aryan-jadon

name: tensorflow
channels:
  - apple
  - conda-forge
dependencies:
    - python=3.9
    - pip>=19.0
    - jupyter
    - tensorflow-deps
    - scikit-learn

aryan-jadon

# What version of Python do you have?
import sys

import tensorflow.keras
import pandas as pd
import sklearn as sk
import tensorflow as tf
import platform

print(f"Python Platform: {platform.platform()}")

aryan-jadon

name: torch
channels:
  - pytorch-nightly
  - conda-forge
dependencies:
    - python=3.9
    - pip>=19.0
    - pytorch 
    - torchvision 
    - jupyter

aryan-jadon

# What version of Python do you have?
import sys
import platform
import torch
import pandas as pd
import sklearn as sk

has_gpu = torch.cuda.is_available()
has_mps = getattr(torch,'has_mps',False)
device = "mps" if getattr(torch,'has_mps',False) \

aryan-jadon

import io
import copy
import torch

# Make use of a GPU or MPS (Apple) if one is available.
device = "mps" if getattr(torch,'has_mps',False) \
    else "cuda" if torch.cuda.is_available() else "cpu"
    

class EarlyStopping():

aryan-jadon

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from torch.autograd import Variable
from sklearn import preprocessing
from torch.utils.data import DataLoader, TensorDataset

aryan-jadon

from sklearn.metrics import accuracy_score

pred = model(x_test)
vloss = loss_fn(pred, y_test)
print(f"Loss = {vloss}")

## Loss = 0.5756629109382629

pred = model(x_test)
_, predict_classes = torch.max(pred, 1)

aryan-jadon

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from torch.autograd import Variable
from sklearn import preprocessing
from torch.utils.data import DataLoader, TensorDataset

aryan-jadon

from sklearn import metrics

# Measure RMSE error.  RMSE is common for regression.
pred = model(x_test)
score = torch.sqrt(torch.nn.functional.mse_loss(pred.flatten(),y_test))
print(f"Final score (RMSE): {score}")

## Final score (RMSE): 3.3968639373779297

aryan-jadon