Python Generators and Random Number Generation Quiz

bernoulli = Draws binary random numbers (0 or 1) from a Bernoulli distribution normal = Returns a tensor of random numbers drawn from separate normal distributions whose mean and standard deviation are given randint = Returns a tensor filled with random integers generated uniformly between low (inclusive) and high (exclusive) poisson = Returns a tensor of the same size as input with each element sampled from a Poisson distribution with rate parameter given by the corresponding element in input

manual_seed = Sets the seed for generating random numbers get_rng_state = Returns the random number generator state as a torch.ByteTensor set_rng_state = Sets the random number generator state torch.default_generator = Returns the default CPU torch.Generator

rand = Returns a tensor filled with random numbers from a uniform distribution on the interval $[ 0 , 1 )$ rand_like = Returns a tensor with the same size as input that is filled with random numbers from a uniform distribution on the interval $[ 0 , 1 )$ multinomial = Returns a tensor where each row contains num_samples indices sampled from the multinomial probability distribution located in the corresponding row of tensor input randint_like = Returns a tensor with the same shape as Tensor input filled with random integers generated uniformly between low (inclusive) and high (exclusive)

<p>torch.Tensor.bernoulli_() = Bernoulli distribution torch.Tensor.cauchy_() = Cauchy distribution torch.Tensor.exponential_() = Exponential distribution torch.Tensor.geometric_() = Geometric distribution</p> Signup and view all the answers

<p>torch.quasirandom.SobolEngine = An engine for generating (scrambled) Sobol sequences torch.save() = Saves an object to a disk file get_num_threads = Returns the number of threads used for parallelizing CPU operations set_num_threads = Sets the number of threads used for intraop parallelism on CPU</p> Signup and view all the answers

<p>get_num_interop_threads = Returns the number of threads used for inter-op parallelism on CPU set_num_interop_threads = Sets the number of threads used for interop parallelism torch.Tensor.log_normal_() = Samples from the log-normal distribution torch.Tensor.uniform_() = Numbers sampled from the continuous uniform distribution</p> Signup and view all the answers

<p>torch.no_grad() = Context-manager that disables gradient calculation torch.enable_grad() = Context-manager that enables gradient calculation torch.set_grad_enabled() = Context-manager that sets gradient calculation on or off torch.is_grad_enabled() = Returns True if grad mode is currently enabled</p> Signup and view all the answers

<p>x = torch.zeros(1, requires_grad=True) = Creates a tensor with gradient computation enabled with torch.no_grad(): y = x * 2 = Performs a computation with gradient calculation disabled with torch.set_grad_enabled(is_train): y = x * 2 = Performs a computation with gradient calculation set according to the is_train variable torch.set_grad_enabled(False) = Globally disables gradient computation</p> Signup and view all the answers

<p>y = x * 2; y.requires_grad = Returns True if x requires gradient and gradient computation is enabled with torch.no_grad(): y = x * 2; y.requires_grad = Returns False, as gradient computation is disabled within the block with torch.set_grad_enabled(is_train): y = x * 2; y.requires_grad = Returns the value of is_train, as gradient computation is set according to the is_train variable within the block torch.set_grad_enabled(False); y = x * 2; y.requires_grad = Returns False, as gradient computation is globally disabled</p> Signup and view all the answers

<p>torch.abs() = Computes the absolute value of each element in input. torch.acos() = Computes the inverse cosine of each element in input. torch.add() = Adds other, scaled by alpha, to input. torch.angle() = Computes the element-wise angle (in radians) of the given input tensor.</p> Signup and view all the answers

<p>torch.asin() = Returns a new tensor with the arcsine of the elements of input. torch.atan() = Returns a new tensor with the arctangent of the elements of input. torch.addcdiv() = Performs the element-wise division of tensor1 by tensor2, multiplies the result by the scalar value and adds it to input. torch.addcmul() = Performs the element-wise multiplication of tensor1 by tensor2, multiplies the result by the scalar value and adds it to input.</p> Signup and view all the answers

