Gouttham

+1

Hi @AllentDan I was able to convert the mode into the .onnx file, but I faced an issue during loading this model in onnxruntime ![Screenshot 2021-10-22 at 11 21 24...

> Hi @AllentDan I was able to convert the mode into the .onnx file, but I faced an issue during loading this model in onnxruntime ![Screenshot 2021-10-22 at 11 21...

> Hi, @gouttham. Good job. The line `nodes[valid] = rnn_nodes[valid].gather(1, (all_nums[valid] - 1).unsqueeze(-1).unsqueeze(-1).expand(-1, -1, rnn_nodes.size(-1))).squeeze(1)` is too long to analyse codes. Maybe we can split it to several shot lines....

> Hi @gouttham, can you provide me with the code to convert the KIE model to onnx format? Thank you so much! Sorry for late reply tofuai. Give me few...

> Hi @skywalkerfmc , Kindly find below with the version i am using. torch==1.10.0 onnx==1.10.1 onnxruntime==1.6.0

Using the below code I was able to visualize the attention maps. **Step 1**: In transformer.py under class `MultiHeadedSelfAttention(nn.Module):` replace the forward method with the below code > def forward(self,...