| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
| |
* Fixes for lint errors introduced with Rust 1.83
* rustfmt
* Fix more lints.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
* Allow loading images with given std and mean
* OpenCLIP text encoder component
* Two MobileCLIP models
* Clippy fixes.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* onnx: fix pad, unsqueeze
both implementations have off-by-one errors:
- Pad 'reflect' cycle for eg `dim==3` is `[0,1,2,1]` which has length of
4 (or `dim*2 - 2`) not 5 (current code `dim*2 - 1`)
- Unsqueeze(-1) for tensor with `dim==3` should be 3 (ie `dim+index+1`)
not 2 (ie currently `dim+index`)
in addition, Pad is incorrectly calculating the starting padding.
If we want to pad out 2 elements to the start, and we have this cycle
of indices of length 6, then we should skip 4 elements, but currently
we skip 2. A more visual representation of what's going on is below:
```
pad_start: 2
data: [a,b,c,d]
indices: [0, 1, 2, 3, 2, 1, 0, 1, 2, 3, 2, 1, 0, ..] // zigzag between 0..4
actual: skip [ c d| c b a b]
expected: ~ skip ~ [ c b| a b c d]
```
The values between `[` and `|` are padding and the values between
`|` and `]` in the example should match the original data being padded.
* Fix clippy lints.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com>
|
| |
|
|
|
|
|
| |
* Support different resolutions in load_image()
* Added MobilenetV4 model.
* Add MobileNetv4 to README
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Add: DINOv2Reg4 with PlantCLEF2024 weights and example ( See https://arxiv.org/abs/2309.16588 and https://zenodo.org/records/10848263 )
* Remove extra files + update README to download them + remove extra lines
* minor fix (README remove extra spaces)
* minor fix (README: Fix image url)
* Modif: Add back interpolate_pos_encoding() + fix when no interpolation + remove extra comments + Update README ( source image changed and so the predictions )
* Fix: Improve code lisibility with '$ cargo clippy' and '$ cargo fmt'
* Another clippy fix.
---------
Co-authored-by: x-VEspit <vincent.espitalier@cirad.fr>
Co-authored-by: laurent <laurent.mazare@gmail.com>
|
| |
|
| |
Signed-off-by: hardlydearly <799511800@qq.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
* Normalize loudness of the generated audio.
* Lints.
* One more lint.
* Avoid running the bs1770 tests.
* Another attempt at discarding doc comments.
* Also normalize the loudness in the encodec example.
|
| |
|
|
|
|
|
| |
* Add the StarCoder2 model.
* Add the example code and get things to work.
* And also tweak the readme.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Encodec model.
* Fixes.
* Add the padding functions.
* Get the LSTM bit to work.
* Get the encodec model to generate some tokens (decoder only for now).
* Minor tweak.
* Minor tweak.
|
| |
|
| |
Co-authored-by: Guoqing Bao <guoqing.bao@enflame-tech.com>
|
| |
|
|
|
|
|
| |
* Fix the quantized mistral example.
* Add a helper function to load sharded safetensors weights.
* Use the sharded loader.
|
| |
|
|
|
| |
* Metal part 1 - Scaffolding for metal.
* Remove tracing.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Quantized version of mistral.
* Integrate the quantized mistral variant.
* Use the quantized weight files.
* Tweak the quantization command.
* Fix the dtype when computing the rotary embeddings.
* Update the readme with the quantized version.
* Fix the decoding of the remaining tokens.
|
| |
|
|
|
|
|
|
|
| |
* Token streaming.
* Use the token output stream.
* Flush the output.
* Ensure that the last characters get reported.
|
| |
|
|
|
|
|
|
|
| |
* Move dinov2.
* Move efficientnet.
* Move the quantized llama model.
* Move segment-anything.
|
| |
|
|
|
|
|
|
|
| |
* A few more contiguous fixes for cuda.
* Mask generation.
* Generic bbox.
* Generate all the masks.
|
| |
|
|
|
|
|
|
|
|
|
| |
* Add more to the automatic mask generator.
* Add the target point.
* Fix.
* Remove the allow-unused.
* Mask post-processing.
|
| |
|
|
|
| |
* Segment-anything fixes: avoid normalizing twice.
* More fixes for the image aspect ratio.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* img2img pipeline for stable diffusion.
* Rename the arguments + fix.
* Fix for zero strength.
* Another fix.
* Another fix.
* Revert.
* Include the backtrace.
* Noise scaling.
* Fix the height/width.
|
| | |
|
| |
|
|
|
| |
- Moved around book from `examples` to `candle-book` proper (overlapping
the book and the lib structures)
|
| |
|
|
|
|
|
| |
- Removed a lot of surface (SerializedFileReader ownership is really
painful).
- Moved example + vision to hf.co version.
- Removed feature gate.
|
| | |
|
| |
|
|
|
|
|
| |
* Move the yolo model bits in a separate file.
* Improve the drawing.
* Bugfix.
|
| |
|
|
|
| |
* More support for pose estimation in yolo-v8.
* Support both object detection and pose-estimation in the yolo-v8 example.
|
| | |
|
| |
|
|
|
|
|
| |
* Move the yolo shared bits to a common place.
* Share more code.
* Configurable thresholds.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Add a couple functions required for yolo.
* Add the yolo-v3 example.
* Add minimum and maximum.
* Use the newly introduced maximum.
* Cuda support for min/max + add some testing.
* Allow for more tests to work with accelerate.
* Fix a typo.
|
| | |
|
| |
|
|
|
| |
* Add the permute op (similar to pytorch).
* Add the backprop for dimension permutation.
|
| |
|
|
|
| |
* Load the image from disk and convert it to a tensor.
* Tweak the function name.
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
| |
- Loading with memmap
- Loading a sharded tensor
- Moved some snippets to `candle-examples/src/lib.rs` This is because
managing book specific dependencies is a pain https://github.com/rust-lang/mdBook/issues/706
- This causes a non aligned inclusion https://github.com/rust-lang/mdBook/pull/1856 which we have
to ignore fmt to remove.
mdbook might need some more love :)
|
| | |
|
| | |
|
| |
|