<p>torch.atan2() = Element-wise arctangent of input $\frac{input_i}{other_i}$ with consideration of the quadrant. torch.asinh() = Returns a new tensor with the inverse hyperbolic sine of the elements of input. torch.acosh() = Returns a new tensor with the inverse hyperbolic cosine of the elements of input. torch.atanh() = Returns a new tensor with the inverse hyperbolic tangent of the elements of input.</p> Signup and view all the answers

<p>bitwise_not = Computes the bitwise NOT of the given input tensor bitwise_and = Computes the bitwise AND of input and other bitwise_or = Computes the bitwise OR of input and other bitwise_xor = Computes the bitwise XOR of input and other</p> Signup and view all the answers

<p>bitwise_left_shift = Computes the left arithmetic shift of input by other bits bitwise_right_shift = Computes the right arithmetic shift of input by other bits ceil = Returns a new tensor with the ceil of the elements of input, the smallest integer greater than or equal to each element clamp = Clamps all elements in input into the range [ min, max ]</p> Signup and view all the answers

<p>clip = Alias for torch.clamp() conj_physical = Computes the element-wise conjugate of the given input tensor copysign = Create a new floating-point tensor with the magnitude of input and the sign of other, elementwise cos = Returns a new tensor with the cosine of the elements of input</p> Signup and view all the answers

<p>cosh = Returns a new tensor with the hyperbolic cosine of the elements of input deg2rad = Returns a new tensor with each of the elements of input converted from angles in degrees to radians div = Divides each element of the input input by the corresponding element of other divide = Alias for torch.div()</p> Signup and view all the answers

<p>digamma = Alias for torch.special.digamma() erf = Alias for torch.special.erf() erfc = Alias for torch.special.erfc() erfinv = Alias for torch.special.erfinv()</p> Signup and view all the answers

<p>exp = Returns a new tensor with the exponential of the elements of the input tensor input exp2 = Alias for torch.special.exp2() expm1 = Alias for torch.special.expm1() fake_quantize_per_channel_affine = Returns a new tensor with the data in input fake quantized per channel using scale, zero_point, quant_min and quant_max, across the channel specified by axis</p> Signup and view all the answers

<p>fake_quantize_per_tensor_affine = Returns a new tensor with the data in input fake quantized using scale, zero_point, quant_min and quant_max. float_power = Raises input to the power of exponent, elementwise, in double precision. gradient = Estimates the gradient of a function in one or more dimensions using the second-order accurate central differences method. ldexp = Multiplies input by $2^{\text{other}}$.</p> Signup and view all the answers

<p>lgamma = Computes the natural logarithm of the absolute value of the gamma function on input. log1p = Returns a new tensor with the natural logarithm of $(1 + \text{input})$. logaddexp2 = Logarithm of the sum of exponentiations of the inputs in base-2. logical_not = Computes the element-wise logical NOT of the given input tensor.</p> Signup and view all the answers

<p>hypot = Given the legs of a right triangle, return its hypotenuse. mul = Multiplies input by other. nan_to_num = Replaces NaN, positive infinity, and negative infinity values in input with the values specified by nan, posinf, and neginf, respectively. negative = Returns a new tensor with the negative of the elements of input.</p> Signup and view all the answers

<p>pow = Takes the power of each element in input with exponent and returns a tensor with the result. quantized_max_pool1d = Applies a 1D max pooling over an input quantized tensor composed of several input planes. reciprocal = Returns a new tensor with the reciprocal of the elements of input remainder = Computes Python's modulus operation entrywise.</p> Signup and view all the answers

<p>rsqrt = Returns a new tensor with the reciprocal of the square-root of each of the elements of input. sign = Returns a new tensor with the signs of the elements of input. sin = Returns a new tensor with the sine of the elements of input. sqrt = Returns a new tensor with the square-root of the elements of input.</p> Signup and view all the answers

