def jojo_0(self, input_vars_12, var_220, input_vars_14, input_vars_11,
input_vars_13):
var_221 = torch.relu_(var_220)
var_239 = torch._convolution(var_221, input_vars_11, input_vars_12, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_240 = torch.relu_(var_239)
var_258 = torch._convolution(var_240, input_vars_13, input_vars_14, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_258
def jojo_20(self, input_vars_45, input_vars_44, var_848, var_799, input_vars_47, input_vars_46, input_vars_49, input_vars_43):
var_850 = torch.add(var_848, var_799, alpha=1)
var_851 = torch.relu_(var_850)
var_870 = torch._convolution(var_851, input_vars_43, None, [2, 2, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_875 = torch.batch_norm(var_870, input_vars_44, input_vars_45, input_vars_46, input_vars_47, False, 0.1, 1e-05, True)
var_876 = torch.relu_(var_875)
var_895 = torch._convolution(var_876, input_vars_49, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_851, var_895
def jojo_5(self, input_vars_50, var_586, input_vars_51, input_vars_49,
input_vars_57, input_vars_64, input_vars_52, input_vars_55,
input_vars_61, input_vars_63, input_vars_58, input_vars_56,
input_vars_53, input_vars_65, input_vars_62, input_vars_59):
var_587 = torch.relu_(var_586)
var_606 = torch._convolution(var_587, input_vars_49, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_611 = torch.batch_norm(var_606, input_vars_50, input_vars_51,
input_vars_52, input_vars_53, False, 0.1,
1e-05, True)
var_612 = torch.relu_(var_611)
var_631 = torch._convolution(var_612, input_vars_55, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_636 = torch.batch_norm(var_631, input_vars_56, input_vars_57,
input_vars_58, input_vars_59, False, 0.1,
1e-05, True)
var_638 = torch.add(var_636, var_587, alpha=1)
var_639 = torch.relu_(var_638)
var_658 = torch._convolution(var_639, input_vars_61, None, [
2,
2,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_663 = torch.batch_norm(var_658, input_vars_62, input_vars_63,
input_vars_64, input_vars_65, False, 0.1,
1e-05, True)
return var_663, var_639
def jojo_6(self, input_vars_44, input_vars_34, input_vars_37, var_459,
input_vars_45, var_508, input_vars_31, input_vars_38,
input_vars_41, input_vars_47, input_vars_40, input_vars_43,
input_vars_33, input_vars_35, input_vars_46, input_vars_32,
input_vars_39):
var_510 = torch.add(var_508, var_459, alpha=1)
var_511 = torch.relu_(var_510)
var_530 = torch._convolution(var_511, input_vars_31, None, [
2,
2,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_535 = torch.batch_norm(var_530, input_vars_32, input_vars_33,
input_vars_34, input_vars_35, False, 0.1,
1e-05, True)
var_536 = torch.relu_(var_535)
var_555 = torch._convolution(var_536, input_vars_37, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_560 = torch.batch_norm(var_555, input_vars_38, input_vars_39,
input_vars_40, input_vars_41, False, 0.1,
1e-05, True)
var_579 = torch._convolution(var_511, input_vars_43, None, [
2,
2,
], [
0,
0,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_584 = torch.batch_norm(var_579, input_vars_44, input_vars_45,
input_vars_46, input_vars_47, False, 0.1,
1e-05, True)
return var_560, var_584
def jojo_25(self, input_vars_15, input_vars_14, input_vars_8, input_vars_11, input_vars_10, input_vars_17, input_vars_9, var_681, input_vars_16, input_vars_7, input_vars_13):
var_695 = torch.max_pool2d(var_681, [3, 3, ], [2, 2, ], [1, 1, ], [1, 1, ], False)
