Imagent models
Collection
The models Imagent downloads. • 13 items • Updated
RAM++ (ONNX, fp16)
RAM++ (Recognize Anything Plus) by xinyu1205, exported to ONNX by CannotFindObject.
Exported for Imagent from CannotFindObject/RAM_ONNX at commit 6c4ca81fb841e359c043c1e8f92f62bf5c3b8c18 by convert_ram_fp16.py, which is in this repo: it states the graphs' inputs and outputs, and checks each graph against its source before writing it. CannotFindObject's fp32 graph converted to fp16 weights and arithmetic, with fp32 input and output. Its tag list and thresholds are fp32's, in imagent/ram-plus-onnx. All credit for the model belongs to its authors; please cite their work, not this repo.
| File | Size | SHA-256 | From |
|---|---|---|---|
ram_plus_fp16.onnx |
929,837,546 bytes | a2ac88e1715f50886281a0826c8d62257b52586af9ecbe0490351b1ee3156381 |
convert_ram_fp16.py |
Licence: apache-2.0, as upstream - see LICENSE.