<p>sub = Subtracts other, scaled by alpha, from input. tan = Returns a new tensor with the tangent of the elements of input. tanh = Returns a new tensor with the hyperbolic tangent of the elements of input. true_divide = Alias for torch.div() with rounding_mode=None.</p> Signup and view all the answers

<p>lerp = Does a linear interpolation of two tensors start (given by input) and end based on a scalar or tensor weight and returns the resulting out tensor. log = Returns a new tensor with the natural logarithm of the elements of input. log10 = Returns a new tensor with the logarithm to the base 10 of the elements of input. log2 = Returns a new tensor with the logarithm to the base 2 of the elements of input.</p> Signup and view all the answers

<p>logit = Alias for torch.special.logit(). i0 = Alias for torch.special.i0(). igamma = Alias for torch.special.gammainc(). igammac = Alias for torch.special.gammaincc().</p> Signup and view all the answers

<p>mvlgamma = Alias for torch.special.multigammaln(). nextafter = Return the next floating-point value after input towards other, elementwise. polygamma = Alias for torch.special.polygamma(). positive = Returns input.</p> Signup and view all the answers

<p>quantized_batch_norm = Applies batch normalization on a 4D (NCHW) quantized tensor. quantized_max_pool2d = Applies a 2D max pooling over an input quantized tensor composed of several input planes. rad2deg = Returns a new tensor with each of the elements of input converted from angles in radians to degrees. real = Returns a new tensor containing real values of the self tensor.</p> Signup and view all the answers

<p>fake_quantize_per_tensor_affine = Returns a new tensor with the data in input fake quantized using scale, zero_point, quant_min, and quant_max. float_power = Raises input to the power of exponent, elementwise, in double precision. ldexp = Multiplies input by $2^{other}$. logical_xor = Computes the element-wise logical XOR of the given input tensors.</p> Signup and view all the answers

<p>log = Returns a new tensor with the natural logarithm of the elements of input. mul = Multiplies input by other. nan_to_num = Replaces NaN, positive infinity, and negative infinity values in input with the values specified by nan, posinf, and neginf, respectively. reciprocal = Returns a new tensor with the reciprocal of the elements of input.</p> Signup and view all the answers

<p>real = Returns a new tensor containing real values of the self tensor. quantized_max_pool2d = Applies a 2D max pooling over an input quantized tensor composed of several input planes. rsqrt = Returns a new tensor with the reciprocal of the square-root of each of the elements of input. sign = Returns a new tensor with the signs of the elements of input.</p> Signup and view all the answers

<p>sin = Returns a new tensor with the sine of the elements of input. sqrt = Returns a new tensor with the square-root of the elements of input. sub = Subtracts other, scaled by alpha, from input. tanh = Returns a new tensor with the hyperbolic tangent of the elements of input.</p> Signup and view all the answers

<p>logit = Alias for torch.special.logit(). lgamma = Computes the natural logarithm of the absolute value of the gamma function on input. quantized_batch_norm = Applies batch normalization on a 4D (NCHW) quantized tensor. floor_divide = Applies C++'s std::fmod entrywise.</p> Signup and view all the answers

<p>lerp = Does a linear interpolation of two tensors start (given by input) and end based on a scalar or tensor weight and returns the resulting out tensor. logaddexp2 = Logarithm of the sum of exponentiations of the inputs in base-2. sigmoid = Alias for torch.special.expit(). hypot = Given the legs of a right triangle, return its hypotenuse.</p> Signup and view all the answers

<p>log1p = Returns a new tensor with the natural logarithm of (1 + input). log10 = Returns a new tensor with the logarithm to the base 10 of the elements of input. log2 = Returns a new tensor with the logarithm to the base 2 of the elements of input. logaddexp = Logarithm of the sum of exponentiations of the inputs.</p> Signup and view all the answers