var_714 = torch._convolution(var_695, input_vars_7, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_719 = torch.batch_norm(var_714, input_vars_8, input_vars_9, input_vars_10, input_vars_11, False, 0.1, 1e-05, True)
var_720 = torch.relu_(var_719)
var_739 = torch._convolution(var_720, input_vars_13, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_744 = torch.batch_norm(var_739, input_vars_14, input_vars_15, input_vars_16, input_vars_17, False, 0.1, 1e-05, True)
var_746 = torch.add(var_744, var_695, alpha=1)
return var_746
def jojo_7(self, input_vars_25, var_431, input_vars_16, input_vars_13,
input_vars_15, input_vars_23, input_vars_19, input_vars_21,
input_vars_22, var_407, input_vars_17, input_vars_14,
input_vars_20):
var_432 = torch.relu_(var_431)
var_451 = torch._convolution(var_432, input_vars_13, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_456 = torch.batch_norm(var_451, input_vars_14, input_vars_15,
input_vars_16, input_vars_17, False, 0.1,
1e-05, True)
var_458 = torch.add(var_456, var_407, alpha=1)
var_459 = torch.relu_(var_458)
var_478 = torch._convolution(var_459, input_vars_19, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_483 = torch.batch_norm(var_478, input_vars_20, input_vars_21,
input_vars_22, input_vars_23, False, 0.1,
1e-05, True)
var_484 = torch.relu_(var_483)
var_503 = torch._convolution(var_484, input_vars_25, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_459, var_503
def jojo_19(self, var_851, input_vars_71, input_vars_70, input_vars_67, input_vars_55, input_vars_57, input_vars_56, var_900, input_vars_62, input_vars_65, input_vars_73, input_vars_61, input_vars_68, input_vars_63, input_vars_69, input_vars_59, input_vars_64, input_vars_58):
var_919 = torch._convolution(var_851, input_vars_55, None, [2, 2, ], [0, 0, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_924 = torch.batch_norm(var_919, input_vars_56, input_vars_57, input_vars_58, input_vars_59, False, 0.1, 1e-05, True)
var_926 = torch.add(var_900, var_924, alpha=1)
var_927 = torch.relu_(var_926)
var_946 = torch._convolution(var_927, input_vars_61, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_951 = torch.batch_norm(var_946, input_vars_62, input_vars_63, input_vars_64, input_vars_65, False, 0.1, 1e-05, True)
var_952 = torch.relu_(var_951)
var_971 = torch._convolution(var_952, input_vars_67, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_976 = torch.batch_norm(var_971, input_vars_68, input_vars_69, input_vars_70, input_vars_71, False, 0.1, 1e-05, True)
var_978 = torch.add(var_976, var_927, alpha=1)
var_979 = torch.relu_(var_978)
var_998 = torch._convolution(var_979, input_vars_73, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_979, var_998
def jojo_14(self, var_1127, input_vars_104, input_vars_111, input_vars_110, input_vars_112, input_vars_106, input_vars_109, input_vars_113, var_1083, input_vars_105, input_vars_107):
var_1132 = torch.batch_norm(var_1127, input_vars_104, input_vars_105, input_vars_106, input_vars_107, False, 0.1, 1e-05, True)
var_1151 = torch._convolution(var_1083, input_vars_109, None, [2, 2, ], [0, 0, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1156 = torch.batch_norm(var_1151, input_vars_110, input_vars_111, input_vars_112, input_vars_113, False, 0.1, 1e-05, True)
var_1158 = torch.add(var_1132, var_1156, alpha=1)
var_1159 = torch.relu_(var_1158)
return var_1159
