resnet18
Datasets
All datasets matching “resnet18”neuralatlas-attributions-resnet18task4_eval_resnet18This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "so101",
"total_episodes": 50,
"total_frames": 23772,
"total_tasks": 1,
"total_videos": 100,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/rocach94/task4_eval_resnet18.weightclip-resnet18slim-operator-bank
WeightCLIP ResNet18Slim operator bank
This private dataset repository stores the exact preprocessed operator dataset
used by the current WeightCLIP production training run. It contains the active
weight-tile bank, the matching activation-context bank, and the metadata needed
to reproduce production sampling.
The active payload is 41,724,270,793 bytes (38.859 GiB) across 3,622 source
files:
weight_tile_bank-9020c363ee2005e8: 135,100 weight records, 793 files,
11,181,671,316… See the full description on the dataset page: https://huggingface.co/datasets/EnriFermi/weightclip-resnet18slim-operator-bank.eval_koch_base_4.1_resnet18This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.0",
"robot_type": "koch",
"total_episodes": 8,
"total_frames": 4965,
"total_tasks": 1,
"total_videos": 16,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:8"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/shin1107/eval_koch_base_4.1_resnet18.Visualize-Transformer-ResNet18-Checkpointseval_task3_Resnet18This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "so101",
"total_episodes": 50,
"total_frames": 35763,
"total_tasks": 1,
"total_videos": 100,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/rocach94/eval_task3_Resnet18.