我正在為TwoStream-IQA編寫訓練代碼，它是一個雙流卷積神經網絡。該模型通過網絡的兩個流預測正在評估的補丁的質量分數。在下面的培訓中，我使用了上面 GitHub 鏈接中提供的測試數據集。訓練代碼如下：import osimport timeimport numpy as npimport argparseimport chainerchainer.global_config.train=Truefrom chainer import cudafrom chainer import serializersfrom chainer import optimizersfrom chainer import iteratorsfrom chainer import training from chainer.training import extensionsfrom PIL import Imagefrom sklearn.feature_extraction.image import extract_patchesfrom model import Modelparser = argparse.ArgumentParser(description='train.py')parser.add_argument('--model', '-m', default='', help='path to the trained model')parser.add_argument('--gpu', '-g', default=0, type=int, help='GPU ID')args = parser.parse_args()model = Model()cuda.cudnn_enabled = Truecuda.check_cuda_available()xp = cuda.cupymodel.to_gpu()## prepare training data test_label_path = 'data_list/test.txt'test_img_path = 'data/live/'test_Graimg_path = 'data/live_grad/'save_model_path = '/models/nr_sana_2stream.model'patches_per_img = 256patchSize = 32print('-------------Load data-------------')final_train_set = []with open(test_label_path, 'rt') as f: for l in f: line, la = l.strip().split() # for debug tic = time.time() full_path = os.path.join(test_img_path, line) Grafull_path = os.path.join(test_Graimg_path, line) inputImage = Image.open(full_path) Graf = Image.open(Grafull_path) img = np.asarray(inputImage, dtype=np.float32) Gra = np.asarray(Graf, dtype=np.float32) img = img.transpose(2, 0, 1) Gra = Gra.transpose(2, 0, 1) img1 = np.zeros((1, 3, Gra.shape[1], Gra.shape[2])) img1[0, :, :, :] = img Gra1 = np.zeros((1, 3, Gra.shape[1], Gra.shape[2])) Gra1[0, :, :, :] = Gra
2 回答
MM們
TA貢獻1886條經驗 獲得超2個贊
簡而言之，您不恰當地調用numpy.asarray:numpy.asarray不連接兩個cupy.ndarrays，而連接兩個numpy.ndarrays。
您的代碼簡介：
import numpy, cupy
final_train_set = []
N_PATCH_PER_IMAGE = 8
for i in range(10):
label = 0
temp_slice_1 = [numpy.zeros((3, 3)) for j in range(N_PATCH_PER_IMAGE)]
temp_slice_2 = [numpy.zeros((3, 3)) for j in range(N_PATCH_PER_IMAGE)]
for j in range(N_PATCH_PER_IMAGE):
temp_slice_1[j] = cupy.array(temp_slice_1[j])
temp_slice_2[j] = cupy.array(temp_slice_2[j])
final_train_set.append(
[
# attempting to concatenate two cupy arrays by numpy.asarray
numpy.asarray([temp_slice_1[j], temp_slice_2[j]]),
label
]
)
錯誤
import numpy as np
import cupy as cp
print("two numpy arrays")
print(np.asarray([np.zeros(shape=(1,)), np.zeros(shape=(1,))]))
print(np.asarray([np.zeros(shape=(1,)), np.zeros(shape=(1,))]).dtype)
print()
print("two cupy arrays")
print(np.asarray([cp.zeros(shape=(1,)), cp.zeros(shape=(1,))]))
print(np.asarray([cp.zeros(shape=(1,)), cp.zeros(shape=(1,))]).dtype)
two numpy arrays
[[0.]
[0.]]
float64
two cupy arrays
[[array(0.)]