def jojo_12(self, input_vars_125, var_1203, var_1159, input_vars_128, input_vars_123, input_vars_124, input_vars_122, input_vars_127, input_vars_130, input_vars_131, input_vars_129):
var_1208 = torch.batch_norm(var_1203, input_vars_122, input_vars_123, input_vars_124, input_vars_125, False, 0.1, 1e-05, True)
var_1210 = torch.add(var_1208, var_1159, alpha=1)
var_1211 = torch.relu_(var_1210)
var_1230 = torch._convolution(var_1211, input_vars_127, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1235 = torch.batch_norm(var_1230, input_vars_128, input_vars_129, input_vars_130, input_vars_131, False, 0.1, 1e-05, True)
return var_1211, var_1235
def jojo_2(self, input_vars_6, input_vars_5, var_136):
var_150 = torch.max_pool2d(var_136, [
2,
2,
], [
2,
2,
], [
0,
0,
], [
1,
1,
], False)
var_168 = torch._convolution(var_150, input_vars_5, input_vars_6, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_168
def jojo_1(self, var_169, input_vars_8, input_vars_7):
var_187 = torch._convolution(var_169, input_vars_7, input_vars_8, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_188 = torch.relu_(var_187)
var_202 = torch.max_pool2d(var_188, [
2,
2,
], [
2,
2,
], [
0,
0,
], [
1,
1,
], False)
return var_202
def jojo_8(self, input_vars_7, input_vars_5, input_vars_4, input_vars_1,
input_vars_2, input_vars_3, input_vars_0):
var_387 = torch._convolution(input_vars_0, input_vars_1, None, [
2,
2,
], [
3,
3,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_392 = torch.batch_norm(var_387, input_vars_2, input_vars_3,
input_vars_4, input_vars_5, False, 0.1,
1e-05, True)
var_393 = torch.relu_(var_392)
var_407 = torch.max_pool2d(var_393, [
3,
3,
], [
2,
2,
], [
1,
1,
], [
1,
1,
], False)
var_426 = torch._convolution(var_407, input_vars_7, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_407, var_426
def _convolution_wrap(
tensor, weight, bias,
stride, padding, dialation,
transposed, output_pad, groups,
benchmark, deterministic, cudnn_en
):
return torch._convolution(
tensor, weight, bias,
stride, padding, dialation,
transposed, output_pad, groups,
benchmark, deterministic, cudnn_en
)
def jojo_3(self, input_vars_3, var_117, input_vars_4):
var_135 = torch._convolution(var_117, input_vars_3, input_vars_4, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_135
def jojo_4(self, input_vars_1, input_vars_0, input_vars_2):
var_116 = torch._convolution(input_vars_0, input_vars_1, input_vars_2,
[
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
return var_116
def forward(self, input):
x1 = torch.zeros(2, 2)
x2 = torch.empty_like(torch.empty(2, 2))
x3 = torch._convolution(
input,
self.weight,
self.bias,
[1, 1],
[0, 0],
[1, 1],
False,
[0, 0],
1,
False,
False,
True,
True,
)
return (x1, x2, x3)
def jojo_2(self, input_vars_89, input_vars_85, input_vars_87, var_740,
input_vars_86, var_715, input_vars_88):
var_759 = torch._convolution(var_740, input_vars_85, None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_764 = torch.batch_norm(var_759, input_vars_86, input_vars_87,
input_vars_88, input_vars_89, False, 0.1,
1e-05, True)
var_766 = torch.add(var_764, var_715, alpha=1)
return var_766
def jojo_4(self, input_vars_69, var_683, input_vars_75, input_vars_71,
input_vars_68, input_vars_70, input_vars_74, input_vars_77,
input_vars_76, var_639, input_vars_73):
var_688 = torch.batch_norm(var_683, input_vars_68, input_vars_69,
input_vars_70, input_vars_71, False, 0.1,
1e-05, True)
var_707 = torch._convolution(var_639, input_vars_73, None, [
2,
2,
], [
0,
