gcvit_tiny / README.md

Add LiteRT converted gcvit_tiny

e057374 verified about 21 hours ago

804 Bytes

library_name: litert
tags:
  - vision
  - image-classification
datasets:
  - imagenet-1k

gcvit_tiny

Converted TIMM image classification model for LiteRT.

Source architecture: gcvit_tiny
Source checkpoint: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights-morevit/gcvit_tiny_224_nvidia-ac783954.pth
File: model.tflite
Input: float32 tensor in NCHW layout, shape [1, 3, 224, 224]
Output: ImageNet-1K logits, shape [1, 1000]

Runtime Status

CPU smoke test: passed with LiteRT CompiledModel.
GPU delegation: currently blocked for this model by rank-5 tensor patterns in the GPU backend, mostly RESHAPE, TRANSPOSE, and related window/attention operations. The model is published as CPU-ready while GPU support is being improved.