為CNN編寫培訓模型

Question

我正在編寫TwoStream-IQA的訓練代碼，它是一個雙流卷積神經網絡。 該模型預測通過兩個網絡流評估的補丁的質量得分。 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。

培訓代碼如下：

import os
import time
import numpy as np
import argparse

import chainer

chainer.global_config.train=True

from chainer import cuda
from chainer import serializers
from chainer import optimizers
from chainer import iterators
from chainer import training 
from chainer.training import extensions
from PIL import Image
from sklearn.feature_extraction.image import extract_patches

from model import Model

parser = 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 = True
cuda.check_cuda_available()
xp = cuda.cupy
model.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 = 256
patchSize = 32

print('-------------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

        patches = extract_patches(img, (3, patchSize, patchSize), patchSize)
        Grapatches = extract_patches(Gra, (3, patchSize, patchSize), patchSize)

        X = patches.reshape((-1, 3, patchSize, patchSize))
        GraX = Grapatches.reshape((-1, 3, patchSize, patchSize))

        temp_slice1 = [X[int(float(index))] for index in range(256)]
        temp_slice2 = [GraX[int(float(index))] for index in range(256)]
        ##############################################  
        for j in range(len(temp_slice1)):
            temp_slice1[j] = xp.array(temp_slice1[j].astype(np.float32))
            temp_slice2[j] = xp.array(temp_slice2[j].astype(np.float32))

            final_train_set.append((
                np.asarray((temp_slice1[j], temp_slice2[j])).astype(np.float32),
                int(la)
                ))      
        ##############################################  
print('--------------Done!----------------')

print('--------------Iterator!----------------')    
train_iter = iterators.SerialIterator(final_train_set, batch_size=4)
optimizer = optimizers.Adam()
optimizer.use_cleargrads()
optimizer.setup(model)

updater = training.StandardUpdater(train_iter, optimizer, device=0)

print('--------------Trainer!----------------') 
trainer = training.Trainer(updater, (50, 'epoch'), out='result')

trainer.extend(extensions.LogReport())

trainer.extend(extensions.PrintReport(['epoch', 'iteration', 'main/loss', 'elapsed_time']))

print('--------------Running trainer!----------------') 
trainer.run()

但代碼在行trainer.run()上產生錯誤：

-------------Load data-------------
--------------Done!----------------
--------------Iterator!----------------
--------------Trainer!----------------
--------------Running trainer!----------------
Exception in main training loop: Unsupported dtype object
Traceback (most recent call last):
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/trainer.py", line 316, in run
    update()
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
    self.update_core()
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/updaters/standard_updater.py", line 154, in update_core
    in_arrays = self.converter(batch, self.device)
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/dataset/convert.py", line 149, in concat_examples
    return to_device(device, _concat_arrays(batch, padding))
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/dataset/convert.py", line 37, in to_device
    return cuda.to_gpu(x, device)
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/backends/cuda.py", line 285, in to_gpu
    return _array_to_gpu(array, device_, stream)
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/backends/cuda.py", line 333, in _array_to_gpu
    return cupy.asarray(array)
  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/cupy/creation/from_data.py", line 60, in asarray
    return core.array(a, dtype, False)
  File "cupy/core/core.pyx", line 2049, in cupy.core.core.array
  File "cupy/core/core.pyx", line 2083, in cupy.core.core.array
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):

  File "<ipython-input-69-12b84b41c6b9>", line 1, in <module>
    runfile('/mnt/nas/sanaalamgeer/Projects/1/MyOwnChainer/Two-stream_IQA-master/train.py', wdir='/mnt/nas/sanaalamgeer/Projects/1/MyOwnChainer/Two-stream_IQA-master')

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 668, in runfile
    execfile(filename, namespace)

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 108, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "/mnt/nas/sanaalamgeer/Projects/1/MyOwnChainer/Two-stream_IQA-master/train.py", line 129, in <module>
    trainer.run()

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/trainer.py", line 330, in run
    six.reraise(*sys.exc_info())

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/six.py", line 693, in reraise
    raise value

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/trainer.py", line 316, in run
    update()

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
    self.update_core()

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/training/updaters/standard_updater.py", line 154, in update_core
    in_arrays = self.converter(batch, self.device)

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/dataset/convert.py", line 149, in concat_examples
    return to_device(device, _concat_arrays(batch, padding))

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/dataset/convert.py", line 37, in to_device
    return cuda.to_gpu(x, device)

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/backends/cuda.py", line 285, in to_gpu
    return _array_to_gpu(array, device_, stream)

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/chainer/backends/cuda.py", line 333, in _array_to_gpu
    return cupy.asarray(array)

  File "/home/sanaalamgeer/anaconda3/lib/python3.6/site-packages/cupy/creation/from_data.py", line 60, in asarray
    return core.array(a, dtype, False)

  File "cupy/core/core.pyx", line 2049, in cupy.core.core.array

  File "cupy/core/core.pyx", line 2083, in cupy.core.core.array

ValueError: Unsupported dtype object

也許那是因為我正在激勵training data錯誤，因為該模型將訓練參數視為：

length = x_data.shape[0]
x1 = Variable(x_data[0:length:2])
x2 = Variable(x_data[1:length:2])

和y_data為：

t = xp.repeat(y_data[0:length:2], 1)

tuple (Numpy Array, 66)的變量final_train_set數據集tuple (Numpy Array, 66) ，其中每個Numpy Array都有尺寸(2, 3, 32, 32) final_train_set (2, 3, 32, 32) ，它帶有兩種類型的補丁(3, 32, 32) final_train_set (3, 32, 32) 。

我使用了上面提供的github鏈接中的數據集。 我是Chainer的新手，請幫忙！

Answer 1

非常簡短，你不恰當地稱為numpy.asarray ： numpy.asarray不會連接兩個cupy.ndarray ，而它連接兩個numpy.ndarray 。

您的代碼簡要說明：

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

解決方案：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

1. 在您提供的代碼中，未指定xp ，因此您無法從任何人那里獲得答案。 如果您無法分離問題，請發布您的代碼的全部內容，包括模型。

2. 我猜你可能因為其他原因而無法運行訓練代碼。 在此代碼中，數據首先在構造final_train_set被帶到主存儲器。 但是如果圖像數量很大，主內存就會耗盡，並且會引發MemoryError 。 （換句話說，如果圖像的數量很少而且你的記憶足夠大，那么就不會發生錯誤）在這種情況下，以下參考文獻（ Chainer at a view and Dataset Abstraction ）會有所幫助。

Answer 2

免責聲明：此代碼均不是由我編寫的

我發現這個 Github存儲庫使用OpenCV，Scipy和其他一些模塊進行質量評估。 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