0,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_712 = torch.batch_norm(var_707, input_vars_74, input_vars_75,
input_vars_76, input_vars_77, False, 0.1,
1e-05, True)
return var_712, var_688
def jojo_17(self, input_vars_89, var_1031, input_vars_86, input_vars_85, input_vars_87, input_vars_88):
var_1050 = torch._convolution(var_1031, input_vars_85, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1055 = torch.batch_norm(var_1050, input_vars_86, input_vars_87, input_vars_88, input_vars_89, False, 0.1, 1e-05, True)
var_1056 = torch.relu_(var_1055)
return var_1056
def jojo_24(self, var_747, input_vars_19):
var_766 = torch._convolution(var_747, input_vars_19, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_766
def jojo_26(self, input_vars_3, input_vars_1, input_vars_4, input_vars_5, input_vars_2, input_vars_0):
var_675 = torch._convolution(input_vars_0, input_vars_1, None, [2, 2, ], [3, 3, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_680 = torch.batch_norm(var_675, input_vars_2, input_vars_3, input_vars_4, input_vars_5, False, 0.1, 1e-05, True)
return var_680
def forward_(self, input_vars):
var_116 = torch.utils.checkpoint.checkpoint(self.jojo_4, input_vars[1],
input_vars[0],
input_vars[2])
var_117 = torch.relu_(var_116)
var_135 = torch.utils.checkpoint.checkpoint(self.jojo_3, input_vars[3],
var_117, input_vars[4])
var_136 = torch.relu_(var_135)
var_168 = torch.utils.checkpoint.checkpoint(self.jojo_2, input_vars[6],
input_vars[5], var_136)
var_169 = torch.relu_(var_168)
var_202 = torch.utils.checkpoint.checkpoint(self.jojo_1, var_169,
input_vars[8],
input_vars[7])
var_220 = torch._convolution(var_202, input_vars[9], input_vars[10], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_258 = torch.utils.checkpoint.checkpoint(self.jojo_0,
input_vars[12], var_220,
input_vars[14],
input_vars[11],
input_vars[13])
var_259 = torch.relu_(var_258)
var_273 = torch.max_pool2d(var_259, [
2,
2,
], [
2,
2,
], [
0,
0,
], [
1,
1,
], False)
var_291 = torch._convolution(var_273, input_vars[15], input_vars[16], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_292 = torch.relu_(var_291)
var_310 = torch._convolution(var_292, input_vars[17], input_vars[18], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_311 = torch.relu_(var_310)
var_329 = torch._convolution(var_311, input_vars[19], input_vars[20], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_330 = torch.relu_(var_329)
var_344 = torch.max_pool2d(var_330, [
2,
2,
], [
2,
2,
], [
0,
0,
], [
1,
1,
], False)
var_362 = torch._convolution(var_344, input_vars[21], input_vars[22], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_363 = torch.relu_(var_362)
var_381 = torch._convolution(var_363, input_vars[23], input_vars[24], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_382 = torch.relu_(var_381)
var_400 = torch._convolution(var_382, input_vars[25], input_vars[26], [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_401 = torch.relu_(var_400)
var_415 = torch.max_pool2d(var_401, [
2,
2,
], [
2,
2,
], [
0,
0,
], [
1,
1,
], False)
var_431 = torch.nn.AdaptiveAvgPool2d([
7,
7,
])(var_415)
var_434 = torch.flatten(var_431, 1, -1)
var_435 = torch.t(input_vars[27])
var_438 = torch.addmm(input_vars[28],
var_434,
var_435,
beta=1,
alpha=1)
var_439 = torch.relu_(var_438)
var_442 = torch.dropout(var_439, 0.5, False)
var_443 = torch.t(input_vars[29])
var_446 = torch.addmm(input_vars[30],
var_442,
var_443,
beta=1,
alpha=1)
var_447 = torch.relu_(var_446)
var_450 = torch.dropout(var_447, 0.5, False)
