ϑi\|SSKrSSKrSSKJrJr SSKJr SSKJr SSK J r J r SS/r S Sjr"S S\ 5rg) N) _legacy_C_opsbase) LayerHelper) ParamAttr)Layer initializerresnet_basic_blockResNetBasicBlockc"`[RR5(a/SPUPSPUPSPUPSPUPSPUPSPUPSPUPSPUPS PUPS PUPS PUPS PUPS PUPSPUPSPUPSPU PSPU(+PSPSPSPU!P7n"[R"UUUUUUUUUU U U U U UUUUU U UU/U"Q76un#n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$n$U#$[ S<0[ 5D6n%[RRRRn&[RRRRn'U%RURSS9n#U%RURSS9n(U%RU&SS9n)U%RU&SS9n*UcU%RU&SS9OUn+UcU%RU&SS9OUn,U%RURSS9n-U%RURSS9n.U%RU&SS9n/U%RU&SS9n0U cU%RU&SS9OU n1U cU%RU&SS9OU n2U%RURSS9n3U%RU&SS9n4U%RU&SS9n5UcU%RU&SS9OUn6UcU%RU&SS9OUn7U%RU'SS9n8U%RU'SS9n9U%RU'SS9n:U%RU'SS9n;U%RU'SS9n0SU_SU_SU_SU_SU_SU_SU_SU_S U_S U_S U_S U_S U_SU_SU_SU _SU(+_SU!S(.En"0S)U#_S*U(_S+U)_S,U*_S-U+_S.U,_S/U-_S0U/_S1U0_S2U1_S3U2_S4U._S5U3_S6U4_S7U5_S8U6_S9U7_U8U9U:U;UU?U"S;9 U#$)=Nstride1stride2stride3padding1padding2padding3 dilation1 dilation2 dilation3groupmomentumepsilon data_format has_shortcutuse_global_statstrainable_statisticsis_testact_typerelufind_conv_input_maxr T)dtype stop_gradientXFilter1Scale1Bias1Mean1Var1Filter2Scale2Bias2Mean2Var2Filter3Scale3Bias3Mean3Var3)rrYConv1 SavedMean1 SavedInvstd1Mean1OutVar1OutConv2 SavedMean2 SavedInvstd2Mean2OutVar2Out Conv2InputConv3 SavedMean3 SavedInvstd3Mean3OutVar3Out) MaxInput1 MaxFilter1 MaxInput2 MaxFilter2 MaxInput3 MaxFilter3)typeinputsoutputsattrs)r )r frameworkin_dygraph_moderr rlocalscoreVarDescVarTypeFP32"create_variable_for_type_inferencer append_op)@xfilter1scale1bias1mean1var1filter2scale2bias2mean2var2filter3scale3bias3mean3var3r r rrrrrrrgroupsrepsrrrtrainingr find_conv_maxrLout_helperbn_param_dtype max_dtypeconv1 saved_mean1 saved_invstd1 running_mean1 running_var1conv2 conv2_input saved_mean2 saved_invstd2 running_mean2 running_var2conv3 saved_mean3 saved_invstd3 running_mean3 running_var3conv1_input_maxconv1_filter_maxconv2_input_maxconv2_filter_maxconv3_input_maxconv3_filter_maxrJrKs@ `/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/incubate/xpu/resnet_block.pyr r sCH ~~%%''' ' '  '   '  '  '  '  '  '  '  '  '  '  '  ' !' " #' $ %' & '' ( )' * +' , -' . /' 0 1' 2 3' 4 5' 6 7' 8 9' : ;' < =' > #?' @ !A' B C' DLE' F G' H I' J "K' L M' B  , ,                     - ./ 1  4  : :FYY&&..33N !!))..I  3 3ggT 4 C  5 5ggT 6 E;;D<K==D>M = 11  2   < 11  2    5 5ggT 6 E;;ggT<K;;D<K==D>M = 11  2   < 11  2    5 5ggT 6 E;;D<K==D>M = 11  2   < 11  2  ??t@O@@tA??t@O@@tA??t@O@@tA Q7 &       7 &    7 &   !F& 7 7  7  H   H   H   Y  Y  Y    H  3  {     ,   4! " x<# $,' E, S k   M  <   k   M < k  k   M!" <#$%&$&$&/G2  !&' Jcx^\rSrSrSrSU4SjjrSrSrU=r$)r iGa[ ResNetBasicBlock is designed for optimize the performance of the basic unit of ssd resnet block. If has_shortcut = True, it can calculate 3 Conv2D, 3 BatchNorm and 2 ReLU in one time. If has_shortcut = False, it can calculate 2 Conv2D, 2 BatchNorm and 2 ReLU in one time. In this case the shape of output is same with input. Args: num_channels (int): The number of input image channel. num_filter (int): The number of filter. It is as same as the output image channel. filter_size (int|list|tuple): The filter size. If filter_size is a tuple, it must contain two integers, (filter_size_height, filter_size_width). Otherwise, filter_size_height = filter_size_width =\ filter_size. stride (int, optional): The stride size. It means the stride in convolution. If stride is a tuple, it must contain two integers, (stride_height, stride_width). Otherwise, stride_height = stride_width = stride. Default: