patch

dalle2_pytorch/__init__.py

@@ -1,3 +1,4 @@
+from dalle2_pytorch.version import __version__
 from dalle2_pytorch.dalle2_pytorch import DALLE2, DiffusionPriorNetwork, DiffusionPrior, Unet, Decoder
 from dalle2_pytorch.dalle2_pytorch import OpenAIClipAdapter
 from dalle2_pytorch.trainer import DecoderTrainer, DiffusionPriorTrainer

dalle2_pytorch/dalle2_pytorch.py

@@ -1347,7 +1347,7 @@ class Unet(nn.Module):
         init_dim = None,
         init_conv_kernel_size = 7,
         resnet_groups = 8,
-        num_resnet_blocks = 1,
+        num_resnet_blocks = 2,
         init_cross_embed_kernel_sizes = (3, 7, 15),
         cross_embed_downsample = False,
         cross_embed_downsample_kernel_sizes = (2, 4),

dalle2_pytorch/optimizer.py

@@ -1,8 +1,10 @@
 from torch.optim import AdamW, Adam
 
 def separate_weight_decayable_params(params):
-    no_wd_params = set([param for param in params if param.ndim < 2])
-    wd_params = set(params) - no_wd_params
+    wd_params, no_wd_params = [], []
+    for param in params:
+        param_list = no_wd_params if param.ndim < 2 else wd_params
+        param_list.append(param)
     return wd_params, no_wd_params
 
 def get_optimizer(
@@ -25,8 +27,8 @@ def get_optimizer(
         wd_params, no_wd_params = separate_weight_decayable_params(params)
 
         params = [
-            {'params': list(wd_params)},
-            {'params': list(no_wd_params), 'weight_decay': 0},
+            {'params': wd_params},
+            {'params': no_wd_params, 'weight_decay': 0},
         ]
 
     return AdamW(params, lr = lr, weight_decay = wd, betas = betas, eps = eps)

dalle2_pytorch/trainer.py

@@ -11,6 +11,8 @@ from torch.cuda.amp import autocast, GradScaler
 
 from dalle2_pytorch.dalle2_pytorch import Decoder, DiffusionPrior
 from dalle2_pytorch.optimizer import get_optimizer
+from dalle2_pytorch.version import __version__
+from packaging import version
 
 import numpy as np
 
@@ -57,8 +59,7 @@ def num_to_groups(num, divisor):
     return arr
 
 def get_pkg_version():
-    from pkg_resources import get_distribution
-    return get_distribution('dalle2_pytorch').version
+    return __version__
 
 # decorators
 
@@ -299,7 +300,7 @@ class DiffusionPriorTrainer(nn.Module):
             scaler = self.scaler.state_dict(),
             optimizer = self.optimizer.state_dict(),
             model = self.diffusion_prior.state_dict(),
-            version = get_pkg_version(),
+            version = __version__,
             step = self.step.item(),
             **kwargs
         )
@@ -315,8 +316,8 @@ class DiffusionPriorTrainer(nn.Module):
 
         loaded_obj = torch.load(str(path))
 
-        if get_pkg_version() != loaded_obj['version']:
-            print(f'loading saved diffusion prior at version {loaded_obj["version"]} but current package version is at {get_pkg_version()}')
+        if version.parse(__version__) != loaded_obj['version']:
+            print(f'loading saved diffusion prior at version {loaded_obj["version"]} but current package version is at {__version__}')
 
         self.diffusion_prior.load_state_dict(loaded_obj['model'], strict = strict)
         self.step.copy_(torch.ones_like(self.step) * loaded_obj['step'])
@@ -463,7 +464,7 @@ class DecoderTrainer(nn.Module):
 
         save_obj = dict(
             model = self.decoder.state_dict(),
-            version = get_pkg_version(),
+            version = __version__,
             step = self.step.item(),
             **kwargs
         )
@@ -486,7 +487,7 @@ class DecoderTrainer(nn.Module):
 
         loaded_obj = torch.load(str(path))
 
-        if get_pkg_version() != loaded_obj['version']:
+        if version.parse(__version__) != loaded_obj['version']:
             print(f'loading saved decoder at version {loaded_obj["version"]}, but current package version is {get_pkg_version()}')
 
         self.decoder.load_state_dict(loaded_obj['model'], strict = strict)

dalle2_pytorch/version.py

@@ -0,0 +1 @@
+__version__ = '0.6.4'

setup.py

@@ -1,4 +1,5 @@
 from setuptools import setup, find_packages
+exec(open('dalle2_pytorch/version.py').read())
 
 setup(
   name = 'dalle2-pytorch',
@@ -10,7 +11,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.6.0',
+  version = __version__,
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',
@@ -31,6 +32,7 @@ setup(
     'embedding-reader',
     'kornia>=0.5.4',
     'numpy',
+    'packaging',
     'pillow',
     'pydantic',
     'resize-right>=0.0.2',