var_451 = torch.t(input_vars[31])
var_454 = torch.addmm(input_vars[32],
var_450,
var_451,
beta=1,
alpha=1)
return var_454
def forward_(self, input_vars):
var_680 = torch.utils.checkpoint.checkpoint(self.jojo_26, input_vars[3], input_vars[1], input_vars[4], input_vars[5], input_vars[2], input_vars[0])
var_681 = torch.relu_(var_680)
var_746 = torch.utils.checkpoint.checkpoint(self.jojo_25, input_vars[15], input_vars[14], input_vars[8], input_vars[11], input_vars[10], input_vars[17], input_vars[9], var_681, input_vars[16], input_vars[7], input_vars[13])
var_747 = torch.relu_(var_746)
var_766 = torch.utils.checkpoint.checkpoint(self.jojo_24, var_747, input_vars[19])
var_771 = torch.batch_norm(var_766, input_vars[20], input_vars[21], input_vars[22], input_vars[23], False, 0.1, 1e-05, True)
var_791 = torch.utils.checkpoint.checkpoint(self.jojo_23, var_771, input_vars[25])
var_796 = torch.batch_norm(var_791, input_vars[26], input_vars[27], input_vars[28], input_vars[29], False, 0.1, 1e-05, True)
var_818, var_799 = torch.utils.checkpoint.checkpoint(self.jojo_22, var_747, var_796, input_vars[31])
var_823 = torch.batch_norm(var_818, input_vars[32], input_vars[33], input_vars[34], input_vars[35], False, 0.1, 1e-05, True)
var_843 = torch.utils.checkpoint.checkpoint(self.jojo_21, input_vars[37], var_823)
var_848 = torch.batch_norm(var_843, input_vars[38], input_vars[39], input_vars[40], input_vars[41], False, 0.1, 1e-05, True)
var_851, var_895 = torch.utils.checkpoint.checkpoint(self.jojo_20, input_vars[45], input_vars[44], var_848, var_799, input_vars[47], input_vars[46], input_vars[49], input_vars[43])
var_900 = torch.batch_norm(var_895, input_vars[50], input_vars[51], input_vars[52], input_vars[53], False, 0.1, 1e-05, True)
var_979, var_998 = torch.utils.checkpoint.checkpoint(self.jojo_19, var_851, input_vars[71], input_vars[70], input_vars[67], input_vars[55], input_vars[57], input_vars[56], var_900, input_vars[62], input_vars[65], input_vars[73], input_vars[61], input_vars[68], input_vars[63], input_vars[69], input_vars[59], input_vars[64], input_vars[58])
var_1003 = torch.batch_norm(var_998, input_vars[74], input_vars[75], input_vars[76], input_vars[77], False, 0.1, 1e-05, True)
var_1004 = torch.relu_(var_1003)
var_1028 = torch.utils.checkpoint.checkpoint(self.jojo_18, input_vars[81], var_1004, input_vars[83], input_vars[79], input_vars[80], input_vars[82])
var_1030 = torch.add(var_1028, var_979, alpha=1)
var_1031 = torch.relu_(var_1030)
var_1056 = torch.utils.checkpoint.checkpoint(self.jojo_17, input_vars[89], var_1031, input_vars[86], input_vars[85], input_vars[87], input_vars[88])
var_1075 = torch._convolution(var_1056, input_vars[91], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1080 = torch.utils.checkpoint.checkpoint(self.jojo_16, input_vars[95], input_vars[94], input_vars[92], var_1075, input_vars[93])
var_1082 = torch.add(var_1080, var_1031, alpha=1)
var_1107, var_1083 = torch.utils.checkpoint.checkpoint(self.jojo_15, input_vars[100], var_1082, input_vars[97], input_vars[99], input_vars[98], input_vars[101])
var_1108 = torch.relu_(var_1107)
var_1127 = torch._convolution(var_1108, input_vars[103], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1159 = torch.utils.checkpoint.checkpoint(self.jojo_14, var_1127, input_vars[104], input_vars[111], input_vars[110], input_vars[112], input_vars[106], input_vars[109], input_vars[113], var_1083, input_vars[105], input_vars[107])
