bpe_simple_vocab_16e6.txt.gz missing

[lexhacke]

Getting FileNotFound error when trying to load processor. For this file in particular "bpe_simple_vocab_16e6.txt.gz"

This is my patch :P

try:
self.model = build_sam3_image_model()
self.processor = Sam3Processor(self.model)
except FileNotFoundError:
response = requests.get("https://github.com/openai/CLIP/raw/refs/heads/main/clip/bpe_simple_vocab_16e6.txt.gz", stream=True) # Use stream=True for large files
response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

        # 3. Write the content to the local file
        with open('/usr/local/lib/python3.12/dist-packages/assets/bpe_simple_vocab_16e6.txt.gz', 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)

        self.model = build_sam3_image_model()
        self.processor = Sam3Processor(self.model)
    finally:
        print('Dude it wasnt the bpe tokenizer :(')

[houssineidoudi12]

i had the same issue today after their update yesterday so if you wanna run the model just do this.
from sam3.model_builder import build_sam3_image_model
from sam3.model.sam3_image_processor import Sam3Processor

model = build_sam3_image_model("sam3/sam3/assets/bpe_simple_vocab_16e6.txt.gz")
processor = Sam3Processor(model, confidence_threshold=0.3)

[cheezafizz]

I have requested a pull for this issue
#359

[anilstream]

Still facing same issue, the solution from @houssineidoudi12 works for now.

[houssineidoudi12]

@anilstream yes it works for me it depends where you placed your project but the file is here on the git https://github.com/facebookresearch/sam3/tree/main/sam3/assets fix the path with respect to that :)