liwenyun
/
CLIP
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: Remove incorrect code snippet from README-HPU section.

This commit is contained in:
bartosz roguski 2025-01-28 18:50:41 +01:00
parent d17b83174d
commit 859a140c04
2 changed files with 23 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
README.md
View File

@ -29,7 +29,9 @@ import torch
import clip import clip
from PIL import Image from PIL import Image
device = "cuda" if torch.cuda.is_available() else "cpu" from clip.utils import get_device_initial
device = get_device_initial() # "HPU" if using Intel® Gaudi® HPU, "cuda" if using CUDA GPU, "cpu" otherwise
model, preprocess = clip.load("ViT-B/32", device=device) model, preprocess = clip.load("ViT-B/32", device=device)
image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device) image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device)
@ -94,8 +96,10 @@ import clip
import torch import torch
from torchvision.datasets import CIFAR100 from torchvision.datasets import CIFAR100
from clip.utils import get_device_initial
# Load the model # Load the model
device = "cuda" if torch.cuda.is_available() else "cpu" device = get_device_initial()
model, preprocess = clip.load('ViT-B/32', device) model, preprocess = clip.load('ViT-B/32', device)
# Download the dataset # Download the dataset
@ -153,8 +157,10 @@ from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR100 from torchvision.datasets import CIFAR100
from tqdm import tqdm from tqdm import tqdm
from clip.utils import get_device_initial
# Load the model # Load the model
device = "cuda" if torch.cuda.is_available() else "cpu" device = get_device_initial()
model, preprocess = clip.load('ViT-B/32', device) model, preprocess = clip.load('ViT-B/32', device)
# Load the dataset # Load the dataset
@ -209,47 +215,11 @@ See the [PyTorch Docker Images for the Intel® Gaudi® Accelerator](https://deve
```bash ```bash
docker run -it --runtime=habana clip_hpu:latest docker run -it --runtime=habana clip_hpu:latest
``` ```
Optionally, you can add a mapping volume (`-v`) to access your project directory inside the container. Add the flag `-v /path/to/your/project:/workspace/project` to the `docker run` command.
Replace `/path/to/your/project` with the path to your project directory on your local machine.
### Command-line Usage with Intel® Gaudi® HPU
To run the notebook with Intel® Gaudi® HPU, use the `--device hpu` option when specifying the device in the code.
For example, modify the device assignment as follows:
```python
device = 'hpu' if torch.device('hpu').is_available() else 'cuda' if torch.cuda.is_available() else 'cpu'
model.to(device)
image_input = image_input.to(device)
text_tokens = text_tokens.to(device)
```
### Python Usage with Intel® Gaudi® HPU ### Python Usage with Intel® Gaudi® HPU
To leverage Intel® Gaudi® HPU in Python, ensure that the device is specified as `hpu` during model initialization and tensor manipulation. You do not need to change the code to leverage Intel® Gaudi® HPU. The `get_device_initial()` function will automatically detect the correct device and return the appropriate device name. So no changes are required.
```python
import clip
import torch
# Load the model on HPU
device = "hpu"
model, preprocess = clip.load("ViT-B/32", device=device)
# Prepare data and move to HPU
image_input = preprocess(image).unsqueeze(0).to(device)
text_tokens = clip.tokenize("a sample text").to(device)
# Run inference
with torch.no_grad():
image_features = model.encode_image(image_input)
text_features = model.encode_text(text_tokens)
print("Inference completed on HPU")
```
## See Also ## See Also

24
tests/test_consistency.py
View File

@ -27,18 +27,18 @@ def test_consistency(model_name):
@pytest.mark.parametrize("model_name", clip.available_models()) @pytest.mark.parametrize("model_name", clip.available_models())
def test_hpu_support(model_name): def test_hpu_support(model_name):
device = "hpu" devices = ["hpu", "cpu"]
jit_model, transform = clip.load(model_name, device="cpu", jit=True) all_probs = []
py_model, _ = clip.load(model_name, device=device, jit=False) for device in devices:
print(f"=== Testing {model_name} on {device} ===")
model, transform = clip.load(model_name, device=device, jit=False)
image = transform(Image.open("CLIP.png")).unsqueeze(0).to(device) image = transform(Image.open("CLIP.png")).unsqueeze(0).to(device)
text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device) text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device)
with torch.no_grad(): with torch.no_grad():
logits_per_image, _ = jit_model(image, text) logits_per_image, _ = model(image, text)
jit_probs = logits_per_image.softmax(dim=-1).cpu().numpy() probs = logits_per_image.softmax(dim=-1).cpu().numpy()
all_probs.append(probs)
logits_per_image, _ = py_model(image, text) assert np.allclose(all_probs[0], all_probs[1], atol=0.01, rtol=0.1)
py_probs = logits_per_image.softmax(dim=-1).cpu().numpy()
assert np.allclose(jit_probs, py_probs, atol=0.01, rtol=0.1)