fix a bug with numerical stability in attention, sorry! 🐛

* add eval/train toggles

* train/eval flags

* shift train toggle

Co-authored-by: nousr <z@localhost.com>

README.md

@@ -902,7 +902,7 @@ Please note that the script internally passes text_embed and image_embed to the
 ### Usage 
 
 ```bash
-$ pyhon train_diffusion_prior.py
+$ python train_diffusion_prior.py
 ```
 
 The most significant parameters for the script are as follows:
@@ -927,7 +927,39 @@ The most significant parameters for the script are as follows:
 
 ### Sample wandb run log
 
-Please find a sample wandb run log at : https://wandb.ai/laion/diffusion-prior/runs/aul0rhv5?workspace=
+Please find a sample wandb run log at : https://wandb.ai/laion/diffusion-prior/runs/1blxu24j
+
+### Loading and saving the Diffusion Prior model
+
+Two methods are provided, load_diffusion_model and save_diffusion_model, the names being self-explanatory. 
+
+## from dalle2_pytorch import load_diffusion_model, save_diffusion_model
+
+    load_diffusion_model(dprior_path, device) 
+
+        dprior_path : path to saved model(.pth)
+    
+        device      : the cuda device you're running on
+    
+    save_diffusion_model(save_path, model, optimizer, scaler, config, image_embed_dim)
+    
+        save_path : path to save at
+    
+        model     : object of Diffusion_Prior
+    
+        optimizer : optimizer object - see train_diffusion_prior.py for how to create one. 
+    
+            e.g: optimizer = get_optimizer(diffusion_prior.net.parameters(), wd=weight_decay, lr=learning_rate)
+    
+        scaler    : a GradScaler object.
+    
+            e.g: scaler = GradScaler(enabled=amp)
+    
+        config    : config object created in train_diffusion_prior.py - see file for example. 
+    
+        image_embed_dim - the dimension of the image_embedding
+    
+            e.g: 768
 
 ## CLI (wip)
 
@@ -966,6 +998,7 @@ Once built, images will be saved to the same directory the command is invoked
 - [x] add convnext backbone for vqgan-vae (in addition to vit [vit-vqgan] + resnet)
 - [x] make sure DDPMs can be run with traditional resnet blocks (but leave convnext as an option for experimentation)
 - [x] make sure for the latter unets in the cascade, one can train on crops for learning super resolution (constrain the unet to be only convolutions in that case, or allow conv-like attention with rel pos bias)
+- [x] offer setting in diffusion prior to split time and image embeddings into multiple tokens, configurable, for more surface area during attention
 - [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet (test out unet² in ddpm repo) - consider https://github.com/lucidrains/uformer-pytorch attention-based unet
 - [ ] make sure the cascading ddpm in the repository can be trained unconditionally, offer a one-line CLI tool for training on a folder of images
 - [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs
@@ -981,6 +1014,7 @@ Once built, images will be saved to the same directory the command is invoked
 - [ ] make sure FILIP works with DALL-E2 from x-clip https://arxiv.org/abs/2111.07783
 - [ ] make sure resnet hyperparameters can be configurable across unet depth (groups and expansion factor)
 - [ ] offer save / load methods on the trainer classes to automatically take care of state dicts for scalers / optimizers / saving versions and checking for breaking changes
+- [ ] bring in skip-layer excitatons (from lightweight gan paper) to see if it helps for either decoder of unet or vqgan-vae training
 
 ## Citations
 

dalle2_pytorch/__init__.py

@@ -1,4 +1,4 @@
-from dalle2_pytorch.dalle2_pytorch import DALLE2, DiffusionPriorNetwork, DiffusionPrior, Unet, Decoder
+from dalle2_pytorch.dalle2_pytorch import DALLE2, DiffusionPriorNetwork, DiffusionPrior, Unet, Decoder,load_diffusion_model,save_diffusion_model
 from dalle2_pytorch.dalle2_pytorch import OpenAIClipAdapter
 from dalle2_pytorch.train import DecoderTrainer, DiffusionPriorTrainer
 

dalle2_pytorch/dalle2_pytorch.py

@@ -4,6 +4,8 @@ from inspect import isfunction
 from functools import partial
 from contextlib import contextmanager
 from collections import namedtuple
+from pathlib import Path
+import time
 
 import torch
 import torch.nn.functional as F
@@ -32,6 +34,42 @@ from rotary_embedding_torch import RotaryEmbedding
 from x_clip import CLIP
 from coca_pytorch import CoCa
 
