class GraphModule(torch.nn.Module):
    def forward(self, L_x_: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0", L_self_modules_res1_modules_conv1_parameters_weight_: "f32[256, 256, 3, 3][2304, 9, 3, 1]cuda:0", L_self_modules_res1_modules_conv1_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res1_modules_gn1_parameters_weight_: "f32[256][1]cuda:0", L_self_modules_res1_modules_gn1_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res1_modules_conv2_parameters_weight_: "f32[256, 256, 3, 3][2304, 9, 3, 1]cuda:0", L_self_modules_res1_modules_conv2_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res1_modules_gn2_parameters_weight_: "f32[256][1]cuda:0", L_self_modules_res1_modules_gn2_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res2_modules_conv1_parameters_weight_: "f32[256, 256, 3, 3][2304, 9, 3, 1]cuda:0", L_self_modules_res2_modules_conv1_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res2_modules_gn1_parameters_weight_: "f32[256][1]cuda:0", L_self_modules_res2_modules_gn1_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res2_modules_conv2_parameters_weight_: "f32[256, 256, 3, 3][2304, 9, 3, 1]cuda:0", L_self_modules_res2_modules_conv2_parameters_bias_: "f32[256][1]cuda:0", L_self_modules_res2_modules_gn2_parameters_weight_: "f32[256][1]cuda:0", L_self_modules_res2_modules_gn2_parameters_bias_: "f32[256][1]cuda:0"):
        l_x_ = L_x_
        l_self_modules_res1_modules_conv1_parameters_weight_ = L_self_modules_res1_modules_conv1_parameters_weight_
        l_self_modules_res1_modules_conv1_parameters_bias_ = L_self_modules_res1_modules_conv1_parameters_bias_
        l_self_modules_res1_modules_gn1_parameters_weight_ = L_self_modules_res1_modules_gn1_parameters_weight_
        l_self_modules_res1_modules_gn1_parameters_bias_ = L_self_modules_res1_modules_gn1_parameters_bias_
        l_self_modules_res1_modules_conv2_parameters_weight_ = L_self_modules_res1_modules_conv2_parameters_weight_
        l_self_modules_res1_modules_conv2_parameters_bias_ = L_self_modules_res1_modules_conv2_parameters_bias_
        l_self_modules_res1_modules_gn2_parameters_weight_ = L_self_modules_res1_modules_gn2_parameters_weight_
        l_self_modules_res1_modules_gn2_parameters_bias_ = L_self_modules_res1_modules_gn2_parameters_bias_
        l_self_modules_res2_modules_conv1_parameters_weight_ = L_self_modules_res2_modules_conv1_parameters_weight_
        l_self_modules_res2_modules_conv1_parameters_bias_ = L_self_modules_res2_modules_conv1_parameters_bias_
        l_self_modules_res2_modules_gn1_parameters_weight_ = L_self_modules_res2_modules_gn1_parameters_weight_
        l_self_modules_res2_modules_gn1_parameters_bias_ = L_self_modules_res2_modules_gn1_parameters_bias_
        l_self_modules_res2_modules_conv2_parameters_weight_ = L_self_modules_res2_modules_conv2_parameters_weight_
        l_self_modules_res2_modules_conv2_parameters_bias_ = L_self_modules_res2_modules_conv2_parameters_bias_
        l_self_modules_res2_modules_gn2_parameters_weight_ = L_self_modules_res2_modules_gn2_parameters_weight_
        l_self_modules_res2_modules_gn2_parameters_bias_ = L_self_modules_res2_modules_gn2_parameters_bias_
        
