align the ema model device back after sampling from the cascading ddpm in the decoder

The default config for clip from openai should be ViT-B/32

README.md

@@ -508,7 +508,7 @@ To use a pretrained OpenAI CLIP, simply import `OpenAIClipAdapter` and pass it i
 import torch
 from dalle2_pytorch import DALLE2, DiffusionPriorNetwork, DiffusionPrior, Unet, Decoder, OpenAIClipAdapter
 
-# openai pretrained clip - defaults to ViT/B-32
+# openai pretrained clip - defaults to ViT-B/32
 
 clip = OpenAIClipAdapter()
 
@@ -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.train 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)
 
@@ -967,22 +999,24 @@ Once built, images will be saved to the same directory the command is invoked
 - [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
+- [x] make sure resnet hyperparameters can be configurable across unet depth (groups and expansion factor)
+- [x] pull logic for training diffusion prior into a class DiffusionPriorTrainer, for eventual script based + CLI based training
+- [x] 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
+- [x] bring in cross-scale embedding from iclr paper https://github.com/lucidrains/vit-pytorch/blob/main/vit_pytorch/crossformer.py#L14
+- [x] cross embed layers for downsampling, as an option
 - [ ] 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
-- [ ] pull logic for training diffusion prior into a class DiffusionPriorTrainer, for eventual script based + CLI based training
 - [ ] train on a toy task, offer in colab
 - [ ] think about how best to design a declarative training config that handles preencoding for prior and training of multiple networks in decoder
 - [ ] extend diffusion head to use diffusion-gan (potentially using lightweight-gan) to speed up inference
-- [ ] bring in cross-scale embedding from iclr paper https://github.com/lucidrains/vit-pytorch/blob/main/vit_pytorch/crossformer.py#L14
 - [ ] figure out if possible to augment with external memory, as described in https://arxiv.org/abs/2204.11824
 - [ ] test out grid attention in cascading ddpm locally, decide whether to keep or remove
 - [ ] use an experimental tracker agnostic setup, as done <a href="https://github.com/lucidrains/tf-bind-transformer#simple-trainer-class-for-fine-tuning">here</a>
 - [ ] interface out the vqgan-vae so a pretrained one can be pulled off the shelf to validate latent diffusion + DALL-E2
 - [ ] 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
+- [ ] decoder needs one day worth of refactor for tech debt
 
 ## Citations
 
@@ -1060,4 +1094,15 @@ Once built, images will be saved to the same directory the command is invoked
 }
 ```
 
+```bibtex
+@misc{wang2021crossformer,
+    title   = {CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention},
+    author  = {Wenxiao Wang and Lu Yao and Long Chen and Binbin Lin and Deng Cai and Xiaofei He and Wei Liu},
+    year    = {2021},
+    eprint  = {2108.00154},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 *Creating noise from data is easy; creating data from noise is generative modeling.* - <a href="https://arxiv.org/abs/2011.13456">Yang Song's paper</a>

dalle2_pytorch/dalle2_pytorch.py

@@ -4,6 +4,7 @@ from inspect import isfunction
 from functools import partial
 from contextlib import contextmanager
 from collections import namedtuple
+from pathlib import Path
 
 import torch
 import torch.nn.functional as F
@@ -302,7 +303,7 @@ def cosine_beta_schedule(timesteps, s = 0.008):
     as proposed in https://openreview.net/forum?id=-NEXDKk8gZ
     """
     steps = timesteps + 1
-    x = torch.linspace(0, timesteps, steps)
+    x = torch.linspace(0, timesteps, steps, dtype = torch.float64)
     alphas_cumprod = torch.cos(((x / timesteps) + s) / (1 + s) * torch.pi * 0.5) ** 2
     alphas_cumprod = alphas_cumprod / alphas_cumprod[0]
     betas = 1 - (alphas_cumprod[1:] / alphas_cumprod[:-1])
@@ -313,21 +314,21 @@ def linear_beta_schedule(timesteps):
     scale = 1000 / timesteps
     beta_start = scale * 0.0001
     beta_end = scale * 0.02
-    return torch.linspace(beta_start, beta_end, timesteps)
+    return torch.linspace(beta_start, beta_end, timesteps, dtype = torch.float64)
 
 
