RepViT
RepViT (Wang et al. 2024): a mobile CNN classifier laid out like a ViT, re-parameterised to plain convolutions.
experimental Fork of huggingface/pytorch-image-models@0df212b · backends: portable, kernels
- Paper RepViT: Revisiting Mobile CNN From ViT Perspective CVPR 2024 · first released 18 Jul 2023
- Authors’ code THU-MIG/RepViT (PyTorch), not the code forked here: timm carries the architecture and the converted authors' checkpoints in its own, simpler API.
Paper 2023 Added in 0.2.0 Evaluated with 0.2.0
Use it
pip install fastforks Lean install with only what this model needs: pip install "fastforks-core[timm]"
from fastforks import classification
model = classification.load("repvit_m0_9.dist_300e_in1k") # kernels on a supported GPU, else portable PyTorch
result = model(image)
result.logits
result.backend # what ran: mode, device, dtype, kernels fastforks bench repvit_m0_9.dist_300e_in1k Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.
Speed and memory
Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.
Input: synthetic, 224x224 (the task’s standard size)
| Backend | dtype | Time per call (ms) | vs original fp32 | Peak memory allocated / reserved | Load (s) | First call (s) |
|---|---|---|---|---|---|---|
| Original fp32 | fp32 | 8.45 | – | 59 MiB/78 MiB | 1.7 | 0.36 |
| Original fp16torch.autocast(float16) around the call | fp16 | 12.7 | 0.67× | 65 MiB/84 MiB | 0.2 | 2.43 |
| Portable fp32 | fp32 | not measured | – | – | – | – |
| Portable | fp16 | 5.35 | 1.6× | 45 MiB/76 MiB | 1.6 | 0.28 |
| Kernels | fp16 | 0.776 | 11× | 45 MiB/76 MiB | 2.0 | 0.08 |
| Portable + torch.compile | 3.30 | 2.6× | 77 MiB/96 MiB | 9 (build) | – | |
| TensorRT fp16 | fp16 | 0.509 | 17× | 32 MiBenginenot comparable | 34 (build) | – |
Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-10. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two
times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.
Other devices
| Device | Backend | dtype | ms / call | Peak memory | Output vs reference | Input |
|---|---|---|---|---|---|---|
| Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-14 | Original | fp32 | 24.5 | 478 MiB process | – | 224x224 |
| Portable | fp16 | 13.2 | 470 MiB process | matches | 224x224 | |
| Portable | fp32 | 11.6 | 453 MiB process | matches | 224x224 | |
| Kernels | fp16 | not implemented | – | 224x224 | ||
CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.
Licence and weights
Commercial use allowed
- Code
- Apache-2.0
- Weights
- Apache-2.0 source
- Training data
-
- ImageNet-1k (ILSVRC 2012 classification) noncommercial, non-commercial
Our reading of the licences, not legal advice.
Weights
repvit_m0_9.dist_300e_in1k.safetensors 22.2 MB· hosted on Hugging Facefastforks downloads and checks these files on first use (fastforks download repvit_m0_9.dist_300e_in1k).
Accuracy
The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.
ImageNet-1k val
5000 random images, top-1 / top-5 %
| Run | dtype | top-1 % ↑ | top-5 % ↑ | Δ top-1 % vs fp32 original | images | ms / image |
|---|---|---|---|---|---|---|
| Original fp32 | fp32 | 79.44 | 94.20 | reference | 5000 | 0.714 |
| Original fp16 | fp16 | 79.48 | 94.16 | +0.04 | 5000 | 0.659 |
| Portable fp32 | fp32 | 79.42 | 94.08 | −0.02 | 5000 | 1.32 |
| Portable | fp16 | 79.44 | 94.08 | ±0.00 | 5000 | 0.484 |
| Kernels | fp16 | 79.42 | 94.08 | −0.02 | 5000 | 0.347 |
fastforks: the model's own resize / crop on the GPU; original: the library's pretrained loader and its PIL eval transform. Original = the authors’ code, same checkpoint and protocol. Measured on original fp32, original fp16: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-10; portable fp32: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 6f0a70e1, 2026-11-17; portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 8b2f2df5, 2026-11-10.
