paddlepaddle / padiff Goto Github PK

import paddle
import torch
from padiff import assign_weight, create_model, auto_diff
import torch
import paddle
import paddle
import signal
import os
from padiff import add_special_init

class SimpleModule(torch.nn.Module):
  def __init__(self):
      super(SimpleModule, self).__init__()
      self.linear1 = torch.nn.Linear(100, 10)
      self.attention = torch.nn.MultiheadAttention(64, 8, dropout=0.1, batch_first=True)
  def forward(self, x):
      x = self.linear1(x)
      return x

class SimpleLayer(paddle.nn.Layer):
  def __init__(self):
      super(SimpleLayer, self).__init__()
      self.linear1 = paddle.nn.Linear(100, 10)
      self.attention = paddle.nn.MultiHeadAttention(64, 8, dropout=0.1)
  def forward(self, x):
      x = self.linear1(x)
      return x
  
module = create_model(SimpleModule())
module.auto_layer_map("base")
layer = create_model(SimpleLayer())
layer.auto_layer_map("raw")

assign_weight(module, layer)

SimpleModule
========================================
    SimpleModule
     |--- Linear
     +--- MultiheadAttention    <---  *** HERE ***
           +--- NonDynamicallyQuantizableLinear  (skip)

SimpleLayer
========================================
    SimpleLayer
     |--- Linear
     +--- MultiHeadAttention  (skip)
           |--- Linear    <---  *** HERE ***
           |--- Linear
           |--- Linear
           +--- Linear

import paddle
import torch
from padiff import auto_diff
import torch
import paddle

class SimpleModule(torch.nn.Module):
  def __init__(self):
      super(SimpleModule, self).__init__()
      self.linear1 = torch.nn.Linear(100, 10)
  def forward(self, x):
      x = self.linear1(x)
      return x

class SimpleLayer(paddle.nn.Layer):
  def __init__(self):
      super(SimpleLayer, self).__init__()
      self.linear1 = paddle.nn.Linear(100, 10)
  def forward(self, x):
      x = self.linear1(x)
      return x

module = SimpleModule()
layer = SimpleLayer()

inp = paddle.rand((100, 100)).numpy().astype("float32")
inp = ({'x': torch.as_tensor(inp) },
     {'x': paddle.to_tensor(inp)})

auto_diff(module, layer, inp, atol=1e-4, auto_init=True)

Traceback (most recent call last):
  File "padiff_test.py", line 63, in <module>
    auto_diff(module, layer, inp, atol=1e-4, auto_init=True)
TypeError: auto_diff() got an unexpected keyword argument 'atol'

Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

[AutoDiff] Auto set layer_map start searching...

[AutoDiff] Auto set layer_map start searching...

[AutoDiff] Your options:
{
  auto_init: `True`
  single_step: `False`
  use_loss: `False`
  use_opt: `False`
  atol: `0`
  rtol: `1e-07`
  compare_mode: `mean`
}
[AutoDiff] Assign weight Failed !!!

RuntimeError:  Error occured when trying init weights, between:
    base_model: `Linear(in_features=1280, out_features=10, bias=True)`
                `SimpleModelRef.linear.weight`
    raw_model: `InstanceNorm2D(num_features=1280, epsilon=1e-05)`
               `SimpleModel.norm.scale`
AssertionError:  Shape of param `weight` in torch::Linear and param `scale` in paddle::InstanceNorm2D is not the same. [10, 1280] vs [1280]

Weight init log saved to 
    /home/greatx/repos/DocTrPP/padiff_log/weight_init_SimpleModelRef.log
    /home/greatx/repos/DocTrPP/padiff_log/weight_init_SimpleModel.log

Please view the reports and checkout the layer marked with `<---  *** HERE ***` !
Hint:
    1. Check the definition order of params is same in submodels.
    2. Check the corresponding submodel have the same style:
       param <=> param, buffer <=> buffer, embedding <=> embedding ...
       cases like param <=> buffer, param <=> embedding are not allowed.
    3. If can not change model codes, try to use a `LayerMap`
       which can solve most problems.
    4. (skip) means this layer is skipped because it is under black_list, or it has no param.
    0. Visit `https://github.com/PaddlePaddle/PaDiff` to find more infomation.