+# Diffusion Prior model loading and saving functions
+
+def load_diffusion_model(dprior_path, device ):
+
+        dprior_path = Path(dprior_path)
+        assert dprior_path.exists(), 'Dprior model file does not exist'
+        loaded_obj = torch.load(str(dprior_path), map_location='cpu')
+
+        # Get hyperparameters of loaded model 
+        dpn_config = loaded_obj['hparams']['diffusion_prior_network']
+        dp_config = loaded_obj['hparams']['diffusion_prior']
+        image_embed_dim = loaded_obj['image_embed_dim']['image_embed_dim']
+
+        # Create DiffusionPriorNetwork and DiffusionPrior with loaded hyperparameters
+
+        # DiffusionPriorNetwork 
+        prior_network = DiffusionPriorNetwork( dim = image_embed_dim, **dpn_config).to(device)
+
+        # DiffusionPrior with text embeddings and image embeddings pre-computed
+        diffusion_prior = DiffusionPrior(net = prior_network, **dp_config, image_embed_dim = image_embed_dim).to(device)
+
+        # Load state dict from saved model
+        diffusion_prior.load_state_dict(loaded_obj['model'])
+
+        return diffusion_prior
+
+def save_diffusion_model(save_path, model, optimizer, scaler, config, image_embed_dim):
+    # Saving State Dict
+    print("====================================== Saving checkpoint ======================================")
+    state_dict = dict(model=model.state_dict(), 
+                      optimizer=optimizer.state_dict(), 
+                      scaler=scaler.state_dict(), 
+                      hparams = config, 
+                      image_embed_dim = {"image_embed_dim":image_embed_dim})
+    torch.save(state_dict, save_path+'/'+str(time.time())+'_saved_model.pth')
+
 # helper functions
 
 def exists(val):
@@ -264,7 +302,7 @@ class OpenAIClipAdapter(BaseClipAdapter):
         text_embed = self.clip.encode_text(text)
         text_encodings = self.text_encodings
         del self.text_encodings
-        return EmbeddedText(text_embed.float(), text_encodings.float(), text_mask)
+        return EmbeddedText(l2norm(text_embed.float()), text_encodings.float(), text_mask)
 
     @torch.no_grad()
     def embed_image(self, image):
@@ -272,7 +310,7 @@ class OpenAIClipAdapter(BaseClipAdapter):
         image = resize_image_to(image, self.image_size)
         image = self.clip_normalize(unnormalize_img(image))
         image_embed = self.clip.encode_image(image)
-        return EmbeddedImage(image_embed.float(), None)
+        return EmbeddedImage(l2norm(image_embed.float()), None)
 
 # classifier free guidance functions
 
@@ -639,7 +677,7 @@ class Attention(nn.Module):
 
         # attention
 
-        sim = sim - sim.amax(dim = -1, keepdim = True)
+        sim = sim - sim.amax(dim = -1, keepdim = True).detach()
         attn = sim.softmax(dim = -1)
         attn = self.dropout(attn)
 
