yoadtew/zero-shot-image-to-text 🖼️🔢📝 → 📝

▶️ 6.7K runs 📅 Dec 2021 ⚙️ Cog 0.4.4 🔗 GitHub 📄 Paper

image-captioning image-to-text

About

image to text generation

Example Output

Output

[object Object]

Performance Metrics

77.98s Prediction Time

256.13s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/mgxm/0958ab0c-8d26-45f8-a5f1-a27a1f2259cc/baby.jpg",
  "beam_size": "5",
  "cond_text": "Image of a",
  "end_factor": "1.01",
  "ce_loss_scale": "0.2",
  "max_seq_length": "15"
}

Input Parameters

image (required) Type: string: input image
beam_size Type: integerDefault: 5Range: 1 - 10: Number of beams to use
cond_text Type: stringDefault: Image of a: conditional text
end_factor Type: numberDefault: 1.01Range: 1 - 1.1: Higher value for shorter captions
ce_loss_scale Type: numberDefault: 0.2Range: 0 - 0.6: Scale of cross-entropy loss with un-shifted language model
max_seq_length Type: integerDefault: 15Range: 1 - 20: Maximum number of tokens to generate

Output Schema

Output

Type: string

Example Execution Logs

08/12/2021 13:20:37 | [' baby %% -1.9783461', ' newborn %% -2.632012', ' child %% -3.1142285', ' Baby %% -3.6589427', ' infant %% -3.8890254']
/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/_tensor.py:575: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
08/12/2021 13:20:49 | [' baby in %% -3.415359', ' baby sleeping %% -3.425561', ' newborn photo %% -3.4403224', ' baby on %% -3.5201316', ' baby. %% -3.6261525']
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at  /pytorch/aten/src/ATen/native/BinaryOps.cpp:467.)
  return torch.floor_divide(self, other)
08/12/2021 13:21:01 | [' baby on leaves %% -3.4305604', ' baby in the %% -3.6233037', ' baby.! %% -3.6261525', ' baby on grass %% -3.6841075', ' baby sleeping in %% -3.69094']
08/12/2021 13:21:13 | [' baby.!! %% -3.6261525', ' baby on leaves. %% -3.6822686', ' baby sleeping in a %% -3.8298764', ' baby sleeping in green %% -3.830517', ' baby on grass. %% -3.8318949']
08/12/2021 13:21:26 | [' baby.!!! %% -3.6261525', ' baby on leaves.! %% -3.6822686', ' baby on grass.! %% -3.8318949', ' baby sleeping in a flower %% -3.8424401', ' baby sleeping in a green %% -3.9262307']
08/12/2021 13:21:39 | [' baby.!!!! %% -3.6261525', ' baby on leaves.!! %% -3.6822686', ' baby on grass.!! %% -3.8318949', ' baby sleeping in a flower. %% -3.890606', ' baby sleeping in a green flower %% -4.0138764']
08/12/2021 13:21:51 | [' baby.!!!!! %% -3.6261525', ' baby on leaves.!!! %% -3.6822686', ' baby on grass.!!! %% -3.8318949', ' baby sleeping in a flower.! %% -3.890606', ' baby sleeping in a green flower. %% -4.1707625']

Version Details

Version ID: 7f2735bab48ff6caa414a3fff239b0d5de77a97f1791dcb7e0eb17c259aa11be
Version Created: October 5, 2022

Run on Replicate →