feat(ml): export clip models to ONNX and host models on Hugging Face ()

* export clip models

* export to hf

refactored export code

* export mclip, general refactoring

cleanup

* updated conda deps

* do transforms with pillow and numpy, add tokenization config to export, general refactoring

* moved conda dockerfile, re-added poetry

* minor fixes

* updated link

* updated tests

* removed `requirements.txt` from workflow

* fixed mimalloc path

* removed torchvision

* cleaner np typing

* review suggestions

* update default model name

* update test
This commit is contained in:
Mert 2023-10-31 06:02:04 -04:00 committed by GitHub
parent 3212a47720
commit 87a0ba3db3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
29 changed files with 6192 additions and 2043 deletions
machine-learning

View file

@ -1,11 +1,12 @@
from io import BytesIO
import json
from argparse import ArgumentParser
from io import BytesIO
from typing import Any
from locust import HttpUser, events, task
from locust.env import Environment
from PIL import Image
from argparse import ArgumentParser
byte_image = BytesIO()
@ -14,11 +15,21 @@ def _(parser: ArgumentParser) -> None:
parser.add_argument("--tag-model", type=str, default="microsoft/resnet-50")
parser.add_argument("--clip-model", type=str, default="ViT-B-32::openai")
parser.add_argument("--face-model", type=str, default="buffalo_l")
parser.add_argument("--tag-min-score", type=int, default=0.0,
help="Returns all tags at or above this score. The default returns all tags.")
parser.add_argument("--face-min-score", type=int, default=0.034,
help=("Returns all faces at or above this score. The default returns 1 face per request; "
"setting this to 0 blows up the number of faces to the thousands."))
parser.add_argument(
"--tag-min-score",
type=int,
default=0.0,
help="Returns all tags at or above this score. The default returns all tags.",
)
parser.add_argument(
"--face-min-score",
type=int,
default=0.034,
help=(
"Returns all faces at or above this score. The default returns 1 face per request; "
"setting this to 0 blows up the number of faces to the thousands."
),
)
parser.add_argument("--image-size", type=int, default=1000)
@ -62,7 +73,7 @@ class CLIPTextFormDataLoadTest(InferenceLoadTest):
("modelName", self.environment.parsed_options.clip_model),
("modelType", "clip"),
("options", json.dumps({"mode": "text"})),
("text", "test search query")
("text", "test search query"),
]
self.client.post("/predict", data=data)
@ -88,5 +99,5 @@ class RecognitionFormDataLoadTest(InferenceLoadTest):
("options", json.dumps({"minScore": self.environment.parsed_options.face_min_score})),
]
files = {"image": self.data}
self.client.post("/predict", data=data, files=files)