@@ -703,10 +741,31 @@ class DiffusionPriorNetwork(nn.Module):
         self,
         dim,
         num_timesteps = None,
+        num_time_embeds = 1,
+        num_image_embeds = 1,
+        num_text_embeds = 1,
         **kwargs
     ):
         super().__init__()
-        self.time_embeddings = nn.Embedding(num_timesteps, dim) if exists(num_timesteps) else nn.Sequential(Rearrange('b -> b 1'), MLP(1, dim)) # also offer a continuous version of timestep embeddings, with a 2 layer MLP
+        self.num_time_embeds = num_time_embeds
+        self.num_image_embeds = num_image_embeds
+        self.num_text_embeds = num_text_embeds
+
+        self.to_text_embeds = nn.Sequential(
+            nn.Linear(dim, dim * num_text_embeds) if num_text_embeds > 1 else nn.Identity(),
+            Rearrange('b (n d) -> b n d', n = num_text_embeds)
+        )
+
+        self.to_time_embeds = nn.Sequential(
+            nn.Embedding(num_timesteps, dim * num_time_embeds) if exists(num_timesteps) else nn.Sequential(SinusoidalPosEmb(dim), MLP(dim, dim * num_time_embeds)), # also offer a continuous version of timestep embeddings, with a 2 layer MLP
+            Rearrange('b (n d) -> b n d', n = num_time_embeds)
+        )
+
+        self.to_image_embeds = nn.Sequential(
+            nn.Linear(dim, dim * num_image_embeds) if num_image_embeds > 1 else nn.Identity(),
+            Rearrange('b (n d) -> b n d', n = num_image_embeds)
+        )
+
         self.learned_query = nn.Parameter(torch.randn(dim))
         self.causal_transformer = CausalTransformer(dim = dim, **kwargs)
 
@@ -736,10 +795,13 @@ class DiffusionPriorNetwork(nn.Module):
     ):
         batch, dim, device, dtype = *image_embed.shape, image_embed.device, image_embed.dtype
 
+        num_time_embeds, num_image_embeds, num_text_embeds = self.num_time_embeds, self.num_image_embeds, self.num_text_embeds
+
         # in section 2.2, last paragraph
         # "... consisting of encoded text, CLIP text embedding, diffusion timestep embedding, noised CLIP image embedding, final embedding for prediction"
 
-        text_embed, image_embed = rearrange_many((text_embed, image_embed), 'b d -> b 1 d')
+        text_embed = self.to_text_embeds(text_embed)
+        image_embed = self.to_image_embeds(image_embed)
 
         # make text encodings optional
         # although the paper seems to suggest it is present <--
@@ -759,16 +821,17 @@ class DiffusionPriorNetwork(nn.Module):
 
         # whether text embedding is masked or not depends on the classifier free guidance conditional masking
 
+        keep_mask = repeat(keep_mask, 'b 1 -> b n', n = num_text_embeds)
         mask = torch.cat((mask, keep_mask), dim = 1)
 
         # whether text embedding is used for conditioning depends on whether text encodings are available for attention (for classifier free guidance, even though it seems from the paper it was not used in the prior ddpm, as the objective is different)
         # but let's just do it right
 
         if exists(mask):
-            mask = F.pad(mask, (0, 2), value = True) # extend mask for text embedding, noised image embedding, time step embedding, and learned query
+            attend_padding = 1 + num_time_embeds + num_image_embeds # 1 for learned queries + number of image embeds + time embeds
+            mask = F.pad(mask, (0, attend_padding), value = True) # extend mask for text embedding, noised image embedding, time step embedding, and learned query
 
-        time_embed = self.time_embeddings(diffusion_timesteps)
-        time_embed = rearrange(time_embed, 'b d -> b 1 d')
+        time_embed = self.to_time_embeds(diffusion_timesteps)
 
         learned_queries = repeat(self.learned_query, 'd -> b 1 d', b = batch)
 
@@ -776,6 +839,7 @@ class DiffusionPriorNetwork(nn.Module):
             text_encodings,
             text_embed,
             time_embed,
+            image_embed,
             learned_queries
         ), dim = -2)
 
