Hi EmbedAnything team — thanks for the great project.
I’m trying to use a HuggingFace ResNet as an image embedding backbone via the Python API, but microsoft/resnet-18 is rejected as "Model not supported" and the process panics (PyO3 unwrap), even though the README/Docs say "We support any hugging-face models on Candle".
Repro
from embed_anything import EmbeddingModel
EmbeddingModel.from_pretrained_hf(model_id="microsoft/resnet-18")
Output
It panics inside the Rust extension:
thread '<unnamed>' panicked at python/src/lib.rs:175:84:
called `Result::unwrap()` on an `Err` value: Model not supported
pyo3_runtime.PanicException: called `Result::unwrap()` on an `Err` value: Model not supported
With RUST_BACKTRACE=1, the panic originates from the _embed_anything module init path (still ends in the same unwrap at python/src/lib.rs:175:84).
Sanity checks
These work fine in the same environment:
EmbeddingModel.from_pretrained_hf(model_id="openai/clip-vit-base-patch32")
EmbeddingModel.from_pretrained_hf(model_id="google/siglip-base-patch16-224")
So it looks like the HF loader supports some vision architectures (CLIP/SigLIP), but not ResNet.
Environment
- OS: macOS
- Python: 3.12
- embed-anything: 0.7.0
Questions / request
- Is ResNet support planned (e.g.
microsoft/resnet-18, microsoft/resnet-50) for image embeddings?
- If not supported, could the docs/README be clarified? The statement "We support any hugging-face models on Candle" reads like arbitrary HF architectures should work.
- Could the Python binding avoid panicking on unsupported models and instead raise a normal Python exception (with a list of supported architectures / next steps)?
Reference: fastembed supports ResNet50
As a point of comparison, Qdrant’s fastembed supports ResNet-50 image embeddings via an ONNX model (Qdrant/resnet50-onnx, dim=2048). Example:
from fastembed import ImageEmbedding
model = ImageEmbedding(model_name="Qdrant/resnet50-onnx")
It would be awesome if EmbedAnything could support a similar ResNet image embedder (via Candle or ONNX).
Happy to test a PR / nightly build if you have guidance on how best to add this.
Hi EmbedAnything team — thanks for the great project.
I’m trying to use a HuggingFace ResNet as an image embedding backbone via the Python API, but
microsoft/resnet-18is rejected as "Model not supported" and the process panics (PyO3 unwrap), even though the README/Docs say "We support any hugging-face models on Candle".Repro
Output
It panics inside the Rust extension:
With
RUST_BACKTRACE=1, the panic originates from the_embed_anythingmodule init path (still ends in the sameunwrapatpython/src/lib.rs:175:84).Sanity checks
These work fine in the same environment:
So it looks like the HF loader supports some vision architectures (CLIP/SigLIP), but not ResNet.
Environment
Questions / request
microsoft/resnet-18,microsoft/resnet-50) for image embeddings?Reference: fastembed supports ResNet50
As a point of comparison, Qdrant’s
fastembedsupports ResNet-50 image embeddings via an ONNX model (Qdrant/resnet50-onnx, dim=2048). Example:It would be awesome if EmbedAnything could support a similar ResNet image embedder (via Candle or ONNX).
Happy to test a PR / nightly build if you have guidance on how best to add this.