Reset

logs/train_example/events.out.tfevents.1717881552.federatedlearning.3513992.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:25fdd45d3190a053834cb6569184eea0d2dc2bfce873bf6e3d0ff6cd3652bafa
-size 118824

pipeline.py

@@ -1,5 +1,6 @@
 from typing import List, Optional, Tuple, Union
-from diffusers import DiffusionPipeline, ImagePipelineOutput, randn_tensor
+from diffusers import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
 
 import torch
 
@@ -22,26 +23,21 @@ class DDPMConditionalPipeline(DiffusionPipeline):
         return_dict: bool = True,
     ) -> Union[ImagePipelineOutput, Tuple]:
         # Sample gaussian noise to begin loop
-        if isinstance(self.unet.config.sample_size, int):
+        if isinstance(self.unet.model.sample_size, int):
             image_shape = (
                 batch_size,
-                self.unet.config.in_channels,
-                self.unet.config.sample_size,
-                self.unet.config.sample_size,
+                self.unet.model.in_channels,
+                self.unet.model.sample_size,
+                self.unet.model.sample_size,
             )
         else:
             image_shape = (
                 batch_size,
-                self.unet.config.in_channels,
-                *self.unet.config.sample_size,
+                self.unet.model.in_channels,
+                *self.unet.model.sample_size,
             )
 
-        if self.device.type == "mps":
-            # randn does not work reproducibly on mps
-            image = randn_tensor(image_shape, generator=generator)
-            image = image.to(self.device)
-        else:
-            image = randn_tensor(image_shape, generator=generator, device=self.device)
+        image = randn_tensor(image_shape, generator=generator)
 
         # set step values
         self.scheduler.set_timesteps(num_inference_steps)

scheduler/scheduler_config.json

@@ -1,19 +0,0 @@
-{
-  "_class_name": "DDPMScheduler",
-  "_diffusers_version": "0.28.0",
-  "beta_end": 0.02,
-  "beta_schedule": "linear",
-  "beta_start": 0.0001,
-  "clip_sample": true,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
-  "steps_offset": 0,
-  "thresholding": false,
-  "timestep_spacing": "leading",
-  "trained_betas": null,
-  "variance_type": "fixed_small"
-}

unet/config.json

@@ -1,45 +0,0 @@
-{
-  "_class_name": "UNet2DModel",
-  "_diffusers_version": "0.27.2",
-  "act_fn": "silu",
-  "add_attention": true,
-  "attention_head_dim": 8,
-  "attn_norm_num_groups": null,
-  "block_out_channels": [
-    128,
-    128,
-    256,
-    512
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "down_block_types": [
-    "DownBlock2D",
-    "DownBlock2D",
-    "AttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "downsample_type": "conv",
-  "dropout": 0.0,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 1,
-  "layers_per_block": 2,
-  "mid_block_scale_factor": 1,
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_class_embeds": 10,
-  "num_train_timesteps": null,
-  "out_channels": 1,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 32,
-  "time_embedding_type": "positional",
-  "up_block_types": [
-    "UpBlock2D",
-    "AttnUpBlock2D",
-    "UpBlock2D",
-    "UpBlock2D"
-  ],
-  "upsample_type": "conv"
-}

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d19e953d793b3cbc0f5e932f83561fb3a7b147c69c5cd473733ecdd19942ecc
-size 246153668