winycg/anchor_net 🖼️❓📝 → ❓

▶️ 223 runs 📅 Jun 2022 ⚙️ Cog 0.3.9 🔗 GitHub 📄 Paper

image-classification

About

Localizing Semantic Patches for Accelerating Image Classification

Example Output

Output

{"plot":"https://replicate.delivery/mgxm/2960d3dc-96b6-4e40-8098-fb4b48dfd886/output.png"}

Performance Metrics

0.00s Prediction Time

73.68s Total Time

All Input Parameters

{
  "input_image": "https://replicate.delivery/mgxm/cf21baaf-55c3-49dd-a5e9-c723eaac5fd5/ILSVRC2012_val_00023440.JPEG",
  "output_format": "Final-probs-plot",
  "iou_thresholds": "0.0, 0.1"
}

Input Parameters

input_image (required) Type: string: Image to be classified
output_format Default: Predictions-plot: Final-probs-plot: Plots the final prediction of top 10 classes Json: Get the final prediction of top 10 classes in json format Predictions-plot: Plot intermediate predictions of patches CAM-plot: Plot the intermediate CAM map from AnchorNet
iou_thresholds Type: stringDefault:: Comma separated list of floats where the ith float determines the allowed IOU to a next (i+1) patch proposal (6 max). Leave empty for a sinle patch proposal

Output Schema

Json Type: string
plot Type: stringFormat: uri: Plot

Example Execution Logs

/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /pytorch/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)

Version Details

Version ID: e361854bcb889339416728e464bf6ae7680ae5ccfbc0ed471e949ec038dd8e25
Version Created: June 23, 2022

Run on Replicate →