Closeness to the original
Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. CPU, float32: max |diff| <= 2.5e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0094 and p99 <= 0.036 (absolute error of the output logits).
| Check | Tolerance | Measured |
|---|---|---|
| CPU fp32, max |diff| | ≤ 0.000025 | not recorded |
| GPU default dtypes, mean |diff| | ≤ 0.0094 | 0.00445 |
| GPU default dtypes, p99 |diff| | ≤ 0.036 | 0.01533 |
Recorded for repvit_m0_9.dist_300e_in1k on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-10, with these kernels: cudnn_haccfvm_convfvm_extrafvm_mbfvm_r3
Details
RepViT (Wang et al. 2024): a mobile CNN with the block layout of a ViT (3x3 depthwise token mixer, 1x1 channel mixer), re-parameterised to plain convolutions at load.
- Input / output
- Input: one RGB image. Output: ImageNet-1k class logits.
- Input size
- fixed 224x224: the input is resized (short side 235) and centre-cropped to it; tested up to 224x224 (45 MiB allocated)
- Outputs
logits- Checkpoint
arch="repvit_m0_9.dist_300e_in1k"- CUDA kernels
cudnn_haccconvolutions with fp16 accumulation (cuDNN)fvm_convfused convolutions for image classifiersfvm_extrafused transformer row operations (rotary split, SwiGLU with LayerNorm)fvm_mbfused MBConv blocks (MobileNet and EfficientNet families)fvm_r3further fused classifier blocks
- Apple (MPS)
- fp32, fp16
Limitations
- The older aliases `repvit_m1` / `repvit_m2` / `repvit_m3` (`.dist_in1k`) that timm also lists are not shipped.
Full reference, generated from the repository
RepViT (Wang et al. 2024): a mobile CNN classifier laid out like a ViT, re-parameterised to plain convolutions.
Commercial use: yes.
| variant | input | backend | time (ms) | peak memory (MiB, allocated / reserved) |
|---|---|---|---|---|
repvit_m0_9.dist_300e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.45 12.7 5.35 0.776 3.30 0.509 | 59 / 78 65 / 84 45 / 76 45 / 76 77 / 96 75 / 108 |
repvit_m0_9.dist_450e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.55 12.6 5.41 0.767 3.34 0.489 | 59 / 78 65 / 84 45 / 76 45 / 76 77 / 96 77 / 110 |
repvit_m1_0.dist_300e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.79 12.6 5.29 0.786 3.33 0.503 | 66 / 82 75 / 92 48 / 78 48 / 78 80 / 118 78 / 110 |
repvit_m1_0.dist_450e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.80 12.6 5.44 0.785 3.21 0.477 | 66 / 82 75 / 92 48 / 78 48 / 78 80 / 118 80 / 112 |
repvit_m1_1.dist_300e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.14 11.7 5.03 0.765 6.12 0.470 | 73 / 86 84 / 98 51 / 62 51 / 64 83 / 102 83 / 96 |
repvit_m1_1.dist_450e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 8.07 11.7 4.99 0.758 6.07 0.478 | 73 / 86 84 / 98 51 / 62 51 / 64 83 / 102 83 / 96 |
repvit_m1_5.dist_300e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 13.9 20.4 8.55 1.19 4.89 0.766 | 95 / 100 118 / 124 62 / 94 62 / 94 94 / 114 96 / 130 |
repvit_m1_5.dist_450e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 13.9 20.5 8.71 1.19 4.93 0.760 | 95 / 100 118 / 124 62 / 94 62 / 94 94 / 114 94 / 128 |
repvit_m2_3.dist_300e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 17.9 26.1 11.1 1.66 6.51 1.03 | 132 / 156 170 / 184 80 / 128 79 / 130 112 / 148 149 / 200 |
repvit_m2_3.dist_450e_in1k | synthetic (224x224) | original (fp32) original portable kernels portable + torch.compile TensorRT fp16 | 18.2 26.1 10.9 1.70 6.49 1.03 | 132 / 156 170 / 184 80 / 128 79 / 130 112 / 148 149 / 200 |
Details
- Original code: https://github.com/huggingface/pytorch-image-models at
0df212b369a5 - Code licence: Apache-2.0 (permissive); files:
- Weights licence: Apache-2.0
- Licence evidence: https://huggingface.co/timm/repvit_m1_1.dist_450e_in1k/blob/ff441038a42982fff1c8c75be7c794f9ba76db72/README.md
- Training data: ImageNet-1k (ILSVRC 2012 classification) (ImageNet-1k with distillation from a RegNetY-16GF teacher (RepViT paper), 300 or 450 epochs)
- Kernel libraries:
cudnn_hacc,fvm_conv,fvm_extra,fvm_mb,fvm_r3 - Variants:
