vgoklani

def verify_ddp_weights_equal(model: torch.nn.Module, atol: float = 1e-5) -> None:
    if hasattr(model, "module"):
        model = model.module
    
    world_size = get_world_size()
    for name, param in model.named_parameters():
        gathered_param = gather(param).reshape((world_size, -1))
        absolute_diffs = (gathered_param[None, 0, :] - gathered_param).abs()
        rank_params_eq = (absolute_diffs < atol).all()
        assert rank_params_eq, f"❌ param [{name}] not equal - got max_absolute_diff={absolute_diffs.max()}"

vgoklani

from typing import Optional
import torch
import torch.nn as nn


@torch.no_grad()
def measure_time_device(
    model: nn.Module,
    dtype: Optional[torch.dtype] = torch.float32,
    num_repeats: Optional[int] = 100,

vgoklani

cimport cython
import numpy as np
cimport numpy as np
from sklearn.metrics import f1_score


@cython.boundscheck(False)
@cython.wraparound(False)
def f1_opt(np.ndarray[long, ndim=1] label, np.ndarray[double, ndim=1] preds):

vgoklani

Building custom layers in Keras

About Keras

Keras is currently one of the most commonly used deep learning libraries today. And part of the reason why it's so popular is its API. Keras was built as a high-level API for other deep learning libraries ie Keras as such does not perform low-level tensor operations, instead provides an interface to its backend which are built for such operations. This allows Keras to abstract a lot of the underlying details and allows the programmer to concentrate on the architecture of the model. Currently Keras supports Tensorflow, Theano and CNTK as its backends.

Let's see what I mean. Tensorflow is one of the backends used by Keras. Here's the code for MNIST classification in TensorFlow and Keras. Both models are nearly identical and applies to the same problem. But if you compare the codes you g

vgoklani

[
  {
    "url": "http://money.cnn.com",
    "rss": "http://rss.cnn.com/rss/money_topstories.rss"
  },
  {
    "url": "http://thehill.com",
    "rss": "http://thehill.com/rss/syndicator/19110"
  },
  {

vgoklani

from pymongo import MongoClient


try:
    client = MongoClient('localhost')
    db = client.searchfollow
except:
    print("Could not connect to MongoDB")

call = db.command("dbstats")

vgoklani

vgoklani

vgoklani

vgoklani