Tony363

Traceback (most recent call last):
  File "/root/sec_filings/scrap_links.py", line 68, in <module>
    main()
  File "/root/sec_filings/scrap_links.py", line 26, in main
    driver = webdriver.Chrome(executable_path=args.chrome_driver_path,options=options)
  File "/usr/local/lib/python3.10/dist-packages/selenium/webdriver/chrome/webdriver.py", line 76, in __init__
    RemoteWebDriver.__init__(
  File "/usr/local/lib/python3.10/dist-packages/selenium/webdriver/remote/webdriver.py", line 157, in __init__
    self.start_session(capabilities, browser_profile)
  File "/usr/local/lib/python3.10/dist-packages/selenium/webdriver/remote/webdriver.py", line 252, in start_session

Tony363

Traceback (most recent call last):
  File "scrap_links.py", line 67, in <module>
    main()
  File "scrap_links.py", line 26, in main
    driver = webdriver.Chrome(executable_path=args.chrome_driver_path,options=options)
  File "/home/seluser/.local/lib/python3.8/site-packages/selenium/webdriver/chrome/webdriver.py", line 76, in __init__
    RemoteWebDriver.__init__(
  File "/home/seluser/.local/lib/python3.8/site-packages/selenium/webdriver/remote/webdriver.py", line 157, in __init__
    self.start_session(capabilities, browser_profile)
  File "/home/seluser/.local/lib/python3.8/site-packages/selenium/webdriver/remote/webdriver.py", line 252, in start_session

Tony363

import os
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from datasets import load_dataset, DatasetDict,load_from_disk

def process(
    example:dict,
    transform:torchvision.transforms
)->dict:

Tony363

    def forward(self, mask_inputs, feat_dis_org_embed, feat_dis_scale_1_embed, feat_dis_scale_2_embed):
        # feat_dis_org_embed: batch x (C=384) x (H=24) x (W=32)
        # feat_dis_scale_1_embed: batch x (C=384) x (H=9) x (W=12)
        # feat_dis_scale_2_embed: batch x (C=384) x (H=5) x (W=7)
          
        # learnable scale embedding
        scale_org_embed = repeat(self.scale_org_embedding, '() c () () -> b c h w', b=self.config.batch_size, h=24, w=32)
        scale_1_embed = repeat(self.scale_1_embedding, '() c () () -> b c h w', b=self.config.batch_size, h=9, w=12)
        scale_2_embed = repeat(self.scale_1_embedding, '() c () () -> b c h w', b=self.config.batch_size, h=5, w=7)

Tony363

""" train model """
def train_epoch(config, epoch, model_transformer, model_backbone, criterion, optimizer, scheduler, train_loader):
    losses = []
    model_transformer.train()
    model_backbone.train()

    # input mask (batch_size x len_sqe+1)
    mask_inputs = torch.ones(config.batch_size, config.n_enc_seq+1).to(config.device)

    # save data for one epoch

Tony363

def _get_batch_logps(logits: torch.FloatTensor, labels: torch.LongTensor, average_log_prob: bool = False) -> torch.FloatTensor:
    """Compute the log probabilities of the given labels under the given logits.

    Args:
        logits: Logits of the model (unnormalized). Shape: (batch_size, sequence_length, vocab_size)
        labels: Labels for which to compute the log probabilities. Label tokens with a value of -100 are ignored. Shape: (batch_size, sequence_length)
        average_log_prob: If True, return the average log probability per (non-masked) token. Otherwise, return the sum of the log probabilities of the (non-masked) tokens.

    Returns:
        A tensor of shape (batch_size,) containing the average/sum log probabilities of the given labels under the given logits.

Tony363

def classification_report(y_test, y_pred):
    # calculate precision, recall, f1-score
    # TODO:
    cm = confusion_matrix(y_test,y_pred)
    precision = cm[1,1]/(cm[1,1] + cm[0,1])
    recall = cm[1,1]/(cm[1,1] + cm[1,0])
    f1 = 2*(precision * recall)/(precision + recall)
    acc = (cm[1,1] + cm[0,0]) / np.sum(cm.flatten())
    # end TODO
    return(precision,recall,f1,acc)

Tony363

class Loader(object):
    def __init__(
        self,
        non_flicker_dir: str,
        flicker_dir: str,
        labels: dict,
        batch_size: int,
        in_mem_batches: int,
    ) -> None:
        mp.set_start_method("spawn")

Tony363

def torch_training(
    ds_train: Streamer,
    ds_val: Streamer,
    model: nn.Module,
    optimizer: torch.optim.Optimizer,
    epochs: int = 1000,
    criterion=nn.BCELoss(),
    f1_torch=f1_score  # F1_Loss().cuda(),
) -> nn.Module:

Tony363

import torch
import numpy as np
import torch.nn as nn


class LSTMModel(nn.Module):
    def __init__(self, input_dim, hidden_dim, layer_dim, output_dim):
        super(LSTMModel, self).__init__()
        # Hidden dimensions
        self.hidden_dim = hidden_dim