nohamoamary/image-captioning-with-visual-attention 🖼️ → ❓

▶️ 11.3K runs 📅 Jan 2022 ⚙️ Cog 0.6.1 🔗 GitHub 📄 Paper

image-captioning image-to-text

About

datasets: Flickr8k

Example Output

Output

[object Object]

Performance Metrics

2.64s Prediction Time

35.87s Total Time

Input Parameters

image (required) Type: string: Image to Descripe

Output Schema

Output

Example Execution Logs

2022-01-23 20:31:00.725074: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudnn.so.8
2022-01-23 20:31:01.363218: I tensorflow/stream_executor/cuda/cuda_dnn.cc:359] Loaded cuDNN version 8101
2022-01-23 20:31:02.099783: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublas.so.11
2022-01-23 20:31:02.600324: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublasLt.so.11

Version Details

Version ID: 9bb60a6baa58801aa7cd4c4fafc95fcf1531bf59b84962aff5a718f4d1f58986
Version Created: April 29, 2023

Run on Replicate →