 def quadratic_beta_schedule(timesteps):
     scale = 1000 / timesteps
     beta_start = scale * 0.0001
     beta_end = scale * 0.02
-    return torch.linspace(beta_start**2, beta_end**2, timesteps) ** 2
+    return torch.linspace(beta_start**2, beta_end**2, timesteps, dtype = torch.float64) ** 2
 
 
 def sigmoid_beta_schedule(timesteps):
     scale = 1000 / timesteps
     beta_start = scale * 0.0001
     beta_end = scale * 0.02
-    betas = torch.linspace(-6, 6, timesteps)
+    betas = torch.linspace(-6, 6, timesteps, dtype = torch.float64)
     return torch.sigmoid(betas) * (beta_end - beta_start) + beta_start
 
 
@@ -367,17 +368,21 @@ class BaseGaussianDiffusion(nn.Module):
         self.loss_type = loss_type
         self.loss_fn = loss_fn
 
-        self.register_buffer('betas', betas)
-        self.register_buffer('alphas_cumprod', alphas_cumprod)
-        self.register_buffer('alphas_cumprod_prev', alphas_cumprod_prev)
+        # register buffer helper function to cast double back to float
+
+        register_buffer = lambda name, val: self.register_buffer(name, val.to(torch.float32))
+
+        register_buffer('betas', betas)
+        register_buffer('alphas_cumprod', alphas_cumprod)
+        register_buffer('alphas_cumprod_prev', alphas_cumprod_prev)
 
         # calculations for diffusion q(x_t | x_{t-1}) and others
 
-        self.register_buffer('sqrt_alphas_cumprod', torch.sqrt(alphas_cumprod))
-        self.register_buffer('sqrt_one_minus_alphas_cumprod', torch.sqrt(1. - alphas_cumprod))
-        self.register_buffer('log_one_minus_alphas_cumprod', torch.log(1. - alphas_cumprod))
-        self.register_buffer('sqrt_recip_alphas_cumprod', torch.sqrt(1. / alphas_cumprod))
-        self.register_buffer('sqrt_recipm1_alphas_cumprod', torch.sqrt(1. / alphas_cumprod - 1))
+        register_buffer('sqrt_alphas_cumprod', torch.sqrt(alphas_cumprod))
+        register_buffer('sqrt_one_minus_alphas_cumprod', torch.sqrt(1. - alphas_cumprod))
+        register_buffer('log_one_minus_alphas_cumprod', torch.log(1. - alphas_cumprod))
+        register_buffer('sqrt_recip_alphas_cumprod', torch.sqrt(1. / alphas_cumprod))
+        register_buffer('sqrt_recipm1_alphas_cumprod', torch.sqrt(1. / alphas_cumprod - 1))
 
         # calculations for posterior q(x_{t-1} | x_t, x_0)
 
@@ -385,13 +390,13 @@ class BaseGaussianDiffusion(nn.Module):
 
         # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
 
-        self.register_buffer('posterior_variance', posterior_variance)
+        register_buffer('posterior_variance', posterior_variance)
 
         # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
 
-        self.register_buffer('posterior_log_variance_clipped', torch.log(posterior_variance.clamp(min =1e-20)))
-        self.register_buffer('posterior_mean_coef1', betas * torch.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod))
-        self.register_buffer('posterior_mean_coef2', (1. - alphas_cumprod_prev) * torch.sqrt(alphas) / (1. - alphas_cumprod))
+        register_buffer('posterior_log_variance_clipped', torch.log(posterior_variance.clamp(min =1e-20)))
+        register_buffer('posterior_mean_coef1', betas * torch.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod))
+        register_buffer('posterior_mean_coef2', (1. - alphas_cumprod_prev) * torch.sqrt(alphas) / (1. - alphas_cumprod))
 
     def q_mean_variance(self, x_start, t):
         mean = extract(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start
@@ -639,7 +644,7 @@ 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)
 
@@ -705,11 +710,18 @@ class DiffusionPriorNetwork(nn.Module):
         num_timesteps = None,
         num_time_embeds = 1,
         num_image_embeds = 1,
+        num_text_embeds = 1,
         **kwargs
     ):
         super().__init__()
         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
@@ -717,7 +729,7 @@ class DiffusionPriorNetwork(nn.Module):
         )
 
         self.to_image_embeds = nn.Sequential(
-            nn.Linear(dim, dim * num_image_embeds),
+            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)
         )
 
@@ -750,12 +762,12 @@ class DiffusionPriorNetwork(nn.Module):