<p>gradient = Estimates the gradient of a function $g : R^n \rightarrow R$ in one or more dimensions using the second-order accurate central differences method. imag = Returns a new tensor containing imaginary values of the self tensor. frac = Computes the fractional portion of each element in input. frexp = Decomposes input into mantissa and exponent tensors such that $input = mantissa \times 2^{exponent}$.</p> Signup and view all the answers

<p>floor = Returns a new tensor with the floor of the elements of input, the largest integer less than or equal to each element. fmod = Applies C++'s std::fmod entrywise. rad2deg = Returns a new tensor with each of the elements of input converted from angles in radians to degrees. square = Returns a new tensor with the square of the elements of input.</p> Signup and view all the answers

<p>nextafter = Return the next floating-point value after input towards other, elementwise. signbit = Tests if each element of input has its sign bit set or not. tan = Returns a new tensor with the tangent of the elements of input. true_divide = Alias for torch.div() with rounding_mode=None.</p> Signup and view all the answers

<p>fake_quantize_per_tensor_affine = Fake quantizes the data in input using scale, zero_point, quant_min and quant_max float_power = Raises input to the power of exponent, elementwise, in double precision log = Returns a new tensor with the natural logarithm of the elements of input mul = Multiplies input by other</p> Signup and view all the answers

<p>neg = Returns a new tensor with the negative of the elements of input log10 = Returns a new tensor with the logarithm to the base 10 of the elements of input ldexp = Multiplies input by 2 ** other logit = Alias for torch.special.logit()</p> Signup and view all the answers

<p>logical_and = Computes the element-wise logical AND of the given input tensors hypot = Given the legs of a right triangle, return its hypotenuse log2 = Returns a new tensor with the logarithm to the base 2 of the elements of input igamma = Alias for torch.special.gammainc()</p> Signup and view all the answers

<p>quantized_max_pool1d = Applies a 1D max pooling over an input quantized tensor composed of several input planes real = Returns a new tensor containing real values of the self tensor sin = Returns a new tensor with the sine of the elements of input tanh = Returns a new tensor with the hyperbolic tangent of the elements of input</p> Signup and view all the answers

<p>sqrt = Returns a new tensor with the square-root of the elements of input polygamma = Alias for torch.special.polygamma() floor = Returns a new tensor with the floor of the elements of input, the largest integer less than or equal to each element reciprocal = Returns a new tensor with the reciprocal of the elements of input</p> Signup and view all the answers

<p>sigmoid = Alias for torch.special.expit() logaddexp = Logarithm of the sum of exponentiations of the inputs sub = Subtracts other, scaled by alpha, from input round = Rounds elements of input to the nearest integer</p> Signup and view all the answers

<p>tan = Returns a new tensor with the tangent of the elements of input imag = Returns a new tensor containing imaginary values of the self tensor logaddexp2 = Logarithm of the sum of exponentiations of the inputs in base-2 gradient = Estimates the gradient of a function in one or more dimensions using the second-order accurate central differences method</p> Signup and view all the answers

<p>log1p = Returns a new tensor with the natural logarithm of (1 + input) lerp = Does a linear interpolation of two tensors start (given by input) and end based on a scalar or tensor weight and returns the resulting out tensor lgamma = Computes the natural logarithm of the absolute value of the gamma function on input rsqrt = Returns a new tensor with the reciprocal of the square-root of each of the elements of input</p> Signup and view all the answers

<p>nan_to_num = Replaces NaN, positive infinity, and negative infinity values in input with the values specified by nan, posinf, and neginf, respectively signbit = Tests if each element of input has its sign bit set or not quantized_max_pool2d = Applies a 2D max pooling over an input quantized tensor composed of several input planes remainder = Computes Python's modulus operation entrywise</p> Signup and view all the answers

<p>sign = Returns a new tensor with the signs of the elements of input nextafter = Return the next floating-point value after input towards other, elementwise logical_xor = Computes the element-wise logical XOR of the given input tensors frexp = Decomposes input into mantissa and exponent tensors such that input = mantissa × 2 exponent input=mantissa×2 exponent</p> Signup and view all the answers