var_1178 = torch._convolution(var_1159, input_vars[115], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1184 = torch.utils.checkpoint.checkpoint(self.jojo_13, input_vars[117], input_vars[119], input_vars[118], input_vars[116], var_1178)
var_1203 = torch._convolution(var_1184, input_vars[121], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1211, var_1235 = torch.utils.checkpoint.checkpoint(self.jojo_12, input_vars[125], var_1203, var_1159, input_vars[128], input_vars[123], input_vars[124], input_vars[122], input_vars[127], input_vars[130], input_vars[131], input_vars[129])
var_1236 = torch.relu_(var_1235)
var_1255 = torch._convolution(var_1236, input_vars[133], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1262 = torch.utils.checkpoint.checkpoint(self.jojo_11, input_vars[135], var_1255, var_1211, input_vars[134], input_vars[136], input_vars[137])
var_1263 = torch.relu_(var_1262)
var_1282 = torch._convolution(var_1263, input_vars[139], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1287 = torch.batch_norm(var_1282, input_vars[140], input_vars[141], input_vars[142], input_vars[143], False, 0.1, 1e-05, True)
var_1307 = torch.utils.checkpoint.checkpoint(self.jojo_10, var_1287, input_vars[145])
var_1312 = torch.batch_norm(var_1307, input_vars[146], input_vars[147], input_vars[148], input_vars[149], False, 0.1, 1e-05, True)
var_1314 = torch.utils.checkpoint.checkpoint(self.jojo_9, var_1263, var_1312)
var_1315 = torch.relu_(var_1314)
var_1334 = torch.utils.checkpoint.checkpoint(self.jojo_8, var_1315, input_vars[151])
var_1339 = torch.batch_norm(var_1334, input_vars[152], input_vars[153], input_vars[154], input_vars[155], False, 0.1, 1e-05, True)
var_1340 = torch.utils.checkpoint.checkpoint(self.jojo_7, var_1339)
var_1359 = torch._convolution(var_1340, input_vars[157], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1364 = torch.batch_norm(var_1359, input_vars[158], input_vars[159], input_vars[160], input_vars[161], False, 0.1, 1e-05, True)
var_1366 = torch.add(var_1364, var_1315, alpha=1)
var_1391, var_1367 = torch.utils.checkpoint.checkpoint(self.jojo_6, input_vars[166], input_vars[164], input_vars[167], var_1366, input_vars[165], input_vars[163])
var_1392 = torch.relu_(var_1391)
var_1411 = torch._convolution(var_1392, input_vars[169], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1416 = torch.utils.checkpoint.checkpoint(self.jojo_5, input_vars[170], input_vars[172], var_1411, input_vars[171], input_vars[173])
var_1418 = torch.add(var_1416, var_1367, alpha=1)
var_1419 = torch.relu_(var_1418)
var_1444 = torch.utils.checkpoint.checkpoint(self.jojo_4, input_vars[178], input_vars[177], var_1419, input_vars[176], input_vars[175], input_vars[179])
var_1463 = torch._convolution(var_1444, input_vars[181], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1468 = torch.batch_norm(var_1463, input_vars[182], input_vars[183], input_vars[184], input_vars[185], False, 0.1, 1e-05, True)
var_1487 = torch._convolution(var_1419, input_vars[187], None, [2, 2, ], [0, 0, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1492 = torch.utils.checkpoint.checkpoint(self.jojo_3, input_vars[190], input_vars[188], var_1487, input_vars[191], input_vars[189])
var_1494 = torch.add(var_1468, var_1492, alpha=1)
var_1495 = torch.utils.checkpoint.checkpoint(self.jojo_2, var_1494)
var_1514 = torch._convolution(var_1495, input_vars[193], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1519 = torch.batch_norm(var_1514, input_vars[194], input_vars[195], input_vars[196], input_vars[197], False, 0.1, 1e-05, True)
