fix training with clip

dalle2_pytorch/dalle2_pytorch.py

@@ -784,7 +784,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
         self.predict_x_start = predict_x_start
 
         # @crowsonkb 's suggestion - https://github.com/lucidrains/DALLE2-pytorch/issues/60#issue-1226116132
-        self.image_embed_scale = default(image_embed_scale, image_embed_dim ** 0.5)
+        self.image_embed_scale = default(image_embed_scale, self.image_embed_dim ** 0.5)
 
         # whether to force an l2norm, similar to clipping denoised, when sampling
         self.sampling_clamp_l2norm = sampling_clamp_l2norm

setup.py

@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.0.106',
+  version = '0.0.107',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',

train_diffusion_prior.py

@@ -85,7 +85,6 @@ def train(image_embed_dim,
           clip,
           dp_condition_on_text_encodings,
           dp_timesteps,
-          dp_l2norm_output,
           dp_normformer,
           dp_cond_drop_prob,
           dpn_depth,
@@ -105,8 +104,7 @@ def train(image_embed_dim,
             depth = dpn_depth, 
             dim_head = dpn_dim_head, 
             heads = dpn_heads,
-            normformer = dp_normformer,
-            l2norm_output = dp_l2norm_output).to(device)
+            normformer = dp_normformer).to(device)
     
     # DiffusionPrior with text embeddings and image embeddings pre-computed
     diffusion_prior = DiffusionPrior( 
@@ -273,7 +271,6 @@ def main():
           args.clip,
           args.dp_condition_on_text_encodings,
           args.dp_timesteps,
-          args.dp_l2norm_output,
           args.dp_normformer,
           args.dp_cond_drop_prob,
           args.dpn_depth,