yuchenlin

import torch
from transformers import BertTokenizer, BertModel, BertForMaskedLM
import logging
logging.basicConfig(level=logging.INFO)# OPTIONAL



tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForMaskedLM.from_pretrained('bert-base-uncased')
model.eval()

yuchenlin

import torch
from transformers import OpenAIGPTTokenizer, OpenAIGPTLMHeadModel
from transformers import GPT2Tokenizer, GPT2LMHeadModel
import numpy as np
from scipy.special import softmax
 
def model_init(model_string, cuda):
    if model_string.startswith("gpt2"):
        tokenizer = GPT2Tokenizer.from_pretrained(model_string)
        model = GPT2LMHeadModel.from_pretrained(model_string)

yuchenlin

```
wget https://s3.amazonaws.com/conceptnet/downloads/2017/edges/conceptnet-assertions-5.5.5.csv.gz
gunzip -k conceptnet-assertions-5.5.5.csv.gz
```

import json

def del_pos(s):
    """
    Deletes part-of-speech encoding from an entity string, if present.

yuchenlin

import torch
import numpy as np
from tqdm import tqdm
from fairseq.models.roberta import RobertaModel
from fairseq.data.data_utils import collate_tokens
from torch.utils.data import DataLoader, SequentialSampler

roberta = torch.hub.load('pytorch/fairseq', 'roberta.large.mnli')
roberta.eval()
roberta.cuda()

yuchenlin

from sentence_transformers import SentenceTransformer   # pip install -U sentence-transformers
from sklearn.cluster import KMeans
from collections import defaultdict

INPUT_FILE = "/tmp/test_input.txt"

with open(INPUT_FILE, "r") as f:
    lines = f.read().splitlines()

print(len(lines))

yuchenlin

#!/bin/bash
# Usage: bash mv.sh /path/to/src/ /path/to/target/

sourcedir=$1
targetdir=$2

filecount=$(find $sourcedir | wc -l)
echo $filecount # Print the number of the total files.
mkdir $targetdir
mv -v $sourcedir $targetdir | pv -l -s $filecount > /tmp/mv_log.txt 

yuchenlin

from argparse import Namespace

from numpy.core.defchararray import index
from semanticdebugger.debug_algs.cl_simple_alg import ContinualFinetuning
from tqdm import tqdm 
import torch 
from semanticdebugger.models.utils import trim_batch
import json
from semanticdebugger.debug_algs import run_lifelong_finetune

yuchenlin

"""
# stanza.download()
# http://nlp.stanford.edu/software/stanza/1.0.0/en/default.zip

Example usage:
CUDA_VISIBLE_DEVICES=1 \
python parsing.py \
    --input_corpus_path ./corpora/gkb_best_sent.txt \
    --output_json_path ./parses/gkb_best.parses.jsonl \
    --prefix gkb_best --num_shards 10000 --shard_id 0

yuchenlin

#!/bin/bash

echo "HW3 Report" > $vocareumReportFile
echo "Programming language..." >> $vocareumReportFile

filename=$(ls|grep NeuralNetwork)
if [[ $filename =~ (^|[[:space:]])"NeuralNetwork.py"($|[[:space:]]) ]]; then
	cmd="python NeuralNetwork.py train_image.csv train_label.csv test_image.csv"
    mnist_cmd="python NeuralNetwork.py grading_train_image.csv grading_train_label.csv grading_test_image.csv"
    ta_cmd="python NeuralNetwork.py grading_train_image.csv grading_train_label.csv additional_test_image.csv"

yuchenlin

import sys

acc = float(sys.argv[1]) # mnist acc
ta_acc = float(sys.argv[2]) # ta acc

t1=50.00
t2=90.00

tt1=30.0
tt2=60.0