     ):
         batch, dim, device, dtype = *image_embed.shape, image_embed.device, image_embed.dtype
 
-        num_time_embeds, num_image_embeds = self.num_time_embeds, self.num_image_embeds
+        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 = rearrange(text_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
@@ -776,6 +788,7 @@ 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)
@@ -818,7 +831,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
         image_channels = 3,
         timesteps = 1000,
         cond_drop_prob = 0.,
-        loss_type = "l1",
+        loss_type = "l2",
         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
@@ -1158,7 +1171,7 @@ 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)
@@ -1219,6 +1232,33 @@ class LinearAttention(nn.Module):
         out = self.nonlin(out)
         return self.to_out(out)
 
+class CrossEmbedLayer(nn.Module):
+    def __init__(
+        self,
+        dim_in,
+        kernel_sizes,
+        dim_out = None,
+        stride = 2
+    ):
+        super().__init__()
+        assert all([*map(lambda t: (t % 2) == (stride % 2), kernel_sizes)])
+        dim_out = default(dim_out, dim_in)
+
+        kernel_sizes = sorted(kernel_sizes)
+        num_scales = len(kernel_sizes)
+
+        # calculate the dimension at each scale
+        dim_scales = [int(dim_out / (2 ** i)) for i in range(1, num_scales)]
+        dim_scales = [*dim_scales, dim_out - sum(dim_scales)]
+
+        self.convs = nn.ModuleList([])
+        for kernel, dim_scale in zip(kernel_sizes, dim_scales):
+            self.convs.append(nn.Conv2d(dim_in, dim_scale, kernel, stride = stride, padding = (kernel - stride) // 2))
+
+    def forward(self, x):
+        fmaps = tuple(map(lambda conv: conv(x), self.convs))
+        return torch.cat(fmaps, dim = 1)
+
 class Unet(nn.Module):
     def __init__(
         self,
@@ -1242,8 +1282,10 @@ class Unet(nn.Module):
         cond_on_image_embeds = False,
         init_dim = None,
         init_conv_kernel_size = 7,
-        block_type = 'resnet',
-        block_resnet_groups = 8,
+        resnet_groups = 8,
+        init_cross_embed_kernel_sizes = (3, 7, 15),
+        cross_embed_downsample = False,
+        cross_embed_downsample_kernel_sizes = (2, 4),
         **kwargs
     ):
         super().__init__()
@@ -1262,10 +1304,9 @@ class Unet(nn.Module):
         self.channels = channels
 
         init_channels = channels if not lowres_cond else channels * 2 # in cascading diffusion, one concats the low resolution image, blurred, for conditioning the higher resolution synthesis
-        init_dim = default(init_dim, dim // 2)
+        init_dim = default(init_dim, dim // 3 * 2)
 
-        assert (init_conv_kernel_size % 2) == 1
-        self.init_conv = nn.Conv2d(init_channels, init_dim, init_conv_kernel_size, padding = init_conv_kernel_size // 2)
+        self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1)
 
         dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
         in_out = list(zip(dims[:-1], dims[1:]))
@@ -1321,7 +1362,15 @@ class Unet(nn.Module):
 
         # resnet block klass
 
-        block_klass = partial(ResnetBlock, groups = block_resnet_groups)
+        resnet_groups = cast_tuple(resnet_groups, len(in_out))
+
+        assert len(resnet_groups) == len(in_out)
+
+        # downsample klass
+
+        downsample_klass = Downsample
+        if cross_embed_downsample:
+            downsample_klass = partial(CrossEmbedLayer, kernel_sizes = cross_embed_downsample_kernel_sizes)
 
         # layers
 
@@ -1329,38 +1378,39 @@ class Unet(nn.Module):
         self.ups = nn.ModuleList([])
         num_resolutions = len(in_out)
 
-        for ind, (dim_in, dim_out) in enumerate(in_out):
+        for ind, ((dim_in, dim_out), groups) in enumerate(zip(in_out, resnet_groups)):
             is_first = ind == 0
             is_last = ind >= (num_resolutions - 1)
             layer_cond_dim = cond_dim if not is_first else None
 
             self.downs.append(nn.ModuleList([
-                block_klass(dim_in, dim_out, time_cond_dim = time_cond_dim),
