Zayn
/

AICVTG_What_if_a_machine_could_create_captions_automatically

vision-encoder-decoder

image-text-to-text

image-captioning

Inference Endpoints

Model card Files Files and versions Community

Zayn commited on Oct 23, 2022

Commit

7457061

·

1 Parent(s): ff2c394

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -18,9 +18,9 @@ This is an image captioning model training by Zayn
 from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
-model = VisionEncoderDecoderModel.from_pretrained("Zayn/vit2distilgpt2")
-feature_extractor = ViTFeatureExtractor.from_pretrained("Zayn/vit2distilgpt2")
-tokenizer = AutoTokenizer.from_pretrained("Zayn/vit2distilgpt2")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)

 from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
+model = VisionEncoderDecoderModel.from_pretrained("Zayn/AICVTG_What_if_a_machine_could_create_captions_automatically")
+feature_extractor = ViTFeatureExtractor.from_pretrained("Zayn/AICVTG_What_if_a_machine_could_create_captions_automatically")
+tokenizer = AutoTokenizer.from_pretrained("Zayn/AICVTG_What_if_a_machine_could_create_captions_automatically")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)