stride = 1. act (str, optional): Activation type, if it is set to None, activation is not appended. Default: None momentum (float, optional): The value used for the moving_mean and moving_var computation. This should be a float number or a 0-D Tensor with shape [] and data type as float32. The updated formula is: :math:`moving\_mean = moving\_mean * momentum + new\_mean * (1. - momentum)` :math:`moving\_var = moving\_var * momentum + new\_var * (1. - momentum)` Default is 0.9. eps (float, optional): A value added to the denominator for numerical stability. Default is 1e-5. data_format (str, optional): Specify the data format of the input, and the data format of the output will be consistent with that of the input. Now is only support `"NCHW"`, the data is stored in the order of: `[batch_size, input_channels, input_height, input_width]`. has_shortcut (bool, optional): Whether to calculate CONV3 and BN3. Default: False. use_global_stats (bool, optional): Whether to use global mean and variance. In inference or test mode, set use_global_stats to true or is_test to true, and the behavior is equivalent. In train mode, when setting use_global_stats True, the global mean and variance are also used during train period. Default: False. is_test (bool, optional): A flag indicating whether it is in test phrase or not. Default: False. filter_attr (ParamAttr, optional): The parameter attribute for learnable parameters/weights of conv2d. If it is set to None or one attribute of ParamAttr, conv2d will create ParamAttr as param_attr. Default: None. scale_attr (ParamAttr, optional): The parameter attribute for Parameter `scale` of batch_norm. If it is set to None or one attribute of ParamAttr, batch_norm will create ParamAttr as param_attr, the name of scale can be set in ParamAttr. If the Initializer of the param_attr is not set, the parameter is initialized with Xavier. Default: None. bias_attr (ParamAttr, optional): The parameter attribute for the bias of batch_norm. If it is set to None or one attribute of ParamAttr, batch_norm will create ParamAttr as bias_attr, the name of bias can be set in ParamAttr. If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None. moving_mean_name (str, optional): The name of moving_mean which store the global Mean. If it is set to None, batch_norm will save global mean with a random name, otherwise, batch_norm will save global mean with the string. Default: None. moving_var_name (str, optional): The name of the moving_variance which store the global Variance. If it is set to None, batch_norm will save global variance with a random name, otherwise, batch_norm will save global variance with the string. Default: None. padding (int, optional): The padding size. It is only support padding_height = padding_width = padding. Default: padding = 0. dilation (int, optional): The dilation size. It means the spacing between the kernel points. It is only support dilation_height = dilation_width = dilation. Default: dilation = 1. trainable_statistics (bool, optional): Whether to calculate mean and var in eval mode. In eval mode, when setting trainable_statistics True, mean and variance will be calculated by current batch statistics. Default: False. find_conv_max (bool, optional): Whether to calculate max value of each conv2d. Default: True. Returns: A Tensor representing the ResNetBasicBlock, whose data type is the same with input. Examples: .. code-block:: pycon >>> # doctest: +REQUIRES(env: XPU) >>> import