maxidl

We couldn’t find that file to show.

maxidl

import numpy as np
import pandas as pd
from scipy import sparse
from pathlib import Path
from joblib import Parallel, delayed
from itertools import chain
from random import shuffle
from tqdm import tqdm
from gensim.models import Word2Vec
import logging

maxidl

import cudf
import cugraph
from numba import cuda
from numba.cuda.random import create_xoroshiro128p_states, xoroshiro128p_uniform_float32
import numpy as np

# gdf = cudf.read_csv('zachary.ssv', header=None, sep=' ', dtype=['int32', 'int32'])
gdf = cudf.read_csv('Flickr-labelled.edgelist', header=None, sep=' ', dtype=['int32', 'int32'])
gdf.columns = ['src', 'dest']
gdf = gdf.sort_values(by='src')

maxidl

# remap prefix from 'C-b' to 'C-a'
unbind C-b
set-option -g prefix C-a
bind-key C-a send-prefix

# split panes using | and -
bind | split-window -h
bind - split-window -v
unbind '"'
unbind %

maxidl

{
    "0": "tench, Tinca tinca",
    "1": "goldfish, Carassius auratus",
    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
    "3": "tiger shark, Galeocerdo cuvieri",
    "4": "hammerhead, hammerhead shark",
    "5": "electric ray, crampfish, numbfish, torpedo",
    "6": "stingray",
    "7": "cock",
    "8": "hen",

maxidl

model.to(device)
model.eval()
model.zero_grad()

def forward_func(inputs, attention_mask=None):
    return model(inputs, attention_mask=attention_mask).logits

lig = LayerIntegratedGradients(forward_func, model.bert.embeddings)

all_input_ids, all_ref_input_ids, all_attributions, all_pred_probs, all_pred_class, all_true_class, all_attr_class, all_attr_score, all_convergence_scores = ([] for i in range(9))

maxidl

import sys
import os  # noqa
sys.path.insert(0, ".")  # noqa

import torch
from utils.styled_plot import plt
from utils.dataset import load_test_image, preprocess_image, normalize_image, convert_idx_to_label
from classifiers.cnn_classifier import ImageNetClassifier
from solutions.explainers import plot_attributions, aggregate_attribution, normalize_attribution

maxidl

import torch
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from pathlib import Path
from tqdm.auto import tqdm

print(torch.cuda.is_available())
dev = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
# dev = torch.device("cpu")

maxidl

def get_simple_gradient_expl(model, images, targets, absolute=False):
    images.requires_grad = True
    outputs = model(images)
    outputs = outputs.gather(1, targets.unsqueeze(1))
    grad = torch.autograd.grad(torch.unbind(outputs), images, create_graph=True)[0] # create_graph=True for second order derivative
    expl = grad.abs() if absolute else grad
    return expl

maxidl

from functools import partial
import types

import torch
from typing import List, Optional, Tuple, Union, Dict
import transformers
from transformers.modeling_outputs import BaseModelOutputWithPast
from transformers.utils import logging as hf_logging

logger = hf_logging.get_logger(__name__)