paddle易错总结
paddle易错总结
aistudio可能的错误（这个真）
import文件夹模块错误
%env PYTHONPATH=.:$PYTHONPATH
%env CUDA_VISIBLE_DEVICES=0
二次求导：
y=x**2
# 这样的式子无法进行二次求导，必须写成
y=x*x
roi_align
这个api，boxes_num，如果应对的是batch大于1，这里要传入list，指定每个batch的num
transform里面的图片调整
这个神奇的框架，居然不支持自己的tensor传入
于是只能自己实现了：
import cv2
import math
import numpy as np
import random
import os
import paddle
import paddle.nn.functional as F
from paddle.vision.transforms.functional import normalize
def _blend(img1, img2, ratio):
ratio = float(ratio)
bound = 1.0 if paddle.is_floating_point(img1) else 255.0
# print(bound)
return (ratio * img1 + (1.0 - ratio) * img2).clip(0, bound)
def _get_image_num_channels(img):
if img.ndim == 2:
return 1
elif img.ndim > 2:
return img.shape[-3]
raise TypeError("Input ndim should be 2 or more. Got {}".format(img.ndim))
def _rgb2hsv(img):
r, g, b = img.unbind(axis=-3)
# Implementation is based on https://github.com/python-pillow/Pillow/blob/4174d4267616897df3746d315d5a2d0f82c656ee/
# src/libImaging/Convert.c#L330
maxc = paddle.max(img, axis=-3)
minc = paddle.min(img, axis=-3)
# The algorithm erases S and H channel where `maxc = minc`. This avoids NaN
# from happening in the results, because
# + S channel has division by `maxc`, which is zero only if `maxc = minc`
# + H channel has division by `(maxc - minc)`.
#
# Instead of overwriting NaN afterwards, we just prevent it from occuring so
# we don't need to deal with it in case we save the NaN in a buffer in
# backprop, if it is ever supported, but it doesn't hurt to do so.
eqc = maxc == minc
cr = maxc - minc
# Since `eqc => cr = 0`, replacing denominator with 1 when `eqc` is fine.
ones = paddle.ones_like(maxc)
s = cr / paddle.where(eqc, ones, maxc)
# Note that `eqc => maxc = minc = r = g = b`. So the following calculation
# of `h` would reduce to `bc - gc + 2 + rc - bc + 4 + rc - bc = 6` so it
# would not matter what values `rc`, `gc`, and `bc` have here, and thus
# replacing denominator with 1 when `eqc` is fine.
cr_divisor = paddle.where(eqc, ones, cr)
rc = (maxc - r) / cr_divisor
gc = (maxc - g) / cr_divisor
bc = (maxc - b) / cr_divisor
t_zero=paddle.zeros_like(bc)
hr=paddle.where(maxc == r, (bc - gc), t_zero)
hg=paddle.where((maxc == g) & (maxc != r), (2.0 + rc - bc), t_zero)
hb=paddle.where((maxc != g) & (maxc != r), (4.0 + gc - rc), t_zero)
h = (hr + hg + hb)
h = paddle.mod((h / 6.0 + 1.0), paddle.to_tensor([1.0]))
return paddle.stack((h, s, maxc), axis=-3)
def _hsv2rgb(img):
h, s, v = img.unbind(axis=-3)
i = paddle.floor(h * 6.0)
f = (h * 6.0) - i
i=paddle.cast(i,dtype='int32')
p = paddle.clip((v * (1.0 - s)), 0.0, 1.0)
q = paddle.clip((v * (1.0 - s * f)), 0.0, 1.0)
t = paddle.clip((v * (1.0 - s * (1.0 - f))), 0.0, 1.0)
i = i % 6
mask = i.unsqueeze(axis=-3) == paddle.arange(6).reshape([-1, 1, 1])
a1 = paddle.stack((v, q, p, p, t, v), axis=-3)
a2 = paddle.stack((t, v, v, q, p, p), axis=-3)
a3 = paddle.stack((p, p, t, v, v, q), axis=-3)
a4 = paddle.stack((a1, a2, a3), axis=-4)
t_zero=paddle.zeros_like(mask,dtype='float32')
t_ones=paddle.ones_like(mask,dtype='float32')
mask=paddle.where(mask,t_ones,t_zero)
return paddle.einsum("...ijk, ...xijk -> ...xjk", mask, a4)
def rgb_to_grayscale(img, num_output_channels = 1) :
if img.ndim < 3:
raise TypeError("Input image tensor should have at least 3 axisensions, but found {}".format(img.ndim))
if num_output_channels not in (1, 3):
raise ValueError('num_output_channels should be either 1 or 3')
r, g, b = img.unbind(axis=-3)
l_img = (0.2989 * r + 0.587 * g + 0.114 * b)
l_img = l_img.unsqueeze(axis=-3)
if num_output_channels == 3:
return l_img.expand(img.shape)
return l_img
def adjust_brightness(img, brightness_factor) :
if brightness_factor < 0:
raise ValueError('brightness_factor ({}) is not non-negative.'.format(brightness_factor))
return _blend(img, paddle.zeros_like(img), brightness_factor)
def adjust_contrast(img, contrast_factor) :
if contrast_factor < 0:
raise ValueError('contrast_factor ({}) is not non-negative.'.format(contrast_factor))
dtype = img.dtype if paddle.is_floating_point(img) else paddle.float32
mean = paddle.mean(paddle.cast(rgb_to_grayscale(img),dtype=dtype), axis=(-3, -2, -1), keepdim=True)
return _blend(img, mean, contrast_factor)
def adjust_hue(img, hue_factor) :
if not (-0.5 <= hue_factor <= 0.5):
raise ValueError('hue_factor ({}) is not in [-0.5, 0.5].'.format(hue_factor))
if not (isinstance(img, paddle.Tensor)):
raise TypeError('Input img should be Tensor image')
if _get_image_num_channels(img) == 1: # Match PIL behaviour
return img
orig_dtype = img.dtype
if img.dtype == paddle.uint8:
img = paddle.cast(img,dtype='float32') / 255.0
img = _rgb2hsv(img)
h, s, v = img.unbind(axis=-3)
h = (h + hue_factor) % 1.0
img = paddle.stack((h, s, v), axis=-3)
img_hue_adj = _hsv2rgb(img)
if orig_dtype == paddle.uint8:
img_hue_adj = paddle.cast(img_hue_adj * 255.0,dtype=orig_dtype)
return img_hue_adj
def adjust_saturation(img, saturation_factor) :
if saturation_factor < 0:
raise ValueError('saturation_factor ({}) is not non-negative.'.format(saturation_factor))
return _blend(img, rgb_to_grayscale(img), saturation_factor)