+                ResnetBlock(dim_in, dim_out, time_cond_dim = time_cond_dim, groups = groups),
                 Residual(LinearAttention(dim_out, **attn_kwargs)) if sparse_attn else nn.Identity(),
-                block_klass(dim_out, dim_out, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim),
-                Downsample(dim_out) if not is_last else nn.Identity()
+                ResnetBlock(dim_out, dim_out, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups),
+                downsample_klass(dim_out) if not is_last else nn.Identity()
             ]))
 
         mid_dim = dims[-1]
 
-        self.mid_block1 = block_klass(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim)
+        self.mid_block1 = ResnetBlock(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim, groups = resnet_groups[-1])
         self.mid_attn = EinopsToAndFrom('b c h w', 'b (h w) c', Residual(Attention(mid_dim, **attn_kwargs))) if attend_at_middle else None
-        self.mid_block2 = block_klass(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim)
+        self.mid_block2 = ResnetBlock(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim, groups = resnet_groups[-1])
 
-        for ind, (dim_in, dim_out) in enumerate(reversed(in_out[1:])):
+        for ind, ((dim_in, dim_out), groups) in enumerate(zip(reversed(in_out[1:]), reversed(resnet_groups))):
             is_last = ind >= (num_resolutions - 2)
             layer_cond_dim = cond_dim if not is_last else None
 
             self.ups.append(nn.ModuleList([
-                block_klass(dim_out * 2, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim),
+                ResnetBlock(dim_out * 2, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups),
                 Residual(LinearAttention(dim_in, **attn_kwargs)) if sparse_attn else nn.Identity(),
-                block_klass(dim_in, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim),
+                ResnetBlock(dim_in, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups),
                 Upsample(dim_in)
             ]))
 
         out_dim = default(out_dim, channels)
+
         self.final_conv = nn.Sequential(
-            block_klass(dim, dim),
+            ResnetBlock(dim, dim, groups = resnet_groups[0]),
             nn.Conv2d(dim, out_dim, 1)
         )
 
@@ -1371,12 +1421,13 @@ class Unet(nn.Module):
         *,
         lowres_cond,
         channels,
-        cond_on_image_embeds
+        cond_on_image_embeds,
+        cond_on_text_encodings
     ):
-        if lowres_cond == self.lowres_cond and channels == self.channels and cond_on_image_embeds == self.cond_on_image_embeds:
+        if lowres_cond == self.lowres_cond and channels == self.channels and cond_on_image_embeds == self.cond_on_image_embeds and cond_on_text_encodings == self.cond_on_text_encodings:
             return self
 
-        updated_kwargs = {'lowres_cond': lowres_cond, 'channels': channels, 'cond_on_image_embeds': cond_on_image_embeds}
+        updated_kwargs = {'lowres_cond': lowres_cond, 'channels': channels, 'cond_on_image_embeds': cond_on_image_embeds, 'cond_on_text_encodings': cond_on_text_encodings}
         return self.__class__(**{**self._locals, **updated_kwargs})
 
     def forward_with_cond_scale(
@@ -1441,11 +1492,12 @@ class Unet(nn.Module):
 
         if self.cond_on_image_embeds:
             image_tokens = self.image_to_cond(image_embed)
+            null_image_embed = self.null_image_embed.to(image_tokens.dtype) # for some reason pytorch AMP not working
 
             image_tokens = torch.where(
                 image_keep_mask,
                 image_tokens,
-                self.null_image_embed
+                null_image_embed
             )
 
         # take care of text encodings (optional)
@@ -1469,10 +1521,12 @@ class Unet(nn.Module):
                 text_mask = rearrange(text_mask, 'b n -> b n 1')
                 text_keep_mask = text_mask & text_keep_mask
 
+            null_text_embed = self.null_text_embed.to(text_tokens.dtype) # for some reason pytorch AMP not working
+
             text_tokens = torch.where(
                 text_keep_mask,
                 text_tokens,
-                self.null_text_embed
