VS (Vui Seng Chua) vuiseng9

Remove files in wandb cloud programmatically via python API

import wandb
api = wandb.Api()
runs = api.runs("<entity>/<project>") # e.g. vchua/huggingface

for run in runs:
    print(run.entity, run.project, run.id, run.name)
    for fff in run.files():
 if fff.name == 'output.log':

This gist is not ready, AYOR

Goal:

Get one example of neural compressor up and running, with existing trained model. We target quantization example that quantize model of eager version of pytorch. At the time of writing INC version is v1.9. Git commit is aaad4c35

Key reference

https://github.com/intel/neural-compressor/tree/master/examples/pytorch/nlp/huggingface_models/language-modeling/quantization/ptq_static/eager

Setup

Create a conda environment

Goal:

Get examples of Intel Neural Compressor (INC) up and running, with existing trained model. We will use HuggingFace's Optimum as frontend and INC is chosen as its backend. We aim to reproduce static quantization example provided by Optimum out-of-the-box

Create a conda environment

conda create -n optimum-inc python=3.8

Setup Intel Neural Compressor per landing page. But we do it slightly different for dev.

OpenVINO BERT/QA Demo

The following docker image is canned after following the demo guide here. https://docs.openvino.ai/latest/omz_demos_bert_question_answering_demo_python.html

launch docker runtime (detach mode)

container=vuiseng9/ov-ubt18_data_dev:2021.4.2-bert-pydemo

docker run -it \
 -d \

Evaluation of different BERT models on SQuADv1.1

https://github.com/huggingface/transformers

# following has been validated with transformers v4.18

# 24 Layers
# https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad
model=bert-large-uncased-whole-word-masking-finetuned-squad

Objective: train a resnet18 for CIFAR10 dataset

Top 1 accuracy of resnet18/CIFAR10 in this repo achieves 93%. We are not using this because it defines/implements its own Resnet. We would like to use the out-of-the-box torchvision resnet18 definition. NNCF provides an image classification example which utilizes torchvision resnet definition.

# Step 1: Create a new virtualenv or conda environment, make sure the env is activated

# Step 2: Install VS's fork of NNCF
git clone https://github.com/vuiseng9/nncf
cd nncf

	import functools
	from typing import Dict, Callable, Any, Union, List, Tuple

	import torch
	import torch.nn as nn
	from torch.utils.data import DataLoader
	from torch.utils.data import Dataset

	from nncf.torch.nncf_network import NNCFNetwork
	from nncf.torch.dynamic_graph.graph_tracer import create_input_infos, create_dummy_forward_fn

	#!/usr/bin/env python3
	# -- coding: utf-8 --
	# Copyright (C) 2018-2022 Intel Corporation
	# SPDX-License-Identifier: Apache-2.0

	import argparse
	import logging as log
	import sys

	import time

	import time
	import numpy as np
	import logging as log

	from openvino.runtime import AsyncInferQueue, Core, PartialShape
	from openvino.tools.benchmark.utils.constants import CPU_DEVICE_NAME

	log.info = print

	model_path="/data1/vchua/jpqd-bert/r0.010-squad-bert-b-mvmt-8bit/ir/squad-BertForQuestionAnswering.cropped.8bit.onnx"