mohitsha's picture
mohitsha HF staff
Add quantized files
f4fe1f7 verified
from functools import partial
import timm
from optimum.amd.ryzenai import (
AutoQuantizationConfig,
RyzenAIOnnxQuantizer,
)
from optimum.exporters.onnx import main_export
from transformers import PretrainedConfig
# Define paths for exporting ONNX model and saving quantized model
export_dir = "resnet_onnx"
quantization_dir = "resnet_onnx_quantized"
# Specify the model ID from Timm
model_id = "timm/resnet18.a1_in1k"
# Step 1: Export the model to ONNX format using Optimum Exporters
main_export(
model_name_or_path=model_id,
output=export_dir,
task="image-classification",
opset=13,
batch_size=1,
no_dynamic_axes=True,
)
# Step 2: Preprocess configuration and data transformations
config = PretrainedConfig.from_pretrained(export_dir)
data_config = timm.data.resolve_data_config(pretrained_cfg=config.pretrained_cfg)
transforms = timm.data.create_transform(**data_config, is_training=False)
def preprocess_fn(ex, transforms):
image = ex["image"]
if image.mode == "L":
# Convert greyscale to RGB if needed
print("WARNING: converting greyscale to RGB")
image = image.convert("RGB")
pixel_values = transforms(image)
return {"pixel_values": pixel_values}
# Step 3: Initialize the RyzenAIOnnxQuantizer with the exported model
quantizer = RyzenAIOnnxQuantizer.from_pretrained(export_dir)
# Step 4: Load recommended quantization config for model
quantization_config = AutoQuantizationConfig.ipu_cnn_config()
# Step 5: Obtain a calibration dataset for computing quantization parameters
train_calibration_dataset = quantizer.get_calibration_dataset(
"imagenet-1k",
preprocess_function=partial(preprocess_fn, transforms=transforms),
num_samples=100,
dataset_split="train",
preprocess_batch=False,
streaming=True,
)
# Step 6: Run the quantizer with the specified configuration and calibration data
quantizer.quantize(
quantization_config=quantization_config,
dataset=train_calibration_dataset,
save_dir=quantization_dir
)