+                null_text_embed
             )
 
         # main conditioning tokens (c)
@@ -1560,7 +1614,7 @@ class Decoder(BaseGaussianDiffusion):
         timesteps = 1000,
         image_cond_drop_prob = 0.1,
         text_cond_drop_prob = 0.5,
-        loss_type = 'l1',
+        loss_type = 'l2',
         beta_schedule = 'cosine',
         predict_x_start = False,
         predict_x_start_for_latent_diffusion = False,
@@ -1572,7 +1626,8 @@ class Decoder(BaseGaussianDiffusion):
         condition_on_text_encodings = False,        # the paper suggested that this didn't do much in the decoder, but i'm allowing the option for experimentation
         clip_denoised = True,
         clip_x_start = True,
-        clip_adapter_overrides = dict()
+        clip_adapter_overrides = dict(),
+        unconditional = False
     ):
         super().__init__(
             beta_schedule = beta_schedule,
@@ -1580,6 +1635,9 @@ class Decoder(BaseGaussianDiffusion):
             loss_type = loss_type
         )
 
+        self.unconditional = unconditional
+        assert not (condition_on_text_encodings and unconditional), 'unconditional decoder image generation cannot be set to True if conditioning on text is present'
+
         assert exists(clip) ^ exists(image_size), 'either CLIP is supplied, or you must give the image_size and channels (usually 3 for RGB)'
 
         self.clip = None
@@ -1621,7 +1679,8 @@ class Decoder(BaseGaussianDiffusion):
 
             one_unet = one_unet.cast_model_parameters(
                 lowres_cond = not is_first,
-                cond_on_image_embeds = is_first,
+                cond_on_image_embeds = is_first and not unconditional,
+                cond_on_text_encodings = one_unet.cond_on_text_encodings and not unconditional,
                 channels = unet_channels
             )
 
@@ -1756,12 +1815,16 @@ class Decoder(BaseGaussianDiffusion):
     @eval_decorator
     def sample(
         self,
-        image_embed,
+        image_embed = None,
         text = None,
+        batch_size = 1,
         cond_scale = 1.,
         stop_at_unet_number = None
     ):
-        batch_size = image_embed.shape[0]
+        assert self.unconditional or exists(image_embed), 'image embed must be present on sampling from decoder unless if trained unconditionally'
+
+        if not self.unconditional:
+            batch_size = image_embed.shape[0]
 
         text_encodings = text_mask = None
         if exists(text):
@@ -1771,10 +1834,11 @@ class Decoder(BaseGaussianDiffusion):
         assert not (not self.condition_on_text_encodings and exists(text_encodings)), 'decoder specified not to be conditioned on text, yet it is presented'
 
         img = None
+        is_cuda = next(self.parameters()).is_cuda
 
         for unet_number, unet, vae, channel, image_size, predict_x_start in tqdm(zip(range(1, len(self.unets) + 1), self.unets, self.vaes, self.sample_channels, self.image_sizes, self.predict_x_start)):
 
-            context = self.one_unet_in_gpu(unet = unet) if image_embed.is_cuda else null_context()
+            context = self.one_unet_in_gpu(unet = unet) if is_cuda else null_context()
 
             with context:
                 lowres_cond_img = None
@@ -1914,3 +1978,4 @@ class DALLE2(nn.Module):
             return images[0]
 
         return images
+

dalle2_pytorch/train.py

@@ -1,3 +1,4 @@
+import time
 import copy
 from functools import partial
 
@@ -39,6 +40,50 @@ def groupby_prefix_and_trim(prefix, d):
     kwargs_without_prefix = dict(map(lambda x: (x[0][len(prefix):], x[1]), tuple(kwargs_with_prefix.items())))
     return kwargs_without_prefix, kwargs
 
+# print helpers
+
+def print_ribbon(s, symbol = '=', repeat = 40):
+    flank = symbol * repeat
+    return f'{flank} {s} {flank}'
+
+# saving and loading functions
+
+# for diffusion prior
+
+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_ribbon('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')
+
 # exponential moving average wrapper
 
 class EMA(nn.Module):
@@ -60,6 +105,10 @@ class EMA(nn.Module):
         self.register_buffer('initted', torch.Tensor([False]))
         self.register_buffer('step', torch.tensor([0.]))