@@ -799,13 +863,14 @@ class DiffusionPrior(BaseGaussianDiffusion):
         image_size = None,
         image_channels = 3,
         timesteps = 1000,
-        cond_drop_prob = 0.2,
+        cond_drop_prob = 0.,
         loss_type = "l1",
         predict_x_start = True,
         beta_schedule = "cosine",
         condition_on_text_encodings = True, # the paper suggests this is needed, but you can turn it off for your CLIP preprocessed text embed -> image embed training
         sampling_clamp_l2norm = False,
         training_clamp_l2norm = False,
+        init_image_embed_l2norm = False,
         image_embed_scale = None,           # this is for scaling the l2-normed image embedding, so it is more suitable for gaussian diffusion, as outlined by Katherine (@crowsonkb) https://github.com/lucidrains/DALLE2-pytorch/issues/60#issue-1226116132
         clip_adapter_overrides = dict()
     ):
@@ -844,6 +909,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
         # whether to force an l2norm, similar to clipping denoised, when sampling
         self.sampling_clamp_l2norm = sampling_clamp_l2norm
         self.training_clamp_l2norm = training_clamp_l2norm
+        self.init_image_embed_l2norm = init_image_embed_l2norm
 
     def p_mean_variance(self, x, t, text_cond, clip_denoised: bool):
         pred = self.net(x, t, **text_cond)
@@ -878,11 +944,16 @@ class DiffusionPrior(BaseGaussianDiffusion):
         device = self.betas.device
 
         b = shape[0]
-        img = torch.randn(shape, device=device)
+        image_embed = torch.randn(shape, device=device)
+
+        if self.init_image_embed_l2norm:
+            image_embed = l2norm(image_embed) * self.image_embed_scale
 
         for i in tqdm(reversed(range(0, self.num_timesteps)), desc='sampling loop time step', total=self.num_timesteps):
-            img = self.p_sample(img, torch.full((b,), i, device = device, dtype = torch.long), text_cond = text_cond)
-        return img
+            times = torch.full((b,), i, device = device, dtype = torch.long)
+            image_embed = self.p_sample(image_embed, times, text_cond = text_cond)
+
+        return image_embed
 
     def p_losses(self, image_embed, times, text_cond, noise = None):
         noise = default(noise, lambda: torch.randn_like(image_embed))
@@ -1133,7 +1204,7 @@ class CrossAttention(nn.Module):
             mask = rearrange(mask, 'b j -> b 1 1 j')
             sim = sim.masked_fill(~mask, max_neg_value)
 
-        sim = sim - sim.amax(dim = -1, keepdim = True)
+        sim = sim - sim.amax(dim = -1, keepdim = True).detach()
         attn = sim.softmax(dim = -1)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
@@ -1889,3 +1960,4 @@ class DALLE2(nn.Module):
             return images[0]
 
         return images
+

dalle2_pytorch/train_vqgan_vae.py

@@ -3,14 +3,15 @@ import copy
 from random import choice
 from pathlib import Path
 from shutil import rmtree
+from PIL import Image
 
 import torch
 from torch import nn
-
-from PIL import Image
-from torchvision.datasets import ImageFolder
-import torchvision.transforms as T
+from torch.cuda.amp import autocast, GradScaler
 from torch.utils.data import Dataset, DataLoader, random_split
+
+import torchvision.transforms as T
+from torchvision.datasets import ImageFolder
 from torchvision.utils import make_grid, save_image
 
 from einops import rearrange
@@ -99,6 +100,7 @@ class VQGanVAETrainer(nn.Module):
         ema_update_after_step = 2000,
         ema_update_every = 10,
         apply_grad_penalty_every = 4,
+        amp = False
     ):
         super().__init__()
         assert isinstance(vae, VQGanVAE), 'vae must be instance of VQGanVAE'
@@ -120,6 +122,10 @@ class VQGanVAETrainer(nn.Module):
         self.optim = get_optimizer(vae_parameters, lr = lr, wd = wd)
         self.discr_optim = get_optimizer(discr_parameters, lr = lr, wd = wd)
 
+        self.amp = amp
+        self.scaler = GradScaler(enabled = amp)
+        self.discr_scaler = GradScaler(enabled = amp)
+
         # create dataset
 
         self.ds = ImageDataset(folder, image_size = image_size)
@@ -178,20 +184,22 @@ class VQGanVAETrainer(nn.Module):
             img = next(self.dl)
             img = img.to(device)
 
