0_0_0_0__11000
0_0_0_0__11000
https://github.com/NLPScott/bert-Chinese-classification-task/issues/25?_pjax=%23js-repo-pjax-container#issuecomment-502511445 感谢大佬，正解，解决了
> Missing key(s) in state_dict: > "embeddings.word_embeddings.weight", > "embeddings.position_embeddings.weight", > "embeddings.token_type_embeddings.weight", > "embeddings.LayerNorm.gamma", > "embeddings.LayerNorm.beta",...... > > Unexpected key(s) in state_dict: > "bert.embeddings.word_embeddings.weight", > "bert.embeddings.position_embeddings.weight", > "bert.embeddings.token_type_embeddings.weight", > "bert.embeddings.LayerNorm.weight", >...
我是这样处理的： state_dict = torch.load(args.init_checkpoint, map_location='cpu') new_keys = ["embeddings.word_embeddings.weight", "embeddings.position_embeddings.weight", "embeddings.token_type_embeddings.weight", "embeddings.LayerNorm.gamma", "embeddings.LayerNorm.beta", "encoder.layer.0.attention.self.query.weight", "encoder.layer.0.attention.self.query.bias", "encoder.layer.0.attention.self.key.weight", "encoder.layer.0.attention.self.key.bias", "encoder.layer.0.attention.self.value.weight", "encoder.layer.0.attention.self.value.bias", "encoder.layer.0.attention.output.dense.weight", "encoder.layer.0.attention.output.dense.bias", "encoder.layer.0.attention.output.LayerNorm.gamma", "encoder.layer.0.attention.output.LayerNorm.beta", "encoder.layer.0.intermediate.dense.weight", "encoder.layer.0.intermediate.dense.bias", "encoder.layer.0.output.dense.weight", "encoder.layer.0.output.dense.bias", "encoder.layer.0.output.LayerNorm.gamma", "encoder.layer.0.output.LayerNorm.beta", "encoder.layer.1.attention.self.query.weight", "encoder.layer.1.attention.self.query.bias",...
Have you figured something out on this issue?
> Try following the steps in this comment: [#99 (comment)](https://github.com/facebookresearch/AnimatedDrawings/issues/99#issue-1669192538) Run the following commands: sudo apt-get install libosmesa6-dev freeglut3-dev sudo apt-get install libglfw3-dev libgles2-mesa-dev sudo apt-get install libosmesa6 export PYOPENGL_PLATFORM=osmesa...
> I tried, but even with manual retargeting, the animate is still out of control. Can you tell me how you generate the bvh file
Is this resolved? I met the same issue, ZeroDivisionError: float division by zero
- warming > python3 train.py --model_type=bert-base-chinese --truncation=True  > How to modify