Update README.md

README.md

@@ -55,12 +55,14 @@ The models can also be used to resume a training or as initialization for new tr
 Please follow instructions in our [GitHub repo](https://github.com/apple/ml-tic-clip) to create the evaluation sets or follow [DataComp](https://github.com/mlfoundations/datacomp) for the standard evaluations on 38 datasets.
 
 The following snippet assumes the TiC-DataComp data has been prepared and following the instructions in the GitHub repo.
+
+### Training
 ```bash
 YEAR=2016 # There are no models before 2016 since data from 2014-2016 were compined into one year
 REPO="apple/TiC-CLIP-basic-oracle"
 huggingface-cli download $REPO checkpoints/$YEAR.pt
 
-## Train Cummulative
+## Train
 pushd datacomp
 final_data_dir=$TIC_DATACOMP_Y_PATH/train/$YEAR/
 torchrun --nproc_per_node 8 --nnodes 1 \
@@ -74,7 +76,10 @@ torchrun --nproc_per_node 8 --nnodes 1 \
     --save_frequency 1 \
     --resume
 popd
+```
 
+### Evaluation
+```bash
 ## Evaluate Model
 # Evaluate a ViT-B/16 model on TiC/Retrieval/Yearly/$YEAR and
 # TiC/DataCompNet/Yearly/$YEAR
@@ -83,6 +88,28 @@ python ../dataset_creation/tic-datacomp/generate_tasklist.py --yaml-path tasklis
 python evaluate.py --data_dir data/ --train_output_dir ./results --use_model "ViT-B-16 $YEAR.pt" --skip_hf --skip_db --skip_notification
 ```
 
+### OpenCLIP Load and Inference Example
+```python
+import open_clip
+from huggingface_hub import hf_hub_download
+filename = hf_hub_download(repo_id="apple/TiC-CLIP-basic-oracle", filename="checkpoints/2016.pt")
+model, _, preprocess = open_clip.create_model_and_transforms('ViT-B-16', filename)
+tokenizer = open_clip.get_tokenizer('ViT-B-16')
+
+image = preprocess(Image.open("image.png").convert('RGB')).unsqueeze(0)
+text = tokenizer(["a diagram", "a dog", "a cat"])
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image)
+    text_features = model.encode_text(text)
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)
+```
+
 ## Training Details
 
 ### Training Data