[BUG]the nums of out channel is not equal to the declaration of the class in the darknet module

the nums of out channel is not equal to the declaration of the class in the darknet module

LOCATION:

PaddleDetection/ppdet/modeling/backbones/darknet.py >>> class BasicBlock(nn.Layer)

VERSION

release 2.3

描述问题/Describe the bug

below is the definition codes about the BasicBlock

class BasicBlock(nn.Layer):
    def __init__(self,
                 ch_in,
                 ch_out,
                 norm_type='bn',
                 norm_decay=0.,
                 freeze_norm=False,
                 data_format='NCHW'):
        super(BasicBlock, self).__init__()

        self.conv1 = ConvBNLayer(
            ch_in=ch_in,
            ch_out=ch_out,
            filter_size=1,
            stride=1,
            padding=0,
            norm_type=norm_type,
            norm_decay=norm_decay,
            freeze_norm=freeze_norm,
            data_format=data_format)
        self.conv2 = ConvBNLayer(
            ch_in=ch_out,
            ch_out=ch_out * 2,
            filter_size=3,
            stride=1,
            padding=1,
            norm_type=norm_type,
            norm_decay=norm_decay,
            freeze_norm=freeze_norm,
            data_format=data_format)

    def forward(self, inputs):
        conv1 = self.conv1(inputs)
        conv2 = self.conv2(conv1)
        out = paddle.add(x=inputs, y=conv2)
        return out

Suppose that i have a input variable with shape [5,10,9,9] and a BasicBlock instance named block with the ch_in=10, ch_out=5, that mean i want have a output with shape [5,5,9,9], but the actually the output is a tensor with shape [5,10,9,9] Below is the codes that i have test in jupyternotebook

import os
import paddle
os.chdir("/home/PaddleDetection")
from ppdet.modeling.backbones.darknet import BasicBlock

input = paddle.rand([5,10,9,9])
block = BasicBlock(10,5)
output = block(input)
print(f"input shape : {input.shape}\n")
print(f"layer: \n{block}\n")
print(f"output shape : {output.shape}")

and the print result is:

input shape : [5, 10, 9, 9]

layer: 
BasicBlock(
  (conv1): ConvBNLayer(
    (conv): Conv2D(10, 5, kernel_size=[1, 1], data_format=NCHW)
    (batch_norm): BatchNorm2D(num_features=5, momentum=0.9, epsilon=1e-05)
  )
  (conv2): ConvBNLayer(
    (conv): Conv2D(5, 10, kernel_size=[3, 3], padding=1, data_format=NCHW)
    (batch_norm): BatchNorm2D(num_features=10, momentum=0.9, epsilon=1e-05)
  )
)

output shape : [5, 10, 9, 9]

and if I input variable with shape [5,10,9,9] to the block with the ch_in=10, ch_out=20 or the block with the ch_in=10, ch_out=20, there will encounter a ValuError:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_17986/1117496369.py in <module>
      6 input = paddle.rand([5,10,9,9])
      7 block = BasicBlock(10,10)
----> 8 output = block(input)
      9 output.shape
     10 print(f"input shape : {input.shape}\n")

/usr/local/lib/python3.7/dist-packages/paddle/fluid/dygraph/layers.py in __call__(self, *inputs, **kwargs)
    912                 self._built = True
    913 
--> 914             outputs = self.forward(*inputs, **kwargs)
    915 
    916             for forward_post_hook in self._forward_post_hooks.values():

/home/PaddleDetection/ppdet/modeling/backbones/darknet.py in forward(self, inputs)
    174         conv1 = self.conv1(inputs)
    175         conv2 = self.conv2(conv1)
--> 176         out = paddle.add(x=inputs, y=conv2)
    177         return out
    178 

/usr/local/lib/python3.7/dist-packages/paddle/tensor/math.py in add(x, y, name)
    238 
    239     if in_dygraph_mode():
--> 240         return _C_ops.elementwise_add(x, y)
    241 
    242     return _elementwise_op(LayerHelper('elementwise_add', **locals()))

ValueError: (InvalidArgument) Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [5, 10, 9, 9] and the shape of Y = [5, 20, 9, 9]. Received [10] in X is not equal to [20] in Y at i:1.
  [Hint: Expected x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1 == true, but received x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1:0 != true:1.] (at /paddle/paddle/fluid/operators/elementwise/elementwise_op_function.h:240)
  [operator < elementwise_add > error]

and

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_17986/3869671924.py in <module>
      6 input = paddle.rand([5,10,9,9])
      7 block = BasicBlock(10,20)
----> 8 output = block(input)
      9 print(f"input shape : {input.shape}\n")
     10 print(f"layer: \n{block}\n")

