_var, text_segments_ids, output_all_encoded_layers=False) 文件“/home/anaconda3/envs/python2.7/lib/python2. 7/site-packages/torch/nn/modules/module.py”，第 532 行，**调用** 结果 = self.forward(*input, **kwargs) 文件“/home/anaconda3/envs/python2.7/lib/...