Skip to content

Commit

Permalink
chore: update executor docstring (#806)
Browse files Browse the repository at this point in the history 
* chore: update executor docstring

* chore: update executor docstring

* chore: minor update

* chore: address comment
  • Loading branch information
@ZiniuYu
ZiniuYu committed Aug 16, 2022
1 parent 3c43eed commit 89205f0
Show file tree
Hide file tree
Showing 4 changed files with 44 additions and 10 deletions.
20 changes: 10 additions & 10 deletions docs/user-guides/server.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ Please also note that **different models give different sizes of output dimensio
| ViT-B-16 | ✅ | ✅ | ✅ | 512 | 335 | 3.20 | 1.44 |
| ViT-B-16-plus-240 | ✅ | ✅ | 🚧 | 640 | 795 | 3.03 | 1.59 |
| ViT-L-14 | ✅ | ✅ | ❌ | 768 | 890 | 3.66 | 2.04 |
| ViT-L-14@336px | ✅ | ✅ | ❌ | 768 | 891 | 3.74 | 2.23 |
| ViT-L-14-336 | ✅ | ✅ | ❌ | 768 | 891 | 3.74 | 2.23 |
| M-CLIP/XLM-Roberta-Large-Vit-B-32 | ✅ | 🚧 | 🚧 | 512 | 4284 | 5.37 | 1.68 |
| M-CLIP/XLM-Roberta-Large-Vit-L-14 | ✅ | 🚧 | ❌ | 768 | 4293 | 4.30 | 4.97 |
| M-CLIP/XLM-Roberta-Large-Vit-B-16Plus | ✅ | 🚧 | 🚧 | 640 | 4293 | 4.30 | 4.13 |
Expand Down Expand Up @@ -262,29 +262,29 @@ executors:

For all backends, you can set the following parameters via `with`:

| Parameter | Description |
|-------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| `name` | Model weights, default is `ViT-B-32::openai`. A full list of models and weights can be found [here](#model-support) |
| `num_worker_preprocess` | The number of CPU workers for image & text prerpocessing, default 4. |
| `minibatch_size` | The size of a minibatch for CPU preprocessing and GPU encoding, default 64. Reduce the size of it if you encounter OOM on GPU. |
| Parameter | Description |
|-------------------------|------------------------------------------------------------------------------------------------------------------------------|
| `name` | The name of the model to be used. Default 'ViT-B-32::openai'. A list of available models can be found [here](#model-support) |
| `num_worker_preprocess` | The number of CPU workers to preprocess images and texts. Default is 4. |
| `minibatch_size` | The size of the minibatch for preprocessing and encoding. Default is 32. Reduce this number if you encounter OOM errors. |

There are also runtime-specific parameters listed below:

````{tab} PyTorch
| Parameter | Description |
|-----------|--------------------------------------------------------------------------------------------------------------------------------|
| `device` | `cuda` or `cpu`. Default is `None` means auto-detect. |
| `jit` | If to enable Torchscript JIT, default is `False`. |
| `device` | 'cpu' or 'cuda'. Default is None, which auto-detects the device. |
| `jit` | Whether to use JIT compilation. Default is False. |
````

````{tab} ONNX
| Parameter | Description |
|-----------|--------------------------------------------------------------------------------------------------------------------------------|
| `device` | `cuda` or `cpu`. Default is `None` means auto-detect.
| `model_path` | The path to custom CLIP model, default `None`. |
| `device` | 'cpu' or 'cuda'. Default is None, which auto-detects the device.
| `model_path` | The path to the model to be used. If not specified, the model will be downloaded or loaded from the local cache. See [here](#use-custom-model-for-onnx) to learn how to finetune custom models. |
````

Expand Down
13 changes: 13 additions & 0 deletions server/clip_server/executors/clip_onnx.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,19 @@ def __init__(
model_path: Optional[str] = None,
**kwargs,
):
"""
:param name: The name of the model to be used. Default 'ViT-B-32::openai'. A list of available models can be
found at https://clip-as-service.jina.ai/user-guides/server/#model-support
:param device: 'cpu' or 'cuda'. Default is None, which auto-detects the device.
:param num_worker_preprocess: The number of CPU workers to preprocess images and texts. Default is 4.
:param minibatch_size: The size of the minibatch for preprocessing and encoding. Default is 32. Reduce this
number if you encounter OOM errors.
:param access_paths: The access paths to traverse on the input documents to get the images and texts to be
processed. Visit https://docarray.jina.ai/fundamentals/documentarray/access-elements for more details.
:param model_path: The path to the model to be used. If not specified, the model will be downloaded or loaded
from the local cache. Visit https://clip-as-service.jina.ai/user-guides/server/#use-custom-model-for-onnx
to learn how to finetune custom models.
"""
super().__init__(**kwargs)

self._minibatch_size = minibatch_size
Expand Down
10 changes: 10 additions & 0 deletions server/clip_server/executors/clip_tensorrt.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,16 @@ def __init__(
access_paths: str = '@r',
**kwargs,
):
"""
:param name: The name of the model to be used. Default 'ViT-B-32::openai'. A list of available models can be
found at https://clip-as-service.jina.ai/user-guides/server/#model-support
:param device: 'cpu' or 'cuda'. Default is 'cuda' since TensorRT is only supported on CUDA.
:param num_worker_preprocess: The number of CPU workers to preprocess images and texts. Default is 4.
:param minibatch_size: The size of the minibatch for preprocessing and encoding. Default is 32. Reduce this
number if you encounter OOM errors.
:param access_paths: The access paths to traverse on the input documents to get the images and texts to be
processed. Visit https://docarray.jina.ai/fundamentals/documentarray/access-elements for more details.
"""
super().__init__(**kwargs)

self._pool = ThreadPool(processes=num_worker_preprocess)
Expand Down
11 changes: 11 additions & 0 deletions server/clip_server/executors/clip_torch.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,17 @@ def __init__(
access_paths: str = '@r',
**kwargs,
):
"""
:param name: The name of the model to be used. Default 'ViT-B-32::openai'. A list of available models can be
found at https://clip-as-service.jina.ai/user-guides/server/#model-support
:param device: 'cpu' or 'cuda'. Default is None, which auto-detects the device.
:param jit: Whether to use JIT compilation. Default is False.
:param num_worker_preprocess: The number of CPU workers to preprocess images and texts. Default is 4.
:param minibatch_size: The size of the minibatch for preprocessing and encoding. Default is 32. Reduce this
number if you encounter OOM errors.
:param access_paths: The access paths to traverse on the input documents to get the images and texts to be
processed. Visit https://docarray.jina.ai/fundamentals/documentarray/access-elements for more details.
"""
super().__init__(**kwargs)

self._minibatch_size = minibatch_size
Expand Down

0 comments on commit 89205f0

Please sign in to comment.