/usr/local/lib/python3.7/dist-packages/paddle/fluid/dygraph/layers.py in __call__(self, *inputs, **kwargs)
    912                 self._built = True
    913 
--> 914             outputs = self.forward(*inputs, **kwargs)
    915 
    916             for forward_post_hook in self._forward_post_hooks.values():

/home/PaddleDetection/ppdet/modeling/backbones/darknet.py in forward(self, inputs)
    174         conv1 = self.conv1(inputs)
    175         conv2 = self.conv2(conv1)
--> 176         out = paddle.add(x=inputs, y=conv2)
    177         return out
    178 

/usr/local/lib/python3.7/dist-packages/paddle/tensor/math.py in add(x, y, name)
    238 
    239     if in_dygraph_mode():
--> 240         return _C_ops.elementwise_add(x, y)
    241 
    242     return _elementwise_op(LayerHelper('elementwise_add', **locals()))

ValueError: (InvalidArgument) Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [5, 10, 9, 9] and the shape of Y = [5, 40, 9, 9]. Received [10] in X is not equal to [40] in Y at i:1.
  [Hint: Expected x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1 == true, but received x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1:0 != true:1.] (at /paddle/paddle/fluid/operators/elementwise/elementwise_op_function.h:240)
  [operator < elementwise_add > error]

I know that is a tiny issue, so would you please fix that in the feature, pleaseure

@heavengate, thanks your explanations about the design of the block from the user view, but actually these is still a implicit restriction that user just allowed to init a block with ch_out is equal to the half of ch_in, which is result from the implementations of conv2 and forward function: You can see that conv2 implement a process that double the channels,

        self.conv2 = ConvBNLayer(
            ch_in=ch_out,
            ch_out=ch_out * 2,
            filter_size=3,
            stride=1,
            padding=1,
            norm_type=norm_type,
            norm_decay=norm_decay,
            freeze_norm=freeze_norm,
            data_format=data_format)

and the output of conv2 need have same shape with the input of the conv1 due to the use of the paddle.add operator not the paddle.concat operator.

    def forward(self, inputs):
        conv1 = self.conv1(inputs)
        conv2 = self.conv2(conv1)
        out = paddle.add(x=inputs, y=conv2) # inpus and conv2 should be the same shape
        return out

so if i give the ch_in = 10, ch_out = 6 , there will be a ValueError from the add operator

import os
import paddle
os.chdir("/home/PaddleDetection")
from ppdet.modeling.backbones.darknet import BasicBlock

input = paddle.rand([5,10,9,9])
block = BasicBlock(10,6)
output = block(input)
print(f"input shape : {input.shape}\n")
print(f"layer: \n{block}\n")
print(f"output shape : {output.shape}")
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_17986/3074278531.py in <module>
      6 input = paddle.rand([5,10,9,9])
      7 block = BasicBlock(10,6)
----> 8 output = block(input)
      9 print(f"input shape : {input.shape}\n")
     10 print(f"layer: \n{block}\n")

/usr/local/lib/python3.7/dist-packages/paddle/fluid/dygraph/layers.py in __call__(self, *inputs, **kwargs)
    912                 self._built = True
    913 
--> 914             outputs = self.forward(*inputs, **kwargs)
    915 
    916             for forward_post_hook in self._forward_post_hooks.values():

/home/PaddleDetection/ppdet/modeling/backbones/darknet.py in forward(self, inputs)
    174         conv1 = self.conv1(inputs)
    175         conv2 = self.conv2(conv1)
--> 176         out = paddle.add(x=inputs, y=conv2)
    177         return out
    178 

/usr/local/lib/python3.7/dist-packages/paddle/tensor/math.py in add(x, y, name)
    238 
    239     if in_dygraph_mode():
--> 240         return _C_ops.elementwise_add(x, y)
    241 
    242     return _elementwise_op(LayerHelper('elementwise_add', **locals()))

ValueError: (InvalidArgument) Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [5, 10, 9, 9] and the shape of Y = [5, 12, 9, 9]. Received [10] in X is not equal to [12] in Y at i:1.
  [Hint: Expected x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1 == true, but received x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1:0 != true:1.] (at /paddle/paddle/fluid/operators/elementwise/elementwise_op_function.h:240)
  [operator < elementwise_add > error]

Even thought the design concept of the ResNet block have demand the same shape of x and f(f(x)) from the y = x+f(f(x)), i think is better to set the ch_in and ch_out to the same even value, and modify the channel variables of the conv1 and conv2 , which may be more friendly to user.*_^

PaddlePaddle / PaddleDetection