-            loss = self.vae(
-                img,
-                return_loss = True,
-                apply_grad_penalty = apply_grad_penalty
-            )
+            with autocast(enabled = self.amp):
+                loss = self.vae(
+                    img,
+                    return_loss = True,
+                    apply_grad_penalty = apply_grad_penalty
+                )
+
+
+                self.scaler.scale(loss / self.grad_accum_every).backward()
 
             accum_log(logs, {'loss': loss.item() / self.grad_accum_every})
 
-            (loss / self.grad_accum_every).backward()
-
-        self.optim.step()
+        self.scaler.step(self.optim)
+        self.scaler.update()
         self.optim.zero_grad()
 
-
         # update discriminator
 
         if exists(self.vae.discr):
@@ -200,12 +208,15 @@ class VQGanVAETrainer(nn.Module):
                 img = next(self.dl)
                 img = img.to(device)
 
-                loss = self.vae(img, return_discr_loss = True)
+                with autocast(enabled = self.amp):
+                    loss = self.vae(img, return_discr_loss = True)
+
+                    self.discr_scaler.scale(loss / self.grad_accum_every).backward()
+
                 accum_log(logs, {'discr_loss': loss.item() / self.grad_accum_every})
 
-                (loss / self.grad_accum_every).backward()
-
-            self.discr_optim.step()
+            self.discr_scaler.step(self.discr_optim)
+            self.discr_scaler.update()
             self.discr_optim.zero_grad()
 
             # log

setup.py

@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.1.2',
+  version = '0.2.2',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',

train_diffusion_prior.py

@@ -6,7 +6,7 @@ import numpy as np
 import torch
 from torch import nn
 from embedding_reader import EmbeddingReader
-from dalle2_pytorch import DiffusionPrior, DiffusionPriorNetwork
+from dalle2_pytorch import DiffusionPrior, DiffusionPriorNetwork, load_diffusion_model, save_diffusion_model
 from dalle2_pytorch.optimizer import get_optimizer
 from torch.cuda.amp import autocast,GradScaler
 
@@ -41,37 +41,56 @@ def eval_model(model,device,image_reader,text_reader,start,end,batch_size,loss_t
         avg_loss = (total_loss / total_samples)
         wandb.log({f'{phase} {loss_type}': avg_loss})
 
-def save_model(save_path, state_dict):
-    # Saving State Dict
-    print("====================================== Saving checkpoint ======================================")
-    torch.save(state_dict, save_path+'/'+str(time.time())+'_saved_model.pth')
+def report_cosine_sims(diffusion_prior,image_reader,text_reader,train_set_size,NUM_TEST_EMBEDDINGS,device):
+    diffusion_prior.eval()
 
-def report_cosine_sims(diffusion_prior,image_reader,text_reader,train_set_size,val_set_size,NUM_TEST_EMBEDDINGS,device):
     cos = nn.CosineSimilarity(dim=1, eps=1e-6)
 
-    tstart = train_set_size+val_set_size
-    tend = train_set_size+val_set_size+NUM_TEST_EMBEDDINGS
-
-    for embt, embi in zip(text_reader(batch_size = NUM_TEST_EMBEDDINGS, start=tstart, end = tend),image_reader(batch_size = NUM_TEST_EMBEDDINGS, start=tstart, end = tend)):
-        text_embed = torch.tensor(embt[0]).to(device)
-        text_embed = text_embed /  text_embed.norm(dim=1, keepdim=True)
-        test_text_cond = dict(text_embed = text_embed)
-
-        test_image_embeddings = torch.tensor(embi[0]).to(device)
-        test_image_embeddings = test_image_embeddings /  test_image_embeddings.norm(dim=1, keepdim=True)
-
-        predicted_image_embeddings = diffusion_prior.p_sample_loop((NUM_TEST_EMBEDDINGS, 768), text_cond = test_text_cond)
-        predicted_image_embeddings = predicted_image_embeddings / predicted_image_embeddings.norm(dim=1, keepdim=True)
-
-        original_similarity = cos(text_embed,test_image_embeddings).cpu().numpy()
-        predicted_similarity = cos(text_embed,predicted_image_embeddings).cpu().numpy()
-
-        wandb.log({"CosineSimilarity(text_embed,image_embed)": np.mean(original_similarity)})
-        wandb.log({"CosineSimilarity(text_embed,predicted_image_embed)":np.mean(predicted_similarity)})
-
-    return np.mean(predicted_similarity - original_similarity)
-
+    tstart = train_set_size
+    tend = train_set_size+NUM_TEST_EMBEDDINGS
 
