class <lambda>(torch.nn.Module):
    def forward(self, arg0_1: "f32[1, 256, 68, 68]", arg1_1: "f32[256, 256, 3, 3]", arg2_1: "f32[256]", arg3_1: "f32[256]", arg4_1: "f32[256]", arg5_1: "f32[256, 256, 3, 3]", arg6_1: "f32[256]", arg7_1: "f32[256]", arg8_1: "f32[256]", arg9_1: "f32[256, 256, 3, 3]", arg10_1: "f32[256]", arg11_1: "f32[256]", arg12_1: "f32[256]", arg13_1: "f32[256, 256, 3, 3]", arg14_1: "f32[256]", arg15_1: "f32[256]", arg16_1: "f32[256]"):
        # File: /workspace/networks/layers/basic.py:69 in forward, code: r = self.conv1(F.relu(x))
        relu: "f32[1, 256, 68, 68]" = torch.ops.aten.relu.default(arg0_1)
        
        # 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,
        convert_element_type: "f16[256]" = torch.ops.prims.convert_element_type.default(arg2_1, torch.float16);  arg2_1 = None
        convert_element_type_1: "f16[256, 256, 3, 3]" = torch.ops.prims.convert_element_type.default(arg1_1, torch.float16);  arg1_1 = None
        convert_element_type_2: "f16[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(relu, torch.float16);  relu = None
        convolution: "f16[1, 256, 68, 68]" = torch.ops.aten.convolution.default(convert_element_type_2, convert_element_type_1, convert_element_type, [1, 1], [1, 1], [1, 1], False, [0, 0], 1);  convert_element_type_2 = convert_element_type_1 = convert_element_type = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        convert_element_type_3: "f32[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(convolution, torch.float32);  convolution = None
        view: "f32[1, 8, 32, 4624]" = torch.ops.aten.view.default(convert_element_type_3, [1, 8, 32, 4624]);  convert_element_type_3 = None
        var_mean = torch.ops.aten.var_mean.correction(view, [2, 3], correction = 0, keepdim = True)
        getitem: "f32[1, 8, 1, 1]" = var_mean[0]
        getitem_1: "f32[1, 8, 1, 1]" = var_mean[1];  var_mean = None
        add: "f32[1, 8, 1, 1]" = torch.ops.aten.add.Tensor(getitem, 1e-05);  getitem = None
        rsqrt: "f32[1, 8, 1, 1]" = torch.ops.aten.rsqrt.default(add);  add = None
        sub: "f32[1, 8, 32, 4624]" = torch.ops.aten.sub.Tensor(view, getitem_1);  view = getitem_1 = None
        mul: "f32[1, 8, 32, 4624]" = torch.ops.aten.mul.Tensor(sub, rsqrt);  sub = rsqrt = None
        view_1: "f32[1, 256, 68, 68]" = torch.ops.aten.view.default(mul, [1, 256, 68, 68]);  mul = None
        unsqueeze: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg4_1, 0);  arg4_1 = None
        unsqueeze_1: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze, 2);  unsqueeze = None
        unsqueeze_2: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_1, 3);  unsqueeze_1 = None
        unsqueeze_3: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg3_1, 0);  arg3_1 = None
        unsqueeze_4: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_3, 2);  unsqueeze_3 = None
        unsqueeze_5: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_4, 3);  unsqueeze_4 = None
        mul_1: "f32[1, 256, 68, 68]" = torch.ops.aten.mul.Tensor(view_1, unsqueeze_5);  view_1 = unsqueeze_5 = None
        add_1: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(mul_1, unsqueeze_2);  mul_1 = unsqueeze_2 = None
        
