diff options
Diffstat (limited to 'modules')
| -rw-r--r-- | modules/hypernetworks/hypernetwork.py | 25 |
1 files changed, 14 insertions, 11 deletions
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 842b6447..eab8b32f 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -34,7 +34,7 @@ class HypernetworkModule(torch.nn.Module): }
activation_dict.update({cls_name.lower(): cls_obj for cls_name, cls_obj in inspect.getmembers(torch.nn.modules.activation) if inspect.isclass(cls_obj) and cls_obj.__module__ == 'torch.nn.modules.activation'})
- def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, weight_init='Normal', add_layer_norm=False, use_dropout=False):
+ def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, weight_init='Normal', add_layer_norm=False, use_dropout=False, activate_output=False):
super().__init__()
assert layer_structure is not None, "layer_structure must not be None"
@@ -47,8 +47,8 @@ class HypernetworkModule(torch.nn.Module): # Add a fully-connected layer
linears.append(torch.nn.Linear(int(dim * layer_structure[i]), int(dim * layer_structure[i+1])))
- # Add an activation func
- if activation_func == "linear" or activation_func is None:
+ # Add an activation func except last layer
+ if activation_func == "linear" or activation_func is None or (i >= len(layer_structure) - 2 and not activate_output):
pass
elif activation_func in self.activation_dict:
linears.append(self.activation_dict[activation_func]())
@@ -59,8 +59,8 @@ class HypernetworkModule(torch.nn.Module): if add_layer_norm:
linears.append(torch.nn.LayerNorm(int(dim * layer_structure[i+1])))
- # Add dropout expect last layer
- if use_dropout and i < len(layer_structure) - 3:
+ # Add dropout except last layer
+ if use_dropout and i < len(layer_structure) - 2:
linears.append(torch.nn.Dropout(p=0.3))
self.linear = torch.nn.Sequential(*linears)
@@ -126,7 +126,7 @@ class Hypernetwork: filename = None
name = None
- def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False):
+ def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, activate_output=False)
self.filename = None
self.name = name
self.layers = {}
@@ -138,11 +138,12 @@ class Hypernetwork: self.weight_init = weight_init
self.add_layer_norm = add_layer_norm
self.use_dropout = use_dropout
+ self.activate_output = activate_output
for size in enable_sizes or []:
self.layers[size] = (
- HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
- HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
+ HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout, self.activate_output),
+ HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout, self.activate_output),
)
def weights(self):
@@ -170,6 +171,7 @@ class Hypernetwork: state_dict['use_dropout'] = self.use_dropout
state_dict['sd_checkpoint'] = self.sd_checkpoint
state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name
+ state_dict['activate_output'] = self.activate_output
torch.save(state_dict, filename)
@@ -188,14 +190,15 @@ class Hypernetwork: print(f"Weight initialization is {self.weight_init}")
self.add_layer_norm = state_dict.get('is_layer_norm', False)
print(f"Layer norm is set to {self.add_layer_norm}")
- self.use_dropout = state_dict.get('use_dropout', False)
+ self.use_dropout = state_dict.get('use_dropout', False
print(f"Dropout usage is set to {self.use_dropout}" )
+ self.activate_output = state_dict.get('activate_output', True)
for size, sd in state_dict.items():
if type(size) == int:
self.layers[size] = (
- HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
- HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
+ HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout, self.activate_output),
+ HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout, self.activate_output),
)
self.name = state_dict.get('name', self.name)
|