ILSVRC/imagenet-1k
Viewer • Updated • 1.43M • 90.8k • 1.17k
The final checkpoint reaches 76.7 % top-1 / 93.3 % top-5 on the 50,000 ImageNet validation images, using a single 224 × 224 center crop.
| file | contents |
|---|---|
checkpoints/step0000000.pt … checkpoints/step0112590.pt |
103 checkpoints, ~103 MB each |
trajectory.csv |
step, epoch, val_top1, val_top5 of every checkpoint |
Each checkpoint is a dict with these keys:
model: a torchvision.models.resnet50 state dict;step, epoch: the training position;val_top1, val_top5: ImageNet validation accuracy;lr: the learning rate at that step;recipe: the name of the training recipe.When checkpoints were saved (1 epoch = 1,251 steps of 1,024 images):
import torch, torchvision
from huggingface_hub import hf_hub_download
path = hf_hub_download("LSL-datasets/resnet50-imagenet-trajectory", "checkpoints/step0112590.pt")
ckpt = torch.load(path, map_location="cpu", weights_only=True)
model = torchvision.models.resnet50()
model.load_state_dict(ckpt["model"])
model.eval()
print(ckpt["epoch"], ckpt["val_top1"]) # 90.0 0.76658
Inputs use the standard torchvision preprocessing:
The recipe follows Goyal et al. (2017), Accurate, Large Minibatch SGD, but uses a cosine schedule instead of step decay:
torchvision.models.resnet50(zero_init_residual=True), trained from random initialization with seed 0.ILSVRC/imagenet-1k, in parquet format.These weights were trained on ImageNet-1k. Their use follows the ImageNet terms of access: non-commercial research and education.