+    for embt, embi in zip(text_reader(batch_size=NUM_TEST_EMBEDDINGS, start=tstart, end=tend), 
+            image_reader(batch_size=NUM_TEST_EMBEDDINGS, start=tstart, end=tend)):
+       # make a copy of the text embeddings for shuffling
+       text_embed = torch.tensor(embt[0]).to(device)
+       text_embed_shuffled = text_embed.clone()
+        # roll the text embeddings to simulate "unrelated" captions
+       rolled_idx = torch.roll(torch.arange(NUM_TEST_EMBEDDINGS), 1)
+       text_embed_shuffled = text_embed_shuffled[rolled_idx]
+       text_embed_shuffled = text_embed_shuffled / \
+           text_embed_shuffled.norm(dim=1, keepdim=True)
+       test_text_shuffled_cond = dict(text_embed=text_embed_shuffled)
+        # prepare the text embedding
+       text_embed = text_embed / text_embed.norm(dim=1, keepdim=True)
+       test_text_cond = dict(text_embed=text_embed)
+        # prepare image embeddings
+       test_image_embeddings = torch.tensor(embi[0]).to(device)
+       test_image_embeddings = test_image_embeddings / \
+           test_image_embeddings.norm(dim=1, keepdim=True)
+        # predict on the unshuffled text embeddings
+       predicted_image_embeddings = diffusion_prior.p_sample_loop(
+           (NUM_TEST_EMBEDDINGS, 768), text_cond=test_text_cond)
+       predicted_image_embeddings = predicted_image_embeddings / \
+           predicted_image_embeddings.norm(dim=1, keepdim=True)
+        # predict on the shuffled embeddings
+       predicted_unrelated_embeddings = diffusion_prior.p_sample_loop(
+           (NUM_TEST_EMBEDDINGS, 768), text_cond=test_text_shuffled_cond)
+       predicted_unrelated_embeddings = predicted_unrelated_embeddings / \
+           predicted_unrelated_embeddings.norm(dim=1, keepdim=True)
+        # calculate similarities
+       original_similarity = cos(
+           text_embed, test_image_embeddings).cpu().numpy()
+       predicted_similarity = cos(
+           text_embed, predicted_image_embeddings).cpu().numpy()
+       unrelated_similarity = cos(
+           text_embed, predicted_unrelated_embeddings).cpu().numpy()
+       predicted_img_similarity = cos(
+           test_image_embeddings, predicted_image_embeddings).cpu().numpy()
+       wandb.log({"CosineSimilarity(text_embed,image_embed)": np.mean(original_similarity),
+            "CosineSimilarity(text_embed,predicted_image_embed)":np.mean(predicted_similarity),
+            "CosineSimilarity(orig_image_embed,predicted_image_embed)":np.mean(predicted_img_similarity),
+            "CosineSimilarity(text_embed,predicted_unrelated_embed)": np.mean(unrelated_similarity),
+            "Cosine similarity difference":np.mean(predicted_similarity - original_similarity)})
 
 def train(image_embed_dim,
           image_embed_url,
@@ -93,9 +112,15 @@ def train(image_embed_dim,
           save_interval,
           save_path,
           device,
+          RESUME,
+          DPRIOR_PATH,
+          config,
+          wandb_entity,
+          wandb_project,
           learning_rate=0.001,
           max_grad_norm=0.5,
           weight_decay=0.01,
+          dropout=0.05,
           amp=False):
 
     # DiffusionPriorNetwork 
@@ -104,6 +129,8 @@ def train(image_embed_dim,
             depth = dpn_depth, 
             dim_head = dpn_dim_head, 
             heads = dpn_heads,
+            attn_dropout = dropout,
+            ff_dropout = dropout,
             normformer = dp_normformer).to(device)
     