paddle >>> from paddle.incubate.xpu.resnet_block import ResNetBasicBlock >>> ch_in = 4 >>> ch_out = 8 >>> x = paddle.uniform((2, ch_in, 16, 16), dtype='float32', min=-1., max=1.) >>> resnet_basic_block = ResNetBasicBlock(num_channels1=ch_in, ... num_filter1=ch_out, ... filter1_size=3, ... num_channels2=ch_out, ... num_filter2=ch_out, ... filter2_size=3, ... num_channels3=ch_in, ... num_filter3=ch_out, ... filter3_size=1, ... stride1=1, ... stride2=1, ... stride3=1, ... act='relu', ... padding1=1, ... padding2=1, ... padding3=0, ... has_shortcut=True) >>> out = resnet_basic_block.forward(x) >>> print(out.shape) paddle.Size([2, 8, 16, 16]) c+ >[T4U]5 XlXl[R R USS5Ul[R R USS5UlU&Ul U'Ul U#Ul U$Ul SUl XlXlUUlXlUUlUUlUUlU)UlU*UlU(a;[R R U SS5UlU%UlXlU(UlOSUlSUlSUlSUlS1n+UU+;a[7SU+SU35eS n,[8R:R<R>R@n-SSU/n.SSU/n/X!X3/n0XTXf/n1URCU0UU,"XR5S 9Ul"URCU.UU-[FRH"S 5S 9Ul%URCU.UU-S S9Ul&URC[OU[FRH"S5SS9U.U-S9Ul(S URPl)URC[OU[FRH"S 5SS9U.U-S9Ul*S URTl)URCU1UU,"X@R5S 9Ul+URCU/UU-[FRH"S 5S 9Ul,URCU/UU-S S9Ul-URC[OU[FRH"S5SS9U/U-S9Ul.S UR\l)URC[OU[FRH"S 5SS9U/U-S9Ul/S UR^l)U(aSSU/n2UUU U /n3URCU3UU,"XpR.5S 9Ul0URCU2UU-[FRH"S 5S 9Ul1URCU2U U-S S9Ul2URC[OU![FRH"S5SS9U2U-S9Ul3S URfl)URC[OU"[FRH"S 5SS9U2U-S9Ul4S URhl)gSUl0SUl1SUl2SUl3SUl4g)N filter1_size filter2_size filter3_sizeNCHWzconv_format must be one of z, but got conv_format=cr[R"U5U-nSU- S-n[R"SU5$)Ng@g?)npprodINormal)channels kernel_sizefilter_elem_numstds r_get_default_param_initializerAResNetBasicBlock.__init__.._get_default_param_initializer s5 ggk2X=O(S0C88C% %r)shapeattrdefault_initializerg?)rrr rT)rrr is_biasrF)namer trainable)rrr )5super__init___stride1_stride2paddleutilsconvert_to_list _kernel1_size _kernel2_size _dilation1 _dilation2 _padding1 _padding2_groups _momentum_eps _data_format_act _has_shortcut_use_global_stats_is_test_trainable_statistics_find_conv_max _kernel3_size _padding3_stride3 _dilation3 ValueErrorrrPrQrRrScreate_parameterfilter_1rConstantscale_1bias_1rmean_1r!var_1filter_2scale_2bias_2mean_2var_2filter_3scale_3bias_3mean_3var_3)5self num_channels1 num_filter1r num_channels2 num_filter2r num_channels3 num_filter3rr r ractrrgrrrr filter1_attr scale1_attr bias1_attrmoving_mean1_namemoving_var1_name filter2_attr scale2_attr bias2_attrmoving_mean2_namemoving_var2_name filter3_attr scale3_attr bias3_attrmoving_mean3_namemoving_var3_namerrrrrrrri valid_formatrrmbn1_param_shapebn2_param_shape filter1_shape filter2_shapebn3_param_shape filter3_shape __class__s5 rrResNetBasicBlock.__init__sZ   #\\99 !^ $\\99 !^ $#!! ! ' )!1 %9"+ !'!=!=a"D &DN#M'DO!%D DNDMDOx l *-l^;QR]Q^_  & **2277a-a-$\P $\P -- >11!.  ,,! ! 3 -  ++!  ,  ++&JJsO " ,  %) !**%JJsO " +  $(  -- >11!.  ,,! ! 3 -  ++!  ,  ++&JJsO " ,  %) !**%JJsO " +  $(   ![1O M !11#!$B!#5#5%2DM 00% $$%JJsO 1DL //%$ 0DK //* ! 3# &$0DK)-DKK %..) ! 3# &$/DJ(,DJJ $ DMDLDKDKDJrc [UURURURURUR UR URURURURURURURURURUR UR"UR$UR&UR(UR*UR,UR.UR0UR2UR4UR6UR8UR:4UR<UR>UR@URBS.6nU$)N)rrhrri)"r rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrhrr)rrVrjs rforwardResNetBasicBlock.forwards MM LL KK KK JJ MM LL KK KK JJ MM LL KK KK JJ MM MM MM NN NN NN OO OO OO LL NN II      =# >"33]]!%!;!;--E# H r)%rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr)!rrrrg?gh㈵>rFFFNNNNNNNNNNNNNNNrrrrrrFT) __name__ __module__ __qualname____firstlineno____doc__rr__static_attributes__ __classcell__)rs@rr r Gshj  "WiV%%r)NFFT)numpyrrrrpaddle.base.layer_helperrpaddle.base.param_attrr paddle.nnrrr__all__r r rrrsM &0, !3 4D EgT {u{r