        # File: /workspace/networks/layers/basic.py:69 in forward, code: r = self.conv1(F.relu(x))
        relu: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.relu(l_x_)
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/conv.py:453 in _conv_forward, code: return F.conv2d(input, weight, bias, self.stride,
        r: "f16[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.conv2d(relu, l_self_modules_res1_modules_conv1_parameters_weight_, l_self_modules_res1_modules_conv1_parameters_bias_, (1, 1), (1, 1), (1, 1), 1);  relu = l_self_modules_res1_modules_conv1_parameters_weight_ = l_self_modules_res1_modules_conv1_parameters_bias_ = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        r_1: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.group_norm(r, 8, l_self_modules_res1_modules_gn1_parameters_weight_, l_self_modules_res1_modules_gn1_parameters_bias_, 1e-05);  r = l_self_modules_res1_modules_gn1_parameters_weight_ = l_self_modules_res1_modules_gn1_parameters_bias_ = None
        
        # File: /workspace/networks/layers/basic.py:72 in forward, code: r = self.conv2(F.relu(r))
        relu_1: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.relu(r_1);  r_1 = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/conv.py:453 in _conv_forward, code: return F.conv2d(input, weight, bias, self.stride,
        r_2: "f16[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.conv2d(relu_1, l_self_modules_res1_modules_conv2_parameters_weight_, l_self_modules_res1_modules_conv2_parameters_bias_, (1, 1), (1, 1), (1, 1), 1);  relu_1 = l_self_modules_res1_modules_conv2_parameters_weight_ = l_self_modules_res1_modules_conv2_parameters_bias_ = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        r_3: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.group_norm(r_2, 8, l_self_modules_res1_modules_gn2_parameters_weight_, l_self_modules_res1_modules_gn2_parameters_bias_, 1e-05);  r_2 = l_self_modules_res1_modules_gn2_parameters_weight_ = l_self_modules_res1_modules_gn2_parameters_bias_ = None
        
        # File: /workspace/networks/layers/basic.py:78 in forward, code: return x + r
        add: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = l_x_ + r_3;  l_x_ = r_3 = None
        
        # File: /workspace/networks/layers/basic.py:69 in forward, code: r = self.conv1(F.relu(x))
        relu_2: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.relu(add)
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/conv.py:453 in _conv_forward, code: return F.conv2d(input, weight, bias, self.stride,
        r_4: "f16[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.conv2d(relu_2, l_self_modules_res2_modules_conv1_parameters_weight_, l_self_modules_res2_modules_conv1_parameters_bias_, (1, 1), (1, 1), (1, 1), 1);  relu_2 = l_self_modules_res2_modules_conv1_parameters_weight_ = l_self_modules_res2_modules_conv1_parameters_bias_ = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        r_5: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.group_norm(r_4, 8, l_self_modules_res2_modules_gn1_parameters_weight_, l_self_modules_res2_modules_gn1_parameters_bias_, 1e-05);  r_4 = l_self_modules_res2_modules_gn1_parameters_weight_ = l_self_modules_res2_modules_gn1_parameters_bias_ = None
        
        # File: /workspace/networks/layers/basic.py:72 in forward, code: r = self.conv2(F.relu(r))
        relu_3: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.relu(r_5);  r_5 = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/conv.py:453 in _conv_forward, code: return F.conv2d(input, weight, bias, self.stride,
        r_6: "f16[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.conv2d(relu_3, l_self_modules_res2_modules_conv2_parameters_weight_, l_self_modules_res2_modules_conv2_parameters_bias_, (1, 1), (1, 1), (1, 1), 1);  relu_3 = l_self_modules_res2_modules_conv2_parameters_weight_ = l_self_modules_res2_modules_conv2_parameters_bias_ = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        r_7: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = torch.nn.functional.group_norm(r_6, 8, l_self_modules_res2_modules_gn2_parameters_weight_, l_self_modules_res2_modules_gn2_parameters_bias_, 1e-05);  r_6 = l_self_modules_res2_modules_gn2_parameters_weight_ = l_self_modules_res2_modules_gn2_parameters_bias_ = None
        
        # File: /workspace/networks/layers/basic.py:78 in forward, code: return x + r
        add_1: "f32[1, 256, 68, 68][1183744, 4624, 68, 1]cuda:0" = add + r_7;  add = r_7 = None
        return (add_1,)