     # DiffusionPrior with text embeddings and image embeddings pre-computed
@@ -116,16 +143,21 @@ def train(image_embed_dim,
             loss_type = dp_loss_type, 
             condition_on_text_encodings = dp_condition_on_text_encodings).to(device)
 
+    # Load pre-trained model from DPRIOR_PATH
+    if RESUME:
+        diffusion_prior=load_diffusion_model(DPRIOR_PATH,device)   
+        wandb.init( entity=wandb_entity, project=wandb_project, config=config) 
+
+    # Create save_path if it doesn't exist
+    if not os.path.exists(save_path):
+        os.makedirs(save_path)
+
     # Get image and text embeddings from the servers
     print("==============Downloading embeddings - image and text====================")
     image_reader = EmbeddingReader(embeddings_folder=image_embed_url, file_format="npy")
     text_reader  = EmbeddingReader(embeddings_folder=text_embed_url, file_format="npy")
     num_data_points = text_reader.count
 
-    # Create save_path if it doesn't exist
-    if not os.path.exists(save_path):
-        os.makedirs(save_path)
-
     ### Training code ###
     scaler = GradScaler(enabled=amp)
     optimizer = get_optimizer(diffusion_prior.net.parameters(), wd=weight_decay, lr=learning_rate)
@@ -136,12 +168,15 @@ def train(image_embed_dim,
 
     train_set_size = int(train_percent*num_data_points)
     val_set_size = int(val_percent*num_data_points)
+    eval_start = train_set_size
 
     for _ in range(epochs):
-        diffusion_prior.train()
 
         for emb_images,emb_text in zip(image_reader(batch_size=batch_size, start=0, end=train_set_size),
                 text_reader(batch_size=batch_size, start=0, end=train_set_size)):
+
+            diffusion_prior.train()
+            
             emb_images_tensor = torch.tensor(emb_images[0]).to(device)
             emb_text_tensor = torch.tensor(emb_text[0]).to(device)
 
@@ -156,9 +191,13 @@ def train(image_embed_dim,
             if(int(time.time()-t) >= 60*save_interval):
                 t = time.time()
 
-                save_model(
+                save_diffusion_model(
                     save_path,
-                    dict(model=diffusion_prior.state_dict(), optimizer=optimizer.state_dict(), scaler=scaler.state_dict()))
+                    diffusion_prior,
+                    optimizer,
+                    scaler,
+                    config,
+                    image_embed_dim)
 
             # Log to wandb
             wandb.log({"Training loss": loss.item(),
@@ -168,14 +207,22 @@ def train(image_embed_dim,
             # Use NUM_TEST_EMBEDDINGS samples from the test set each time
             # Get embeddings from the most recently saved model
             if(step % REPORT_METRICS_EVERY) == 0:
-                diff_cosine_sim = report_cosine_sims(diffusion_prior,
+                report_cosine_sims(diffusion_prior,
                         image_reader,
                         text_reader,
                         train_set_size,
-                        val_set_size,
                         NUM_TEST_EMBEDDINGS,
                         device)
-                wandb.log({"Cosine similarity difference": diff_cosine_sim})
+                ### Evaluate model(validation run) ###
+                eval_model(diffusion_prior,
+                        device,
+                        image_reader,
+                        text_reader,
+                        eval_start,
+                        eval_start+NUM_TEST_EMBEDDINGS,
+                        NUM_TEST_EMBEDDINGS,
+                        dp_loss_type,
+                        phase="Validation")
 
             scaler.unscale_(optimizer)
             nn.utils.clip_grad_norm_(diffusion_prior.parameters(), max_grad_norm)
@@ -184,11 +231,6 @@ def train(image_embed_dim,
             scaler.update()
             optimizer.zero_grad()
 