repvit_m0_9.dist_300e_in1k(default ofrepvit_m0_9),repvit_m0_9.dist_450e_in1k,repvit_m1_0.dist_300e_in1k(default ofrepvit_m1_0),repvit_m1_0.dist_450e_in1k,repvit_m1_1.dist_300e_in1k(default ofrepvit_m1_1),repvit_m1_1.dist_450e_in1k,repvit_m1_5.dist_300e_in1k(default ofrepvit_m1_5),repvit_m1_5.dist_450e_in1k,repvit_m2_3.dist_300e_in1k(default ofrepvit_m2_3),repvit_m2_3.dist_450e_in1k - Outputs: logits; label_set:
imagenet-1k - Input size: fixed 224x224: the input is resized (short side 235) and centre-cropped to it
- Tested up to (portable, fp16, RTX 5060 Ti 16 GB):
repvit_m0_9.dist_300e_in1k224x224 (0.0 GiB peak allocated, 0.0 reserved);repvit_m0_9.dist_450e_in1k224x224 (0.0 GiB peak allocated, 0.0 reserved);repvit_m1_0.dist_300e_in1k224x224 (0.0 GiB peak allocated, 0.0 reserved);repvit_m1_0.dist_450e_in1k224x224 (0.0 GiB peak allocated, 0.0 reserved);repvit_m1_1.dist_300e_in1k224x224 (0.0 GiB peak allocated, 0.1 reserved);repvit_m1_1.dist_450e_in1k224x224 (0.0 GiB peak allocated, 0.1 reserved);repvit_m1_5.dist_300e_in1k224x224 (0.1 GiB peak allocated, 0.1 reserved);repvit_m1_5.dist_450e_in1k224x224 (0.1 GiB peak allocated, 0.1 reserved);repvit_m2_3.dist_300e_in1k224x224 (0.1 GiB peak allocated, 0.1 reserved);repvit_m2_3.dist_450e_in1k224x224 (0.1 GiB peak allocated, 0.1 reserved) repvit_m0_9.dist_300e_in1k224x224, first call: portable + torch.compile 9 s (cold Inductor cache), TensorRT fp16 34 s (ONNX + engine).repvit_m0_9.dist_450e_in1k224x224, first call: portable + torch.compile 8 s (cold Inductor cache), TensorRT fp16 30 s (ONNX + engine).repvit_m1_0.dist_300e_in1k224x224, first call: portable + torch.compile 8 s (cold Inductor cache), TensorRT fp16 35 s (ONNX + engine).repvit_m1_0.dist_450e_in1k224x224, first call: portable + torch.compile 8 s (cold Inductor cache), TensorRT fp16 40 s (ONNX + engine).repvit_m1_1.dist_300e_in1k224x224, first call: portable + torch.compile 8 s (cold Inductor cache), TensorRT fp16 33 s (ONNX + engine).repvit_m1_1.dist_450e_in1k224x224, first call: portable + torch.compile 8 s (cold Inductor cache), TensorRT fp16 33 s (ONNX + engine).repvit_m1_5.dist_300e_in1k224x224, first call: portable + torch.compile 10 s (cold Inductor cache), TensorRT fp16 39 s (ONNX + engine).repvit_m1_5.dist_450e_in1k224x224, first call: portable + torch.compile 10 s (cold Inductor cache), TensorRT fp16 34 s (ONNX + engine).repvit_m2_3.dist_300e_in1k224x224, first call: portable + torch.compile 12 s (cold Inductor cache), TensorRT fp16 41 s (ONNX + engine).repvit_m2_3.dist_450e_in1k224x224, first call: portable + torch.compile 12 s (cold Inductor cache), TensorRT fp16 41 s (ONNX + engine).repvit_m0_9.dist_300e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m0_9.dist_450e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_0.dist_300e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_0.dist_450e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_1.dist_300e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_1.dist_450e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_5.dist_300e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m1_5.dist_450e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m2_3.dist_300e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m2_3.dist_450e_in1koriginal 224x224: torch.autocast(float16) around the callrepvit_m0_9.dist_300e_in1kload / first call: original 0.2 s / 2.43 s, portable 1.65 s / 0.283 s, kernels 2.01 s / 0.081 srepvit_m0_9.dist_450e_in1kload / first call: original 0.19 s / 0.014 s, portable 1.65 s / 0.265 s, kernels 1.96 s / 0.052 srepvit_m1_0.dist_300e_in1kload / first call: original 0.2 s / 1.436 s, portable 1.64 s / 0.277 s, kernels 2.0 s / 0.052 srepvit_m1_0.dist_450e_in1kload / first call: original 0.2 s / 0.014 s, portable 1.74 s / 0.271 s, kernels 1.96 s / 0.051 srepvit_m1_1.dist_300e_in1kload / first call: original 0.2 s / 1.365 s, portable 1.86 s / 0.281 s, kernels 1.97 s / 0.057 srepvit_m1_1.dist_450e_in1kload / first call: original 0.21 s / 0.013 s, portable 1.89 s / 0.266 s, kernels 2.35 s / 0.054 srepvit_m1_5.dist_300e_in1kload / first call: original 0.26 s / 0.023 s, portable 1.84 s / 0.268 s, kernels 2.63 s / 0.053 srepvit_m1_5.dist_450e_in1kload / first call: original 0.25 s / 0.023 s, portable 1.86 s / 0.275 s, kernels 2.21 s / 0.053 srepvit_m2_3.dist_300e_in1kload / first call: original 0.33 s / 1.536 s, portable 2.0 s / 0.275 s, kernels 2.41 s / 0.053 srepvit_m2_3.dist_450e_in1kload / first call: original 0.34 s / 0.033 s, portable 2.01 s / 0.274 s, kernels 2.64 s / 0.057 s- Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5