[array(0.)]]
object
解決方法：注釋掉兩行
import numpy # not import cupy here
for i in range(10):
label = 0
temp_slice_1 = [numpy.zeros((3, 3)) for j in range(N_PATCH_PER_IMAGE)]
temp_slice_2 = [numpy.zeros((3, 3)) for j in range(N_PATCH_PER_IMAGE)]
for j in range(N_PATCH_PER_IMAGE):
# temp_slice_1[j] = cupy.array(temp_slice_1[j]) <- comment out!
# temp_slice_2[j] = cupy.array(temp_slice_2[j]) <- comment out!
final_train_set.append(
[
# concatenate two numpy arrays: usually cupy should not be used in dataset
numpy.asarray([temp_slice_1[j], temp_slice_2[j]]),
label
]
)
腳注
在您提供的代碼中，
xp未指定，因此您無法從任何人那里得到答案。如果您無法分離問題，請發布您的代碼的整體，包括模型。我猜您可能由于其他原因無法運行訓練代碼。在這段代碼中，數據首先在
final_train_set. 但是如果圖像數量很大，主內存就會耗盡并被MemoryError抬高。（換句話說，如果圖像數量很少，并且您的內存足夠大，則不會發生錯誤）在這種情況下，以下參考資料（Chainer at glass和Dataset Abstraction）會有所幫助。
千巷貓影
TA貢獻1829條經驗 獲得超7個贊
我使用 OpenCV、Scipy 和其他一些用于質量評估的模塊找到了這個Github 存儲庫。這是代碼：
# Python code for BRISQUE model
# Original paper title: No-Reference Image Quality Assessment in the Spatial Domain
# Link: http://ieeexplore.ieee.org/document/6272356/
import cv2
import numpy as np
from scipy import ndimage
import math
def get_gaussian_filter():
[m,n] = [(ss - 1.0) / 2.0 for ss in (shape,shape)]
[y,x] = np.ogrid[-m:m+1,-n:n+1]
window = np.exp( -(x*x + y*y) / (2.0*sigma*sigma) )
window[window < np.finfo(window.dtype).eps*window.max() ] = 0
sum_window = window.sum()
if sum_window != 0:
window = np.divide(window, sum_window)
return window
def lmom(X):
(rows, cols) = X.shape
if cols == 1:
X = X.reshape(1,rows)
n = rows
X.sort()
b = np.zeros(3)
b0 = X.mean()
for r in range(1,4):
Num = np.prod(np.tile(np.arange(r+1,n+1), (r,1))-np.tile(np.arange(1,r+1).reshape(r,1),(1,n-r)),0)
Num = Num.astype(np.float)
Den = np.prod(np.tile(n, (1, r)) - np.arange(1,r+1), 1)
b[r-1] = 1.0/n * sum(Num/Den * X[0,r:])
L = np.zeros(4)
L[0] = b0
L[1] = 2*b[0] - b0
L[2] = 6*b[1] - 6*b[0] + b0
L[3] = 20*b[2] - 30*b[1] + 12*b[0] - b0
return L
def compute_features(im):
im = im.astype(np.float)
window = get_gaussian_filter()
scalenum = 2
feat = []
for itr_scale in range(scalenum):
mu = cv2.filter2D(im, cv2.CV_64F, window, borderType=cv2.BORDER_CONSTANT)
mu_sq = mu * mu
sigma = np.sqrt(abs(cv2.filter2D(im*im, cv2.CV_64F, window, borderType=cv2.BORDER_CONSTANT) - mu_sq))
structdis = (im-mu)/(sigma+1)
structdis_col_vector = np.reshape(structdis.transpose(), (structdis.size,1))
L = lmom(structdis.reshape(structdis.size,1))
feat = np.append(feat,[L[1], L[3]])
shifts = [[0,1], [1,0], [1,1], [-1,1]]
for itr_shift in shifts:
shifted_structdis = np.roll(structdis, itr_shift[0], axis=0)
shifted_structdis = np.roll(shifted_structdis, itr_shift[1], axis=1)
shifted_structdis_col_vector = np.reshape(shifted_structdis.T, (shifted_structdis.size,1))
pair = structdis_col_vector * shifted_structdis_col_vector
L = lmom(pair.reshape(pair.size,1))
feat = np.append(feat, L)
im = cv2.resize(im, (0,0), fx=0.5, fy=0.5, interpolation=cv2.INTER_CUBIC)
return feat
im = ndimage.imread('example.bmp', flatten=True)
feat = compute_features(im)
print feat
添加回答
舉報
0/150
提交
取消