 
+    def restore_ema_model_device(self):
+        device = self.initted.device
+        self.ema_model.to(device)
+
     def update(self):
         self.step += 1
 
@@ -260,6 +309,11 @@ class DecoderTrainer(nn.Module):
 
         if self.use_ema:
             self.decoder.unets = trainable_unets             # restore original training unets
+
+        # cast the ema_model unets back to original device
+        for ema in self.ema_unets:
+            ema.restore_ema_model_device()
+
         return output
 
     def forward(

setup.py

@@ -10,11 +10,12 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.2.0',
+  version = '0.2.12',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',
   author_email = 'lucidrains@gmail.com',
+  long_description_content_type = 'text/markdown',
   url = 'https://github.com/lucidrains/dalle2-pytorch',
   keywords = [
     'artificial intelligence',

train_diffusion_prior.py

@@ -7,6 +7,7 @@ import torch
 from torch import nn
 from embedding_reader import EmbeddingReader
 from dalle2_pytorch import DiffusionPrior, DiffusionPriorNetwork
+from dalle2_pytorch.train import load_diffusion_model, save_diffusion_model, print_ribbon
 from dalle2_pytorch.optimizer import get_optimizer
 from torch.cuda.amp import autocast,GradScaler
 
@@ -41,73 +42,56 @@ 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)):
-        # make a copy of the text embeddings for shuffling
-        text_embed = torch.tensor(embt[0]).to(device)
-        text_embed_shuffled = text_embed.clone()
+    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)
-
+       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)
-
+       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)
-
+       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)
-
+       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)
-
+       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)})
-        wandb.log({"CosineSimilarity(text_embed,predicted_image_embed)": np.mean(
-            predicted_similarity)})
-        wandb.log({"CosineSimilarity(text_embed,predicted_unrelated_embed)": np.mean(
-            unrelated_similarity)})
-        wandb.log({"CosineSimilarity(image_embed,predicted_image_embed)": np.mean(
-            predicted_img_similarity)})
-
-    return np.mean(predicted_similarity - original_similarity)
-
-
+       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,
@@ -129,9 +113,15 @@ 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 
@@ -140,6 +130,8 @@ 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
@@ -152,16 +144,21 @@ def train(image_embed_dim,
             loss_type = dp_loss_type, 
             condition_on_text_encodings = dp_condition_on_text_encodings).to(device)
 
-    # 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
+    # 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_ribbon("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
+
     ### Training code ###
     scaler = GradScaler(enabled=amp)
     optimizer = get_optimizer(diffusion_prior.net.parameters(), wd=weight_decay, lr=learning_rate)
@@ -172,12 +169,15 @@ 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)
 
@@ -192,9 +192,13 @@ 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(),
@@ -204,14 +208,22 @@ 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)
@@ -220,11 +232,6 @@ 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
@@ -236,7 +243,6 @@ 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 
@@ -245,6 +251,7 @@ 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)
@@ -262,7 +269,6 @@ 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")
@@ -271,22 +277,40 @@ 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()
@@ -315,9 +339,15 @@ def main():
           args.save_interval,
           args.save_path,
           device,
+          RESUME,
+          DPRIOR_PATH,
+          config,
+          args.wandb_entity,
+          args.wandb_project,
           args.learning_rate,
           args.max_grad_norm,
           args.weight_decay,
+          args.dropout,
           args.amp)
 
 if __name__ == "__main__":