Measured
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 | portable fp32 | kernels | note |
|---|---|---|---|---|---|---|---|
repvit_m0_9.dist_300e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 79.44 / 94.20 | 79.48 / 94.16 | 79.44 / 94.08 | 79.42 / 94.08 | 79.42 / 94.08 | |
repvit_m0_9.dist_450e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 79.52 / 94.22 | 79.56 / 94.26 | 79.52 / 94.24 | 79.48 / 94.26 | 79.52 / 94.24 | |
repvit_m1_0.dist_300e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 81.12 / 94.78 | 81.12 / 94.76 | 81.10 / 94.74 | 81.12 / 94.74 | 81.10 / 94.80 | |
repvit_m1_0.dist_450e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 81.10 / 94.86 | 81.10 / 94.88 | 81.16 / 94.90 | 81.12 / 94.96 | 81.14 / 94.92 | |
repvit_m1_1.dist_300e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 81.40 / 95.10 | 81.40 / 95.10 | 81.32 / 95.02 | 81.34 / 95.02 | 81.34 / 95.02 | |
repvit_m1_1.dist_450e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 82.32 / 95.70 | 82.28 / 95.72 | 82.18 / 95.66 | 82.14 / 95.62 | 82.18 / 95.62 | |
repvit_m1_5.dist_300e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 82.94 / 96.22 | 82.98 / 96.24 | 82.96 / 96.24 | 82.98 / 96.24 | 83.00 / 96.26 | |
repvit_m1_5.dist_450e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 83.18 / 96.38 | 83.20 / 96.38 | 83.24 / 96.36 | 83.28 / 96.34 | 83.24 / 96.36 | |
repvit_m2_3.dist_300e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.12 / 96.54 | 84.14 / 96.52 | 84.22 / 96.54 | 84.22 / 96.56 | 84.20 / 96.54 | |
repvit_m2_3.dist_450e_in1k | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.30 / 96.58 | 84.30 / 96.60 | 84.26 / 96.62 | 84.26 / 96.62 | 84.20 / 96.62 |
Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 8b2f2df5, 2026-11-10; portable32: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 6f0a70e1, 2026-11-17; kernels: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 8b2f2df5, 2026-11-10.
Parity
CPU, float32: max |diff| <= 2.5e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0094 and p99 <= 0.036 (absolute error of the output logits).
| variant | kernels error vs original, mean / p99 | GPU, torch | kernels used |
|---|---|---|---|
repvit_m0_9.dist_300e_in1k | 0.00445 / 0.01533 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m0_9.dist_450e_in1k | 0.006 / 0.02362 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_0.dist_300e_in1k | 0.00624 / 0.02055 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_0.dist_450e_in1k | 0.00517 / 0.01958 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_1.dist_300e_in1k | 0.00582 / 0.02136 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_1.dist_450e_in1k | 0.00608 / 0.02142 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_5.dist_300e_in1k | 0.00536 / 0.01993 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m1_5.dist_450e_in1k | 0.00508 / 0.02024 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m2_3.dist_300e_in1k | 0.00459 / 0.01603 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
repvit_m2_3.dist_450e_in1k | 0.00489 / 0.01714 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120 |
Limitations
- The older aliases
repvit_m1/repvit_m2/repvit_m3(.dist_in1k) that timm also lists are not shipped.
Example output
One fixed input through this checkpoint, the same for every model of the task (kernels · float16 · NVIDIA GeForce RTX 5060 Ti).
Top 5
Input: Chelsea the cat, Stéfan van der Walt (CC0).