initdl 0.1.0__tar.gz

initdl-0.1.0/PKG-INFO

@@ -0,0 +1,7 @@
+Metadata-Version: 2.4
+Name: initdl
+Version: 0.1.0
+Summary: sss
+Author: sss
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown

initdl-0.1.0/initdl/__init__.py

@@ -0,0 +1,3 @@
+from .experiments import ex1, ex2, ex3, ex4, ex5a, ex5b, ex6a, ex6b, ex6c, ex7, ex8, ex9, create_all
+
+__version__ = "0.1.0"

initdl-0.1.0/initdl/experiments.py

@@ -0,0 +1,326 @@
+import os
+
+def _write(filename, code):
+    with open(filename, "w", encoding="utf-8") as f:
+        f.write(code)
+
+
+def ex1():
+    code = '''
+EX1: DEEP NEURAL NETWORK
+REQUIRED LIBRARIES: numpy, tensorflow, matplotlib
+
+import numpy as np
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import layers
+import matplotlib.pyplot as plt
+
+x=np.array([0,1,2,3,4,5],dtype=float)
+y=3*x+2
+
+model=keras.Sequential([layers.Dense(1,input_shape=[1])])
+model.compile(optimizer='adam',loss='mse')
+
+history=model.fit(x,y,epochs=500,verbose=0)
+
+weights=model.layers[0].get_weights()
+print("Learned weight (slope):",weights[0][0][0])
+print("Learned bias:",weights[1][0])
+
+test_value=np.array([10.0])
+prediction=model.predict(test_value)[0][0]
+print("Prediction for x=10:",prediction)
+
+plt.plot(history.history['loss'])
+plt.xlabel("Epochs")
+plt.ylabel("Loss")
+plt.title("Training Loss Curve")
+plt.show()
+'''
+    _write("ex1.py", code)
+
+
+def ex2():
+    code = '''
+EX2: SPEECH TO TEXT
+REQUIRED LIBRARIES: speechrecognition
+
+import speech_recognition as sr
+
+r=sr.Recognizer()
+
+with sr.AudioFile("audio.wav") as source:
+    audio=r.record(source)
+
+try:
+    text=r.recognize_google(audio)
+    print("Recognized text:",text)
+except sr.UnknownValueError:
+    print("Sorry, could not understand the audio")
+except sr.RequestError as e:
+    print("Could not request results;",e)
+'''
+    _write("ex2.py", code)
+
+
+def ex3():
+    code = '''
+EX3: TEXT TO SPEECH
+REQUIRED LIBRARIES: pyttsx3
+
+import pyttsx3
+
+engine=pyttsx3.init()
+engine.setProperty('rate',170)
+engine.setProperty('volume',0.9)
+
+voices=engine.getProperty('voices')
+engine.setProperty('voice',voices[1].id)
+
+text=input("Enter the text to convert to speech: ")
+
+engine.say(text)
+engine.runAndWait()
+'''
+    _write("ex3.py", code)
+
+
+def ex4():
+    code = '''
+EX4: TIME SERIES FORECASTING WITH LSTM
+REQUIRED LIBRARIES: numpy, pandas, matplotlib, scikit-learn, tensorflow
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.preprocessing import MinMaxScaler
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM,Dense
+
+time=np.arange(0,100,0.1)
+data=np.sin(time)
+
+df=pd.DataFrame(data,columns=['value'])
+
+scaler=MinMaxScaler(feature_range=(0,1))
+scaled_data=scaler.fit_transform(df)
+
+def create_sequences(data,time_step=10):
+    X=[]
+    y=[]
+    for i in range(len(data)-time_step):
+        X.append(data[i:i+time_step,0])
+        y.append(data[i+time_step,0])
+    return np.array(X),np.array(y)
+
+time_step=10
+
+X,y=create_sequences(scaled_data,time_step)
+X=X.reshape(X.shape[0],X.shape[1],1)
+
+train_size=int(len(X)*0.8)
+
+X_train=X[:train_size]
+X_test=X[train_size:]
+
+y_train=y[:train_size]
+y_test=y[train_size:]
+
+model=Sequential()
+model.add(LSTM(50,input_shape=(time_step,1)))
+model.add(Dense(1))
+
+model.compile(loss='mean_squared_error',optimizer='adam')
+
+model.fit(X_train,y_train,epochs=10,batch_size=32)
+
+plt.plot(df.values)
+plt.show()
+'''
+    _write("ex4.py", code)
+
+
+def ex5a():
+    code = '''
+EX5A: FEEDFORWARD NEURAL NETWORK FOR SINGLE LOGIC GATE
+REQUIRED LIBRARIES: numpy, tensorflow
+
+import numpy as np
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense,Input
+
+inputs=np.array([[0,0],[0,1],[1,0],[1,1]])
+outputs=np.array([[0],[1],[1],[0]])
+
+model=Sequential([
+Input(shape=(2,)),
+Dense(4,activation='relu'),
+Dense(1,activation='sigmoid')
+])
+
+model.compile(optimizer='adam',loss='binary_crossentropy')
+model.fit(inputs,outputs,epochs=3000,verbose=0)
+'''
+    _write("ex5a.py", code)
+
+
+def ex5b():
+    code = '''
+EX5B: FEEDFORWARD NEURAL NETWORK FOR MULTIPLE LOGIC GATES
+REQUIRED LIBRARIES: numpy, tensorflow
