177 lines
6.1 KiB
Python
Executable File
177 lines
6.1 KiB
Python
Executable File
from __future__ import print_function
|
|
# from vgg19Pytorch import Vgg19Module
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import torch.optim as optim
|
|
import torchvision
|
|
from torchvision import datasets, transforms
|
|
import torchvision.models as models
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
from visdom import Visdom
|
|
import cv2
|
|
import os
|
|
import shutil
|
|
|
|
|
|
viz = Visdom()
|
|
# use visdom , we must start visdom Host first
|
|
# with python -m visdom.server
|
|
|
|
|
|
CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/"
|
|
print("Current Path :" + CurrentPath)
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
# vgg19 = Vgg19Module(CurrentPath+'/vgg19Pytorch.npy')
|
|
vgg19 = torchvision.models.vgg19(True)
|
|
|
|
if torch.cuda.is_available():
|
|
vgg19 = vgg19.to(device)
|
|
|
|
|
|
def weightVisual(layer, name=''):
|
|
mm4 = layer.weight.data
|
|
datodis = mm4 * 256 + 128
|
|
dashape = datodis.shape
|
|
datodis = datodis.view(dashape[1] * dashape[0], 1, dashape[2], dashape[3])
|
|
imaglisnp = datodis.detach().cpu().numpy()
|
|
viz.images(imaglisnp, opts=dict(
|
|
title=name, caption='How random.'), nrow=dashape[1])
|
|
|
|
|
|
def imageVisual(data, name='', rownum=8):
|
|
datodis = data
|
|
#datodis = datodis * 256 + 128
|
|
dashape = datodis.shape
|
|
datodis = datodis.view(dashape[1] * dashape[0], 1, dashape[2], dashape[3])
|
|
imaglisnp = datodis.detach().cpu().numpy()
|
|
viz.images(imaglisnp, opts=dict(
|
|
title=name, caption='How random.'), nrow=rownum)
|
|
|
|
|
|
def readAndPreprocessImage(imagepath):
|
|
mean = np.array([103.939, 116.779, 123.68])
|
|
img = cv2.imread(imagepath)
|
|
img = img.astype('float32')
|
|
img -= mean
|
|
img = cv2.resize(img, (224, 224)).transpose((2, 0, 1))
|
|
img = img[np.newaxis, :, :, :]
|
|
# cv image read is by BGR order
|
|
# and the network Need RGB
|
|
# the following BGR values should be subtracted: [103.939, 116.779, 123.68].
|
|
image = torch.from_numpy(img)
|
|
if torch.cuda.is_available():
|
|
image = image.cuda()
|
|
return image
|
|
|
|
|
|
#region forward image
|
|
image = readAndPreprocessImage(CurrentPath+"dog_resize.jpg")
|
|
imgfor = vgg19.forward(image)
|
|
imgfornumpy = imgfor.cpu().detach().numpy()
|
|
|
|
words = open(CurrentPath+'synset_words.txt').readlines()
|
|
words = [(w[0], ' '.join(w[1:])) for w in [w.split() for w in words]]
|
|
words = np.asarray(words)
|
|
|
|
top5 = np.argsort(imgfornumpy)[0][::-1][:5]
|
|
probs = np.sort(imgfornumpy)[0][::-1][:5]
|
|
for w, p in zip(words[top5], probs):
|
|
print('{}\tprobability:{}'.format(w, p))
|
|
#endregion
|
|
|
|
# # region write image and weight
|
|
# image = readAndPreprocessImage(CurrentPath+"dog_resize.jpg")
|
|
# conv1_1_pad = F.pad(image, (1L, 1L, 1L, 1L))
|
|
# conv1_1 = vgg19.conv1_1(conv1_1_pad)
|
|
# relu1_1 = F.relu(conv1_1)
|
|
# conv1_2_pad = F.pad(relu1_1, (1L, 1L, 1L, 1L))
|
|
# conv1_2 = vgg19.conv1_2(conv1_2_pad)
|
|
# relu1_2 = F.relu(conv1_2)
|
|
# pool1 = F.max_pool2d(relu1_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
|
|
# conv2_1_pad = F.pad(pool1, (1L, 1L, 1L, 1L))
|
|
# conv2_1 = vgg19.conv2_1(conv2_1_pad)
|
|
# relu2_1 = F.relu(conv2_1)
|
|
# conv2_2_pad = F.pad(relu2_1, (1L, 1L, 1L, 1L))
|
|
# conv2_2 = vgg19.conv2_2(conv2_2_pad)
|
