Tower Hanoi Resnet18 Reward v2

--- license: apache-2.0 tags: - robotics - reward-model - resnet - tower-of-hanoi - posttraining-for-robotics library_name: pytorch pipeline_tag: image-classification --- # Tower of Hanoi ResNet Reward Model V2 ## Input Format The model expects a Wan-aligned RGB multiview image tensor: ```text shape: [3, 544, 320] layout: CHW view order: cam_high, cam_left_wrist, cam_right_wrist ``` Preprocessing contract: ```text Each camera image: 320x180 RGB Vertical stack: 540x320 Resize: 540x320 -> 544x320 with bilinear interpolation Final tensor: [3, 544, 320] ``` The view order and resize are part of the checkpoint contract. Do not use the old horizontal `[3, 224, 672]` format or a bottom-padded `[3, 544, 320]` input. ## Output Format The model outputs a scalar binary reward/logit. The evaluation uses: ```python prob = sigmoid(logit) pred = prob > 0.5 ``` Interpretation: ```text prob close to 1: state looks like a successful/completed tower state prob close to 0: state looks like an incomplete or failed state ``` ## Files ```text full_weights.pt model weights README.md model card eval_results.json validation and hard-validation metrics dataset_metadata.json processed dataset metadata manifest.json file sizes and SHA-256 checksums ``` ## Test Results ```text val.pt: count: 1926 positive: 963 negative: 963 loss: 0.0159152 accuracy: 0.9968848 auc: 0.9993875 prob_mean: 0.5008704 prob_pos_mean: 0.9956364 prob_neg_mean: 0.0061045 hard_val.pt: count: 842 positive: 421 negative: 421 loss: 0.0166353 accuracy: 0.9964371 auc: 0.9998984 prob_mean: 0.5043597 prob_pos_mean: 0.9975614 prob_neg_mean: 0.0111578 ```

Source context: 0 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo qmddn/tower-hanoi-resnet18-reward-v2