+
+import numpy as np
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense,Input
+
+inputs=np.array([[0,0],[0,1],[1,0],[1,1]])
+
+outputs=np.array([
+[0,0,0],
+[0,1,1],
+[0,1,1],
+[1,1,0]
+])
+
+model=Sequential([
+Input(shape=(2,)),
+Dense(6,activation='relu'),
+Dense(3,activation='sigmoid')
+])
+
+model.compile(optimizer='adam',loss='binary_crossentropy')
+model.fit(inputs,outputs,epochs=4000,verbose=0)
+'''
+    _write("ex5b.py", code)
+
+
+def ex6a():
+    code = '''
+EX6A: RGB TO GRAYSCALE
+REQUIRED LIBRARIES: scikit-image, matplotlib
+
+from skimage import data
+from skimage.color import rgb2gray
+import matplotlib.pyplot as plt
+
+coffee=data.coffee()
+
+plt.imshow(rgb2gray(coffee),cmap="gray")
+plt.show()
+'''
+    _write("ex6a.py", code)
+
+
+def ex6b():
+    code = '''
+EX6B: RGB TO HSV
+REQUIRED LIBRARIES: scikit-image, matplotlib
+
+from skimage import data
+from skimage.color import rgb2hsv
+import matplotlib.pyplot as plt
+
+coffee=data.coffee()
+
+plt.imshow(rgb2hsv(coffee))
+plt.show()
+'''
+    _write("ex6b.py", code)
+
+
+def ex6c():
+    code = '''
+EX6C: SUPERVISED SEGMENTATION
+REQUIRED LIBRARIES: scikit-image, matplotlib
+
+from skimage import data
+from skimage.color import rgb2gray
+import matplotlib.pyplot as plt
+
+coffee=data.coffee()
+gray=rgb2gray(coffee)
+
+plt.imshow(gray>0.5,cmap='gray')
+plt.show()
+'''
+    _write("ex6c.py", code)
+
+
+def ex7():
+    code = '''
+EX7: OBJECT DETECTION USING YOLO
+REQUIRED LIBRARIES: ultralytics, opencv-python
+
+from ultralytics import YOLO
+import cv2
+
+model=YOLO("yolov8n.pt")
+results=model("nun.jpg")
+
+for r in results:
+    cv2.imshow("Result",r.plot())
+    cv2.waitKey(0)
+
+cv2.destroyAllWindows()
+'''
+    _write("ex7.py", code)
+
+
+def ex8():
+    code = '''
+EX8: CHARACTER RECOGNITION USING CNN
+REQUIRED LIBRARIES: tensorflow, numpy, opencv-python, matplotlib
+
+import tensorflow as tf
+from tensorflow.keras import layers,models
+import numpy as np
+import cv2
+import matplotlib.pyplot as plt
+
+(x_train,y_train),(x_test,y_test)=tf.keras.datasets.mnist.load_data()
+
+x_train=x_train/255.0
+x_train=x_train.reshape((-1,28,28,1))
+
+model=models.Sequential([
+layers.Conv2D(32,(3,3),activation='relu',input_shape=(28,28,1)),
+layers.MaxPooling2D(),
+layers.Flatten(),
+layers.Dense(10,activation='softmax')
+])
+
+model.compile(optimizer='adam',loss='sparse_categorical_crossentropy')
+model.fit(x_train,y_train,epochs=3)
+'''
+    _write("ex8.py", code)
+
+
+def ex9():
+    code = '''
+EX9: AUTOENCODER USING MNIST
+REQUIRED LIBRARIES: tensorflow, numpy, matplotlib
+
+import numpy as np
+import matplotlib.pyplot as plt
+from tensorflow.keras.datasets import mnist
+from tensorflow.keras.layers import Input,Dense
+from tensorflow.keras.models import Model
+
+(x_train,_),(x_test,_)=mnist.load_data()
+
+x_train=x_train/255.0
+x_train=x_train.reshape((len(x_train),784))
+
+input_img=Input(shape=(784,))
+encoded=Dense(32,activation='relu')(input_img)
+decoded=Dense(784,activation='sigmoid')(encoded)
+
+model=Model(input_img,decoded)
+model.compile(optimizer='adam',loss='binary_crossentropy')
+model.fit(x_train,x_train,epochs=5)
+
+plt.imshow(x_train[0].reshape(28,28),cmap='gray')
+plt.show()
+'''
+    _write("ex9.py", code)

initdl-0.1.0/initdl.egg-info/PKG-INFO

@@ -0,0 +1,7 @@
+Metadata-Version: 2.4
+Name: initdl
+Version: 0.1.0
+Summary: sss
+Author: sss
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown

initdl-0.1.0/initdl.egg-info/SOURCES.txt

@@ -0,0 +1,7 @@
+pyproject.toml
+initdl/__init__.py
+initdl/experiments.py
+initdl.egg-info/PKG-INFO
+initdl.egg-info/SOURCES.txt
+initdl.egg-info/dependency_links.txt
+initdl.egg-info/top_level.txt

initdl-0.1.0/initdl.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

initdl-0.1.0/initdl.egg-info/top_level.txt

@@ -0,0 +1 @@
+initdl

initdl-0.1.0/pyproject.toml

@@ -0,0 +1,11 @@
+[project]
+name = "initdl"
+version = "0.1.0"
+description = "sss"
+readme = "README.md"
+authors = [{ name = "sss" }]
+requires-python = ">=3.7"
+
+dependencies = [
+    
+]

initdl-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+