Skip to content

Fixed Nits in Evaluation Docs #10063

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 2, 2024
Merged

Fixed Nits in Evaluation Docs #10063

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions docs/source/en/conceptual/evaluation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
```
Expand Down Expand Up @@ -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:
Expand Down Expand Up @@ -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).
Expand All @@ -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(
Expand All @@ -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)
Expand Down Expand Up @@ -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)])
Expand All @@ -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):
Expand All @@ -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",
Expand Down