Add quantized files

config.json

@@ -0,0 +1,105 @@
+{
+  "architecture": "resnet18",
+  "num_classes": 1000,
+  "num_features": 512,
+  "pretrained_cfg": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier": "fc",
+    "crop_mode": "center",
+    "crop_pct": 0.95,
+    "cross_attention_hidden_size": null,
+    "custom_load": false,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "first_conv": "conv1",
+    "fixed_input_size": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "interpolation": "bicubic",
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "min_length": 0,
+    "model_type": "",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_classes": 1000,
+    "num_return_sequences": 1,
+    "origin_url": "https://github.com/huggingface/pytorch-image-models",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "paper_ids": "arXiv:2110.00476",
+    "pool_size": [
+      7,
+      7
+    ],
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "suppress_tokens": null,
+    "tag": "a1_in1k",
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "test_crop_pct": 1.0,
+    "test_input_size": [
+      3,
+      288,
+      288
+    ],
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "transformers_version": "4.36.2"
+}

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0723876d0a12903d84705a98c29851774fc947448b43b730db84f9ae15976415
+size 11731625

quantize.py

@@ -0,0 +1,63 @@
+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
+)
+

ryzenai_config.json

@@ -0,0 +1,14 @@
+{
+  "opset": null,
+  "optimum_version": "1.17.0.dev0",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": true,
+    "calibration_method": "MinMSE",
+    "enable_dpu": true,
+    "format": "QDQ",
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "transformers_version": "4.36.2"
+}