From cb4d2ce6a0c2ac58d8a074de0a51a3b97ce769cc Mon Sep 17 00:00:00 2001
From: smthemex <138738845+smthemex@users.noreply.github.com>
Date: Wed, 12 Jun 2024 19:52:48 +0800
Subject: [PATCH] Create fp16_util.py

add
---
 kandinsky2/model/fp16_util.py | 78 +++++++++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)
 create mode 100644 kandinsky2/model/fp16_util.py

diff --git a/kandinsky2/model/fp16_util.py b/kandinsky2/model/fp16_util.py
new file mode 100644
index 0000000..95b148b
--- /dev/null
+++ b/kandinsky2/model/fp16_util.py
@@ -0,0 +1,78 @@
+"""
+Helpers to inference with 16-bit precision.
+"""
+
+import torch.nn as nn
+from torch._utils import _flatten_dense_tensors, _unflatten_dense_tensors
+
+
+def convert_module_to_f16(l):
+    """
+    Convert primitive modules to float16.
+    """
+    if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)):
+        l.weight.data = l.weight.data.half()
+        if l.bias is not None:
+            l.bias.data = l.bias.data.half()
+
+
+def convert_module_to_f32(l):
+    """
+    Convert primitive modules to float32, undoing convert_module_to_f16().
+    """
+    if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)):
+        l.weight.data = l.weight.data.float()
+        if l.bias is not None:
+            l.bias.data = l.bias.data.float()
+
+
+def make_master_params(model_params):
+    """
+    Copy model parameters into a (differently-shaped) list of full-precision
+    parameters.
+    """
+    master_params = _flatten_dense_tensors(
+        [param.detach().float() for param in model_params]
+    )
+    master_params = nn.Parameter(master_params)
+    master_params.requires_grad = True
+    return [master_params]
+
+
+def model_grads_to_master_grads(model_params, master_params):
+    """
+    Copy the gradients from the model parameters into the master parameters
+    from make_master_params().
+    """
+    master_params[0].grad = _flatten_dense_tensors(
+        [param.grad.data.detach().float() for param in model_params]
+    )
+
+
+def master_params_to_model_params(model_params, master_params):
+    """
+    Copy the master parameter data back into the model parameters.
+    """
+    # Without copying to a list, if a generator is passed, this will
+    # silently not copy any parameters.
+    model_params = list(model_params)
+
+    for param, master_param in zip(
+        model_params, unflatten_master_params(model_params, master_params)
+    ):
+        param.detach().copy_(master_param)
+
+
+def unflatten_master_params(model_params, master_params):
+    """
+    Unflatten the master parameters to look like model_params.
+    """
+    return _unflatten_dense_tensors(master_params[0].detach(), model_params)
+
+
+def zero_grad(model_params):
+    for param in model_params:
+        # Taken from https://pytorch.org/docs/stable/_modules/torch/optim/optimizer.html#Optimizer.add_param_group
+        if param.grad is not None:
+            param.grad.detach_()
+            param.grad.zero_()