        # File: /workspace/networks/layers/basic.py:72 in forward, code: r = self.conv2(F.relu(r))
        relu_1: "f32[1, 256, 68, 68]" = torch.ops.aten.relu.default(add_1);  add_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,
        convert_element_type_4: "f16[256]" = torch.ops.prims.convert_element_type.default(arg6_1, torch.float16);  arg6_1 = None
        convert_element_type_5: "f16[256, 256, 3, 3]" = torch.ops.prims.convert_element_type.default(arg5_1, torch.float16);  arg5_1 = None
        convert_element_type_6: "f16[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(relu_1, torch.float16);  relu_1 = None
        convolution_1: "f16[1, 256, 68, 68]" = torch.ops.aten.convolution.default(convert_element_type_6, convert_element_type_5, convert_element_type_4, [1, 1], [1, 1], [1, 1], False, [0, 0], 1);  convert_element_type_6 = convert_element_type_5 = convert_element_type_4 = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        convert_element_type_7: "f32[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(convolution_1, torch.float32);  convolution_1 = None
        view_2: "f32[1, 8, 32, 4624]" = torch.ops.aten.view.default(convert_element_type_7, [1, 8, 32, 4624]);  convert_element_type_7 = None
        var_mean_1 = torch.ops.aten.var_mean.correction(view_2, [2, 3], correction = 0, keepdim = True)
        getitem_2: "f32[1, 8, 1, 1]" = var_mean_1[0]
        getitem_3: "f32[1, 8, 1, 1]" = var_mean_1[1];  var_mean_1 = None
        add_2: "f32[1, 8, 1, 1]" = torch.ops.aten.add.Tensor(getitem_2, 1e-05);  getitem_2 = None
        rsqrt_1: "f32[1, 8, 1, 1]" = torch.ops.aten.rsqrt.default(add_2);  add_2 = None
        sub_1: "f32[1, 8, 32, 4624]" = torch.ops.aten.sub.Tensor(view_2, getitem_3);  view_2 = getitem_3 = None
        mul_2: "f32[1, 8, 32, 4624]" = torch.ops.aten.mul.Tensor(sub_1, rsqrt_1);  sub_1 = rsqrt_1 = None
        view_3: "f32[1, 256, 68, 68]" = torch.ops.aten.view.default(mul_2, [1, 256, 68, 68]);  mul_2 = None
        unsqueeze_6: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg8_1, 0);  arg8_1 = None
        unsqueeze_7: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_6, 2);  unsqueeze_6 = None
        unsqueeze_8: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_7, 3);  unsqueeze_7 = None
        unsqueeze_9: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg7_1, 0);  arg7_1 = None
        unsqueeze_10: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_9, 2);  unsqueeze_9 = None
        unsqueeze_11: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_10, 3);  unsqueeze_10 = None
        mul_3: "f32[1, 256, 68, 68]" = torch.ops.aten.mul.Tensor(view_3, unsqueeze_11);  view_3 = unsqueeze_11 = None
        add_3: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(mul_3, unsqueeze_8);  mul_3 = unsqueeze_8 = None
        
        # File: /workspace/networks/layers/basic.py:78 in forward, code: return x + r
        add_4: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(arg0_1, add_3);  arg0_1 = add_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]" = torch.ops.aten.relu.default(add_4)
        
        # 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,
        convert_element_type_8: "f16[256]" = torch.ops.prims.convert_element_type.default(arg10_1, torch.float16);  arg10_1 = None
        convert_element_type_9: "f16[256, 256, 3, 3]" = torch.ops.prims.convert_element_type.default(arg9_1, torch.float16);  arg9_1 = None
        convert_element_type_10: "f16[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(relu_2, torch.float16);  relu_2 = None
        convolution_2: "f16[1, 256, 68, 68]" = torch.ops.aten.convolution.default(convert_element_type_10, convert_element_type_9, convert_element_type_8, [1, 1], [1, 1], [1, 1], False, [0, 0], 1);  convert_element_type_10 = convert_element_type_9 = convert_element_type_8 = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        convert_element_type_11: "f32[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(convolution_2, torch.float32);  convolution_2 = None
        view_4: "f32[1, 8, 32, 4624]" = torch.ops.aten.view.default(convert_element_type_11, [1, 8, 32, 4624]);  convert_element_type_11 = None
        var_mean_2 = torch.ops.aten.var_mean.correction(view_4, [2, 3], correction = 0, keepdim = True)
        getitem_4: "f32[1, 8, 1, 1]" = var_mean_2[0]
        getitem_5: "f32[1, 8, 1, 1]" = var_mean_2[1];  var_mean_2 = None
        add_5: "f32[1, 8, 1, 1]" = torch.ops.aten.add.Tensor(getitem_4, 1e-05);  getitem_4 = None
        rsqrt_2: "f32[1, 8, 1, 1]" = torch.ops.aten.rsqrt.default(add_5);  add_5 = None
        sub_2: "f32[1, 8, 32, 4624]" = torch.ops.aten.sub.Tensor(view_4, getitem_5);  view_4 = getitem_5 = None
        mul_4: "f32[1, 8, 32, 4624]" = torch.ops.aten.mul.Tensor(sub_2, rsqrt_2);  sub_2 = rsqrt_2 = None
        view_5: "f32[1, 256, 68, 68]" = torch.ops.aten.view.default(mul_4, [1, 256, 68, 68]);  mul_4 = None
        unsqueeze_12: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg12_1, 0);  arg12_1 = None
        unsqueeze_13: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_12, 2);  unsqueeze_12 = None
        unsqueeze_14: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_13, 3);  unsqueeze_13 = None
        unsqueeze_15: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg11_1, 0);  arg11_1 = None
        unsqueeze_16: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_15, 2);  unsqueeze_15 = None
        unsqueeze_17: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_16, 3);  unsqueeze_16 = None
        mul_5: "f32[1, 256, 68, 68]" = torch.ops.aten.mul.Tensor(view_5, unsqueeze_17);  view_5 = unsqueeze_17 = None
        add_6: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(mul_5, unsqueeze_14);  mul_5 = unsqueeze_14 = None
        
