Inception-v3 (fastforks)

Inception-v3 (Szegedy et al. 2015): factorised inception modules; 299 px input.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/pytorch/vision at 1f1a920d685d.

Task: classification. Tier: stable. Outputs: logits. Backends: portable, kernels.

Input: one RGB image. Output: ImageNet-1k class logits.

Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.

variant weights (author link) SHA-256 weights licence commercial use
inception_v3.tv_in1k@1 inception_v3_google-0cc3c7bd.pth 0cc3c7bd7505 BSD-3-Clause (assumed from code) yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause.

Code licence: BSD-3-Clause; the authors do not state a separate weights licence.

Training data: ImageNet-1k (ILSVRC 2012 classification).

Licence evidence: https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE

Input size

fixed 299x299: the input is resized (short side 342) and centre-cropped to it Tested up to (portable, fp16, RTX 5060 Ti 16 GB): inception_v3.tv_in1k 299x299 (0.1 GiB peak allocated, 0.2 reserved)

Speed and memory

Classification, synthetic

model input time (ms): original fp32 original portable kernels kernels speed-up: vs original vs portable peak memory (MiB, allocated / reserved): original portable kernels
inception_v3.tv_in1k 224x224 7.88 10.3 5.21 1.30 6.1x 4.0x 185 / 206 120 / 166 150 / 228

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
inception_v3.tv_in1k 1.62 0.28 1.86 0.40 0.04 0.05

torch.compile and TensorRT

model input time: portable compile TensorRT fp16 kernels preparation: compile (cold first call) ONNX + engine build peak MiB (alloc / reserved): portable compile kernels TensorRT (engine + torch)
inception_v3.tv_in1k 224x224 5.21 ms 3.03 ms 0.685 ms 1.30 ms 8.61 s 22.4 s 120 / 166 152 / 184 150 / 228 184 / 234

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

Accuracy

On public datasets

fastforks: the model's own resize / crop on the GPU; original: the library's pretrained loader and its PIL eval transform. Original = the original code named under Details, same checkpoint and protocol.

variant dataset original fp32 original fp16 portable kernels note
inception_v3.tv_in1k ImageNet-1k val, 5000 random images, top-1 / top-5 % 78.00 / 93.50 77.98 / 93.52 77.98 / 93.48 78.04 / 93.56

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.08 (absolute error of the output logits).

Usage

from fastforks import classification

model = classification.load("inception_v3.tv_in1k")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg")
result.top(5)  # top-5 classes
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')

Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: inception_v3.tv_in1k.

Kernels backend

classification.load("inception_v3.tv_in1k", mode="kernels") runs our CUDA kernels (cudnn_hacc, fvm_conv, fvm_extra, fvm_mb, fvm_r3). It needs a prebuilt kernel for your GPU architecture (downloaded from https://huggingface.co/fastforks/kernels on first use) and a recent NVIDIA driver; if there is none it raises BackendUnavailableError with the reason and never falls back silently. mode="auto" picks kernels when it can run and logs the choice.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including fastforks/inception-v3