Support T5 Model #794
Merged
Support T5 Model #794
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jiangjiajun
requested changes
May 12, 2022
| @@ -741,6 +742,7 @@ def Unsqueeze(self, node): | |||
| axes = node.get_attr('axes') | |||
| if axes is None: | |||
| axes = self.graph.get_input_node(node, idx=1, copy=True) | |||
| axes = _const_weight_or_none(axes) | |||
There was a problem hiding this comment.
上面判断了是否axes为None, 下面又调用了一个可能返回为None的函数，这个需要给一个方案来解决，要么这个函数是否不能返回为None
There was a problem hiding this comment.
Done.
之前实现是因为ONNX版本不同判断axes是Node的一个属性还是输入，若是输入再用_const_weight_or_none获取value
目前修改逻辑，因为paddle.unsqueeze支持axes为一个Tensor，所以按如下逻辑判断：
- 若
axes为一个属性，直接获取属性值 - 若
axes为一个输入节点，输入该节点的name
从而去掉_const_weight_or_none 函数
There was a problem hiding this comment.
目前发现一个问题，unsqueeze输入可能有scalar tensor（ONNX支持但Paddle不支持），为解决此问题，还是需要使用_const_weight_or_none 去判断，加入necessary=True条件
- 若输入shape为空，且
axes值为0，使用paddle.reshape替代 - 否则，使用
paddle.unsqueeze
| @@ -749,7 +751,8 @@ def Unsqueeze(self, node): | |||
| outputs=[node.name], | |||
| shape=[1]) | |||
| else: | |||
| if isinstance(axes, list) or isinstance(axes, tuple): | |||
| if isinstance(axes, list) or isinstance(axes, tuple) or isinstance( | |||
There was a problem hiding this comment.
改成isinstance(axes, (list, tuple, np.ndarray))这样会更简洁点
There was a problem hiding this comment.
Done.重新实现逻辑无此判断条件
| @@ -893,72 +896,24 @@ def GatherND(self, node): | |||
| def Gather(self, node): | |||
| val_x = self.graph.get_input_node(node, idx=0, copy=True) | |||
| indices = self.graph.get_input_node(node, idx=1, copy=True) | |||
| indices_values = _const_weight_or_none(indices) | |||
There was a problem hiding this comment.
Done.加入necessary=True条件
jiangjiajun
approved these changes
May 20, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Create A Good Pull Request
Please check the follow step before merging this pull request
If this PR add new model support, please update
model_zoo.mdand add model to out test model zoos(@wjj19950828)Do follow contributes
1、新增op：LessOrEqual
2、修复Unsqueeze、MatMul op：
x_shape或者y_shape可能为空导致x_shape[0]报错，增加不为空条件3、重写Gather逻辑，具体如下：
a、首先判断
indices的shape是否为1D，若为1D，则直接调用paddle.gatherb、若
indices的shape不为1D：paddle.nn.Embedding替代gather之前实现gather，当axis>0时会多两个transpose，现在版本则无，如下图：
4、去掉重复
GatherND代码5、支持HF T5模型