Merge pull request #1 from ModeratePrawn/ModeratePrawn-patch-1

Add files via upload

ldm/models/diffusion/ddim.py

@@ -18,7 +18,7 @@ class DDIMSampler(object):
 
     def register_buffer(self, name, attr):
         if type(attr) == torch.Tensor:
-            if attr.device != torch.device("cuda"):
+            if attr.device != torch.device("cuda") and torch.cuda.is_available():
                 attr = attr.to(torch.device("cuda"))
         setattr(self, name, attr)
 
@@ -238,4 +238,4 @@ class DDIMSampler(object):
             x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps,
                                           unconditional_guidance_scale=unconditional_guidance_scale,
                                           unconditional_conditioning=unconditional_conditioning)
-        return x_dec
+        return x_dec

ldm/models/diffusion/plms.py

@@ -17,7 +17,7 @@ class PLMSSampler(object):
 
     def register_buffer(self, name, attr):
         if type(attr) == torch.Tensor:
-            if attr.device != torch.device("cuda"):
+            if attr.device != torch.device("cuda") and torch.cuda.is_available():
                 attr = attr.to(torch.device("cuda"))
         setattr(self, name, attr)
 

ldm/modules/encoders/modules.py

@@ -35,7 +35,7 @@ class ClassEmbedder(nn.Module):
 
 class TransformerEmbedder(AbstractEncoder):
     """Some transformer encoder layers"""
-    def __init__(self, n_embed, n_layer, vocab_size, max_seq_len=77, device="cuda"):
+    def __init__(self, n_embed, n_layer, vocab_size, max_seq_len=77, device="cuda" if torch.cuda.is_available() else "cpu"):
         super().__init__()
         self.device = device
         self.transformer = TransformerWrapper(num_tokens=vocab_size, max_seq_len=max_seq_len,
@@ -52,7 +52,7 @@ class TransformerEmbedder(AbstractEncoder):
 
 class BERTTokenizer(AbstractEncoder):
     """ Uses a pretrained BERT tokenizer by huggingface. Vocab size: 30522 (?)"""
-    def __init__(self, device="cuda", vq_interface=True, max_length=77):
+    def __init__(self, device="cuda" if torch.cuda.is_available() else "cpu", vq_interface=True, max_length=77):
         super().__init__()
         from transformers import BertTokenizerFast  # TODO: add to reuquirements
         self.tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
@@ -80,7 +80,7 @@ class BERTTokenizer(AbstractEncoder):
 class BERTEmbedder(AbstractEncoder):
     """Uses the BERT tokenizr model and add some transformer encoder layers"""
     def __init__(self, n_embed, n_layer, vocab_size=30522, max_seq_len=77,
-                 device="cuda",use_tokenizer=True, embedding_dropout=0.0):
+                 device="cuda" if torch.cuda.is_available() else "cpu", use_tokenizer=True, embedding_dropout=0.0):
         super().__init__()
         self.use_tknz_fn = use_tokenizer
         if self.use_tknz_fn:
@@ -136,7 +136,7 @@ class SpatialRescaler(nn.Module):
 
 class FrozenCLIPEmbedder(AbstractEncoder):
     """Uses the CLIP transformer encoder for text (from Hugging Face)"""
-    def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77):
+    def __init__(self, version="openai/clip-vit-large-patch14", device="cuda" if torch.cuda.is_available() else "cpu", max_length=77):
         super().__init__()
         self.tokenizer = CLIPTokenizer.from_pretrained(version)
         self.transformer = CLIPTextModel.from_pretrained(version)
@@ -231,4 +231,4 @@ class FrozenClipImageEmbedder(nn.Module):
 if __name__ == "__main__":
     from ldm.util import count_params
     model = FrozenCLIPEmbedder()
-    count_params(model, verbose=True)
+    count_params(model, verbose=True)

notebook_helpers.py

@@ -44,7 +44,8 @@ def load_model_from_config(config, ckpt):
     sd = pl_sd["state_dict"]
     model = instantiate_from_config(config.model)
     m, u = model.load_state_dict(sd, strict=False)
-    model.cuda()
+    if torch.cuda.is_available():
+        model.cuda()
     model.eval()
     return {"model": model}, global_step
 
@@ -117,7 +118,8 @@ def get_cond(mode, selected_path):
         c = rearrange(c, '1 c h w -> 1 h w c')
         c = 2. * c - 1.
 
-        c = c.to(torch.device("cuda"))
+        if torch.cuda.is_available():
+             c = c.to(torch.device("cuda"))
         example["LR_image"] = c
         example["image"] = c_up
 
@@ -267,4 +269,4 @@ def make_convolutional_sample(batch, model, mode="vanilla", custom_steps=None, e
     log["sample"] = x_sample
     log["time"] = t1 - t0
 
-    return log
+    return log

scripts/knn2img.py

@@ -53,7 +53,8 @@ def load_model_from_config(config, ckpt, verbose=False):
         print("unexpected keys:")
         print(u)
 
-    model.cuda()
+    if torch.cuda.is_available():
+        model.cuda()
     model.eval()
     return model
 
@@ -358,7 +359,10 @@ if __name__ == "__main__":
                     uc = None
                     if searcher is not None:
                         nn_dict = searcher(c, opt.knn)
-                        c = torch.cat([c, torch.from_numpy(nn_dict['nn_embeddings']).cuda()], dim=1)
+                        nn_embeddings = torch.from_numpy(nn_dict['nn_embeddings'])
+                        if torch.cuda.is_available():
+                            nn_embeddings = nn_embeddings.cuda()
+                        c = torch.cat([c, nn_embeddings], dim=1)
                     if opt.scale != 1.0:
                         uc = torch.zeros_like(c)
                     if isinstance(prompts, tuple):

scripts/sample_diffusion.py

@@ -220,7 +220,8 @@ def get_parser():
 def load_model_from_config(config, sd):
     model = instantiate_from_config(config)
     model.load_state_dict(sd,strict=False)
-    model.cuda()
+    if torch.cuda.is_available():
+        model.cuda()
     model.eval()
     return model
 

scripts/txt2img.py

@@ -60,7 +60,8 @@ def load_model_from_config(config, ckpt, verbose=False):
         print("unexpected keys:")
         print(u)
 
-    model.cuda()
+    if torch.cuda.is_available():
+        model.cuda()
     model.eval()
     return model