        # File: /workspace/networks/layers/basic.py:72 in forward, code: r = self.conv2(F.relu(r))
        relu_3: "f32[1, 256, 68, 68]" = torch.ops.aten.relu.default(add_6);  add_6 = 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,
        convert_element_type_12: "f16[256]" = torch.ops.prims.convert_element_type.default(arg14_1, torch.float16);  arg14_1 = None
        convert_element_type_13: "f16[256, 256, 3, 3]" = torch.ops.prims.convert_element_type.default(arg13_1, torch.float16);  arg13_1 = None
        convert_element_type_14: "f16[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(relu_3, torch.float16);  relu_3 = None
        convolution_3: "f16[1, 256, 68, 68]" = torch.ops.aten.convolution.default(convert_element_type_14, convert_element_type_13, convert_element_type_12, [1, 1], [1, 1], [1, 1], False, [0, 0], 1);  convert_element_type_14 = convert_element_type_13 = convert_element_type_12 = None
        
        # File: /opt/conda/lib/python3.11/site-packages/torch/nn/modules/normalization.py:287 in forward, code: return F.group_norm(
        convert_element_type_15: "f32[1, 256, 68, 68]" = torch.ops.prims.convert_element_type.default(convolution_3, torch.float32);  convolution_3 = None
        view_6: "f32[1, 8, 32, 4624]" = torch.ops.aten.view.default(convert_element_type_15, [1, 8, 32, 4624]);  convert_element_type_15 = None
        var_mean_3 = torch.ops.aten.var_mean.correction(view_6, [2, 3], correction = 0, keepdim = True)
        getitem_6: "f32[1, 8, 1, 1]" = var_mean_3[0]
        getitem_7: "f32[1, 8, 1, 1]" = var_mean_3[1];  var_mean_3 = None
        add_7: "f32[1, 8, 1, 1]" = torch.ops.aten.add.Tensor(getitem_6, 1e-05);  getitem_6 = None
        rsqrt_3: "f32[1, 8, 1, 1]" = torch.ops.aten.rsqrt.default(add_7);  add_7 = None
        sub_3: "f32[1, 8, 32, 4624]" = torch.ops.aten.sub.Tensor(view_6, getitem_7);  view_6 = getitem_7 = None
        mul_6: "f32[1, 8, 32, 4624]" = torch.ops.aten.mul.Tensor(sub_3, rsqrt_3);  sub_3 = rsqrt_3 = None
        view_7: "f32[1, 256, 68, 68]" = torch.ops.aten.view.default(mul_6, [1, 256, 68, 68]);  mul_6 = None
        unsqueeze_18: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg16_1, 0);  arg16_1 = None
        unsqueeze_19: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_18, 2);  unsqueeze_18 = None
        unsqueeze_20: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_19, 3);  unsqueeze_19 = None
        unsqueeze_21: "f32[1, 256]" = torch.ops.aten.unsqueeze.default(arg15_1, 0);  arg15_1 = None
        unsqueeze_22: "f32[1, 256, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_21, 2);  unsqueeze_21 = None
        unsqueeze_23: "f32[1, 256, 1, 1]" = torch.ops.aten.unsqueeze.default(unsqueeze_22, 3);  unsqueeze_22 = None
        mul_7: "f32[1, 256, 68, 68]" = torch.ops.aten.mul.Tensor(view_7, unsqueeze_23);  view_7 = unsqueeze_23 = None
        add_8: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(mul_7, unsqueeze_20);  mul_7 = unsqueeze_20 = None
        
        # File: /workspace/networks/layers/basic.py:78 in forward, code: return x + r
        add_9: "f32[1, 256, 68, 68]" = torch.ops.aten.add.Tensor(add_4, add_8);  add_4 = add_8 = None
        return (add_9,)