var_1539 = torch.utils.checkpoint.checkpoint(self.jojo_1, input_vars[199], var_1519)
var_1544 = torch.batch_norm(var_1539, input_vars[200], input_vars[201], input_vars[202], input_vars[203], False, 0.1, 1e-05, True)
var_1571, var_1547 = torch.utils.checkpoint.checkpoint(self.jojo_0, var_1544, input_vars[205], input_vars[208], input_vars[209], var_1495, input_vars[206], input_vars[207])
var_1572 = torch.relu_(var_1571)
var_1591 = torch._convolution(var_1572, input_vars[211], None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1596 = torch.batch_norm(var_1591, input_vars[212], input_vars[213], input_vars[214], input_vars[215], False, 0.1, 1e-05, True)
var_1598 = torch.add(var_1596, var_1547, alpha=1)
var_1599 = torch.relu_(var_1598)
var_1615 = self.layer_0(var_1599)
var_1618 = torch.flatten(var_1615, 1, -1)
var_1619 = torch.t(input_vars[217])
var_1622 = torch.addmm(input_vars[218], var_1618, var_1619, beta=1, alpha=1)
return var_1622
def jojo_1(self, input_vars_199, var_1519):
var_1520 = torch.relu_(var_1519.clone())
var_1539 = torch._convolution(var_1520, input_vars_199, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_1539
def jojo_4(self, input_vars_178, input_vars_177, var_1419, input_vars_176, input_vars_175, input_vars_179):
var_1438 = torch._convolution(var_1419, input_vars_175, None, [2, 2, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1443 = torch.batch_norm(var_1438, input_vars_176, input_vars_177, input_vars_178, input_vars_179, False, 0.1, 1e-05, True)
var_1444 = torch.relu_(var_1443)
return var_1444
def forward_(self, input_vars):
var_407, var_426 = torch.utils.checkpoint.checkpoint(
self.jojo_8, input_vars[7], input_vars[5], input_vars[4],
input_vars[1], input_vars[2], input_vars[3], input_vars[0])
var_431 = torch.batch_norm(var_426, input_vars[8], input_vars[9],
input_vars[10], input_vars[11], False, 0.1,
1e-05, True)
var_459, var_503 = torch.utils.checkpoint.checkpoint(
self.jojo_7, input_vars[25], var_431, input_vars[16],
input_vars[13], input_vars[15], input_vars[23], input_vars[19],
input_vars[21], input_vars[22], var_407, input_vars[17],
input_vars[14], input_vars[20])
var_508 = torch.batch_norm(var_503, input_vars[26], input_vars[27],
input_vars[28], input_vars[29], False, 0.1,
1e-05, True)
var_560, var_584 = torch.utils.checkpoint.checkpoint(
self.jojo_6, input_vars[44], input_vars[34], input_vars[37],
var_459, input_vars[45], var_508, input_vars[31], input_vars[38],
input_vars[41], input_vars[47], input_vars[40], input_vars[43],
input_vars[33], input_vars[35], input_vars[46], input_vars[32],
input_vars[39])
var_586 = torch.add(var_560, var_584, alpha=1)
var_663, var_639 = torch.utils.checkpoint.checkpoint(
self.jojo_5, input_vars[50], var_586, input_vars[51],
input_vars[49], input_vars[57], input_vars[64], input_vars[52],
input_vars[55], input_vars[61], input_vars[63], input_vars[58],
input_vars[56], input_vars[53], input_vars[65], input_vars[62],
input_vars[59])
var_664 = torch.relu_(var_663)
var_683 = torch._convolution(var_664, input_vars[67], None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_712, var_688 = torch.utils.checkpoint.checkpoint(
self.jojo_4, input_vars[69], var_683, input_vars[75],
input_vars[71], input_vars[68], input_vars[70], input_vars[74],
input_vars[77], input_vars[76], var_639, input_vars[73])