|
# relu2_2 = F.relu(conv2_2)
|
|
# pool2 = F.max_pool2d(relu2_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
|
|
# conv3_1_pad = F.pad(pool2, (1L, 1L, 1L, 1L))
|
|
# conv3_1 = vgg19.conv3_1(conv3_1_pad)
|
|
# relu3_1 = F.relu(conv3_1)
|
|
# conv3_2_pad = F.pad(relu3_1, (1L, 1L, 1L, 1L))
|
|
# conv3_2 = vgg19.conv3_2(conv3_2_pad)
|
|
# relu3_2 = F.relu(conv3_2)
|
|
# conv3_3_pad = F.pad(relu3_2, (1L, 1L, 1L, 1L))
|
|
# conv3_3 = vgg19.conv3_3(conv3_3_pad)
|
|
# relu3_3 = F.relu(conv3_3)
|
|
# conv3_4_pad = F.pad(relu3_3, (1L, 1L, 1L, 1L))
|
|
# conv3_4 = vgg19.conv3_4(conv3_4_pad)
|
|
# relu3_4 = F.relu(conv3_4)
|
|
# pool3 = F.max_pool2d(relu3_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
|
|
# conv4_1_pad = F.pad(pool3, (1L, 1L, 1L, 1L))
|
|
# conv4_1 = vgg19.conv4_1(conv4_1_pad)
|
|
# relu4_1 = F.relu(conv4_1)
|
|
# conv4_2_pad = F.pad(relu4_1, (1L, 1L, 1L, 1L))
|
|
# conv4_2 = vgg19.conv4_2(conv4_2_pad)
|
|
# relu4_2 = F.relu(conv4_2)
|
|
# conv4_3_pad = F.pad(relu4_2, (1L, 1L, 1L, 1L))
|
|
# conv4_3 = vgg19.conv4_3(conv4_3_pad)
|
|
# relu4_3 = F.relu(conv4_3)
|
|
# conv4_4_pad = F.pad(relu4_3, (1L, 1L, 1L, 1L))
|
|
# conv4_4 = vgg19.conv4_4(conv4_4_pad)
|
|
# relu4_4 = F.relu(conv4_4)
|
|
# pool4 = F.max_pool2d(relu4_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
|
|
# conv5_1_pad = F.pad(pool4, (1L, 1L, 1L, 1L))
|
|
# conv5_1 = vgg19.conv5_1(conv5_1_pad)
|
|
# relu5_1 = F.relu(conv5_1)
|
|
# conv5_2_pad = F.pad(relu5_1, (1L, 1L, 1L, 1L))
|
|
# conv5_2 = vgg19.conv5_2(conv5_2_pad)
|
|
# relu5_2 = F.relu(conv5_2)
|
|
# conv5_3_pad = F.pad(relu5_2, (1L, 1L, 1L, 1L))
|
|
# conv5_3 = vgg19.conv5_3(conv5_3_pad)
|
|
# relu5_3 = F.relu(conv5_3)
|
|
# conv5_4_pad = F.pad(relu5_3, (1L, 1L, 1L, 1L))
|
|
# conv5_4 = vgg19.conv5_4(conv5_4_pad)
|
|
# relu5_4 = F.relu(conv5_4)
|
|
# pool5 = F.max_pool2d(relu5_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
|
|
# fc6_0 = pool5.view(pool5.size(0), -1)
|
|
|
|
# imageVisual(conv1_1, "conv1_1", 8)
|
|
# imageVisual(conv1_2, 'conv1_2', 8)
|
|
# imageVisual(conv2_1, "conv2_1", 16)
|
|
# imageVisual(conv2_2, "conv2_2", 16)
|
|
# imageVisual(conv3_1, "conv3_1", 16)
|
|
# imageVisual(conv3_2, "conv3_2", 16)
|
|
# imageVisual(conv3_3, "conv3_3", 16)
|
|
# imageVisual(conv3_4, "conv3_4", 16)
|
|
# imageVisual(conv4_1, "conv4_1", 32)
|
|
# imageVisual(conv4_2, "conv4_2", 32)
|
|
# imageVisual(conv4_3, "conv4_3", 32)
|
|
# imageVisual(conv4_4, "conv4_4", 32)
|
|
# imageVisual(conv5_1, "conv5_1", 32)
|
|
# imageVisual(conv5_2, "conv5_2", 32)
|
|
# imageVisual(conv5_3, "conv5_3", 32)
|
|
# imageVisual(conv5_4, "conv5_4", 32)
|
|
|
|
# weightVisual(vgg19.conv1_1, "conv1_1")
|
|
# weightVisual(vgg19.conv1_2, 'conv1_2')
|
|
# weightVisual(vgg19.conv2_1, "conv2_1")
|
|
# weightVisual(vgg19.conv2_2, "conv2_2")
|
|
# weightVisual(vgg19.conv3_1, "conv3_1")
|
|
# weightVisual(vgg19.conv3_2, "conv3_2")
|
|
# weightVisual(vgg19.conv3_3, "conv3_3")
|
|
# weightVisual(vgg19.conv3_4, "conv3_4")
|
|
# weightVisual(vgg19.conv4_1, "conv4_1")
|
|
# weightVisual(vgg19.conv4_2, "conv4_2")
|
|
# weightVisual(vgg19.conv4_3, "conv4_3")
|
|
# weightVisual(vgg19.conv4_4, "conv4_4")
|
|
# weightVisual(vgg19.conv5_1, "conv5_1")
|
|
# weightVisual(vgg19.conv5_2, "conv5_2")
|
|
# weightVisual(vgg19.conv5_3, "conv5_3")
|
|
# weightVisual(vgg19.conv5_4, "conv5_4")
|
|
# # endregion
|