-        ### Evaluate model(validation run) ###
-        start = train_set_size
-        end=start+val_set_size
-        eval_model(diffusion_prior,device,image_reader,text_reader,start,end,batch_size,dp_loss_type,phase="Validation")
-
     ### Test run ###
     test_set_size = int(test_percent*train_set_size) 
     start=train_set_size+val_set_size
@@ -200,7 +242,6 @@ def main():
     # Logging
     parser.add_argument("--wandb-entity", type=str, default="laion")
     parser.add_argument("--wandb-project", type=str, default="diffusion-prior")
-    parser.add_argument("--wandb-name", type=str, default="laion-dprior")
     parser.add_argument("--wandb-dataset", type=str, default="LAION-5B")
     parser.add_argument("--wandb-arch", type=str, default="DiffusionPrior")
     # URLs for embeddings 
@@ -209,6 +250,7 @@ def main():
     # Hyperparameters
     parser.add_argument("--learning-rate", type=float, default=1.1e-4)
     parser.add_argument("--weight-decay", type=float, default=6.02e-2)
+    parser.add_argument("--dropout", type=float, default=5e-2)
     parser.add_argument("--max-grad-norm", type=float, default=0.5)
     parser.add_argument("--batch-size", type=int, default=10**4)
     parser.add_argument("--num-epochs", type=int, default=5)
@@ -226,7 +268,6 @@ def main():
     # DiffusionPrior(dp) parameters
     parser.add_argument("--dp-condition-on-text-encodings", type=bool, default=False)
     parser.add_argument("--dp-timesteps", type=int, default=100)
-    parser.add_argument("--dp-l2norm-output", type=bool, default=False)
     parser.add_argument("--dp-normformer", type=bool, default=False)
     parser.add_argument("--dp-cond-drop-prob", type=float, default=0.1)
     parser.add_argument("--dp-loss-type", type=str, default="l2")
@@ -235,22 +276,40 @@ def main():
     # Model checkpointing interval(minutes)
     parser.add_argument("--save-interval", type=int, default=30)
     parser.add_argument("--save-path", type=str, default="./diffusion_prior_checkpoints")
+    # Saved model path 
+    parser.add_argument("--pretrained-model-path", type=str, default=None)
 
     args = parser.parse_args()
 
-    print("Setting up wandb logging... Please wait...")
+    config = ({"learning_rate": args.learning_rate,
+        "architecture": args.wandb_arch,
+        "dataset": args.wandb_dataset,
+        "weight_decay":args.weight_decay,
+        "max_gradient_clipping_norm":args.max_grad_norm,
+        "batch_size":args.batch_size,
+        "epochs": args.num_epochs,
+        "diffusion_prior_network":{"depth":args.dpn_depth,
+        "dim_head":args.dpn_dim_head,
+        "heads":args.dpn_heads,
+        "normformer":args.dp_normformer},
+        "diffusion_prior":{"condition_on_text_encodings": args.dp_condition_on_text_encodings,
+        "timesteps": args.dp_timesteps,
+        "cond_drop_prob":args.dp_cond_drop_prob,
+        "loss_type":args.dp_loss_type,
+        "clip":args.clip}
+        })
 
-    wandb.init(
-      entity=args.wandb_entity,
-      project=args.wandb_project,
-      config={
-      "learning_rate": args.learning_rate,
-      "architecture": args.wandb_arch,
-      "dataset": args.wandb_dataset,
-      "epochs": args.num_epochs,
-      })
+    RESUME = False
+    # Check if DPRIOR_PATH exists(saved model path)
+    DPRIOR_PATH = args.pretrained_model_path
+    if(DPRIOR_PATH is not None):
+        RESUME = True
+    else:
+        wandb.init(
+          entity=args.wandb_entity,
+          project=args.wandb_project,
+          config=config)
 
-    print("wandb logging setup done!")
     # Obtain the utilized device.
 
     has_cuda = torch.cuda.is_available()
@@ -279,9 +338,15 @@ def main():
           args.save_interval,
           args.save_path,
           device,
+          RESUME,
+          DPRIOR_PATH,
+          config,
+          atgs.wandb_entity,
+          args.wandb_project,
           args.learning_rate,
           args.max_grad_norm,
           args.weight_decay,
+          args.dropout,
           args.amp)
 
 if __name__ == "__main__":