Fixed Nits in Evaluation Docs (#10063)

Minor fixes and script improvement in evaluation
docs.

docs/source/en/conceptual/evaluation.md

@@ -181,7 +181,7 @@ Then we load the [v1-5 checkpoint](https://huggingface.co/stable-diffusion-v1-5/
 
 ```python
 model_ckpt_1_5 = "stable-diffusion-v1-5/stable-diffusion-v1-5"
-sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)
+sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=torch.float16).to("cuda")
 
 images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
 ```
@@ -280,7 +280,7 @@ from diffusers import StableDiffusionInstructPix2PixPipeline
 
 instruct_pix2pix_pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
     "timbrooks/instruct-pix2pix", torch_dtype=torch.float16
-).to(device)
+).to("cuda")
 ```
 
 Now, we perform the edits:
@@ -326,9 +326,9 @@ from transformers import (
 
 clip_id = "openai/clip-vit-large-patch14"
 tokenizer = CLIPTokenizer.from_pretrained(clip_id)
-text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to(device)
+text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to("cuda")
 image_processor = CLIPImageProcessor.from_pretrained(clip_id)
-image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to(device)
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to("cuda")
 ```
 
 Notice that we are using a particular CLIP checkpoint, i.e., `openai/clip-vit-large-patch14`. This is because the Stable Diffusion pre-training was performed with this CLIP variant. For more details, refer to the [documentation](https://huggingface.co/docs/transformers/model_doc/clip).
@@ -350,7 +350,7 @@ class DirectionalSimilarity(nn.Module):
 
     def preprocess_image(self, image):
         image = self.image_processor(image, return_tensors="pt")["pixel_values"]
-        return {"pixel_values": image.to(device)}
+        return {"pixel_values": image.to("cuda")}
 
     def tokenize_text(self, text):
         inputs = self.tokenizer(
@@ -360,7 +360,7 @@ class DirectionalSimilarity(nn.Module):
             truncation=True,
             return_tensors="pt",
         )
-        return {"input_ids": inputs.input_ids.to(device)}
+        return {"input_ids": inputs.input_ids.to("cuda")}
 
     def encode_image(self, image):
         preprocessed_image = self.preprocess_image(image)
@@ -459,6 +459,7 @@ with ZipFile(local_filepath, "r") as zipper:
 ```python
 from PIL import Image
 import os
+import numpy as np
 
 dataset_path = "sample-imagenet-images"
 image_paths = sorted([os.path.join(dataset_path, x) for x in os.listdir(dataset_path)])
@@ -477,6 +478,7 @@ Now that the images are loaded, let's apply some lightweight pre-processing on t
 
 ```python
 from torchvision.transforms import functional as F
+import torch
 
 
 def preprocess_image(image):
@@ -498,6 +500,10 @@ dit_pipeline = DiTPipeline.from_pretrained("facebook/DiT-XL-2-256", torch_dtype=
 dit_pipeline.scheduler = DPMSolverMultistepScheduler.from_config(dit_pipeline.scheduler.config)
 dit_pipeline = dit_pipeline.to("cuda")
 
+seed = 0
+generator = torch.manual_seed(seed)
+
+
 words = [
     "cassette player",
     "chainsaw",