var_714 = torch.add(var_688, var_712, alpha=1)
var_715 = torch.utils.checkpoint.checkpoint(self.jojo_3, var_714)
var_734 = torch._convolution(var_715, input_vars[79], None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_739 = torch.batch_norm(var_734, input_vars[80], input_vars[81],
input_vars[82], input_vars[83], False, 0.1,
1e-05, True)
var_740 = torch.relu_(var_739)
var_766 = torch.utils.checkpoint.checkpoint(
self.jojo_2, input_vars[89], input_vars[85], input_vars[87],
var_740, input_vars[86], var_715, input_vars[88])
var_767 = torch.relu_(var_766)
var_786 = torch._convolution(var_767, input_vars[91], None, [
2,
2,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_791 = torch.utils.checkpoint.checkpoint(self.jojo_1,
input_vars[95],
input_vars[92],
input_vars[94], var_786,
input_vars[93])
var_792 = torch.relu_(var_791)
var_811 = torch._convolution(var_792, input_vars[97], None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_816 = torch.batch_norm(var_811, input_vars[98], input_vars[99],
input_vars[100], input_vars[101], False,
0.1, 1e-05, True)
var_835 = torch._convolution(var_767, input_vars[103], None, [
2,
2,
], [
0,
0,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_840 = torch.batch_norm(var_835, input_vars[104], input_vars[105],
input_vars[106], input_vars[107], False,
0.1, 1e-05, True)
var_842 = torch.add(var_816, var_840, alpha=1)
var_843 = torch.relu_(var_842)
var_862 = torch._convolution(var_843, input_vars[109], None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_867 = torch.batch_norm(var_862, input_vars[110], input_vars[111],
input_vars[112], input_vars[113], False,
0.1, 1e-05, True)
var_868 = torch.relu_(var_867)
var_887 = torch._convolution(var_868, input_vars[115], None, [
1,
1,
], [
1,
1,
], [
1,
1,
], False, [
0,
0,
], 1, False, False, True)
var_892 = torch.batch_norm(var_887, input_vars[116], input_vars[117],
input_vars[118], input_vars[119], False,
0.1, 1e-05, True)
var_894 = torch.add(var_892, var_843, alpha=1)
var_895 = torch.relu_(var_894)
var_911 = self.layer_0(var_895)
var_914 = torch.flatten(var_911, 1, -1)
var_915 = torch.utils.checkpoint.checkpoint(self.jojo_0,
input_vars[121])
var_918 = torch.addmm(input_vars[122],
var_914,
var_915,
beta=1,
alpha=1)
return var_918
def jojo_6(self, input_vars_166, input_vars_164, input_vars_167, var_1366, input_vars_165, input_vars_163):
var_1367 = torch.relu_(var_1366.clone())
var_1386 = torch._convolution(var_1367, input_vars_163, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1391 = torch.batch_norm(var_1386, input_vars_164, input_vars_165, input_vars_166, input_vars_167, False, 0.1, 1e-05, True)
return var_1391, var_1367
def jojo_8(self, var_1315, input_vars_151):
var_1334 = torch._convolution(var_1315, input_vars_151, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_1334
def jojo_10(self, var_1287, input_vars_145):
var_1288 = torch.relu_(var_1287.clone())
var_1307 = torch._convolution(var_1288, input_vars_145, None, [1, 1, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
return var_1307
def jojo_15(self, input_vars_100, var_1082, input_vars_97, input_vars_99, input_vars_98, input_vars_101):
var_1083 = torch.relu_(var_1082.clone())
var_1102 = torch._convolution(var_1083, input_vars_97, None, [2, 2, ], [1, 1, ], [1, 1, ], False, [0, 0, ], 1, False, False, True)
var_1107 = torch.batch_norm(var_1102, input_vars_98, input_vars_99, input_vars_100, input_vars_101, False, 0.1, 1e-05, True)
return var_1107, var_1083
