Skip to content
Snippets Groups Projects
Commit a39dd418 authored by nz11's avatar nz11
Browse files

Update vgg16_imagenet.py

parent f9d15930
No related branches found
No related tags found
No related merge requests found
import os import os
import glob import glob
import random
import scipy import scipy
import scipy.io import scipy.io
import cv2 import cv2
import numpy as np import numpy as np
import tensorflow as tf
import keras import keras
from keras.models import Sequential, Model from keras.models import Sequential, Model
from keras.layers import * from keras.layers import *
from keras.applications.vgg16 import VGG16, preprocess_input
from keras.utils import to_categorical from keras.utils import to_categorical
from keras.applications.vgg16 import VGG16, preprocess_input
from keras import backend as K from keras import backend as K
from frontend.approxhpvm_translator import translate_to_approxhpvm from frontend.approxhpvm_translator import translate_to_approxhpvm
from frontend.weight_utils import dumpCalibrationData from frontend.weight_utils import dumpCalibrationData2
np.random.seed(0) np.random.seed(2020)
os.environ["CUDA_VISIBLE_DEVICES"] = "1" os.environ["CUDA_VISIBLE_DEVICES"] = "1"
K.set_image_data_format('channels_first') K.set_image_data_format('channels_first')
data_format = 'channels_first'
num_images = 5000
val_size = 100
data_format = 'channels_first' IMAGENET_DIR = '/home/nz11/ILSVRC2012/'
OUTPUT_DIR = 'data/vgg16_imagenet_tune/'
NUM_CLASSES = 200
IMAGES_PER_CLASS = 40
# VAL_SIZE = 100
...@@ -111,12 +116,28 @@ def get_vgg16_nchw_keras(): ...@@ -111,12 +116,28 @@ def get_vgg16_nchw_keras():
x = Dense(1000)(x) x = Dense(1000)(x)
x = Activation('softmax')(x) x = Activation('softmax')(x)
model = Model(img_input, x) model_nchw = Model(img_input, x)
return model
model = VGG16()
j = 0
for i in range(len(model_nchw.layers)):
if 'padding' in model_nchw.layers[i].name or 'activation' in model_nchw.layers[i].name:
continue
try:
model_nchw.layers[i].set_weights(model.layers[j].get_weights())
except:
print (i, model_nchw.layers[i], 'skipped')
j += 1
return model_nchw
def load_image(x): def load_image(x):
image = cv2.imread(x) image = cv2.imread(x)
height, width, _ = image.shape height, width, _ = image.shape
...@@ -136,76 +157,73 @@ def load_image(x): ...@@ -136,76 +157,73 @@ def load_image(x):
return image.astype(np.float32) return image.astype(np.float32)
meta = scipy.io.loadmat(IMAGENET_DIR + 'ILSVRC2012_devkit_t12/data/meta.mat')
model = VGG16()
model_nchw = get_vgg16_nchw_keras()
j = 0
for i in range(len(model_nchw.layers)):
if 'padding' in model_nchw.layers[i].name or 'activation' in model_nchw.layers[i].name:
continue
try:
model_nchw.layers[i].set_weights(model.layers[j].get_weights())
except:
print (i, model_nchw.layers[i], 'skipped')
j += 1
classes = os.listdir('/home/nz11/ILSVRC2012/train')
train_images = glob.glob('/home/nz11/ILSVRC2012/train/*/*')
val_images = glob.glob('/home/nz11/ILSVRC2012/val/*/*')
val_images = sorted(val_images, key=lambda x: x.split('/')[-1].split('_')[-1].split('.')[0])
idx = np.random.permutation(len(val_images))[:num_images]
val_images = np.array(val_images)[idx]
d = {k:v for v, k in enumerate(classes)}
X_test = []
for x in val_images:
X_test.append(load_image(x))
X_test = np.array(X_test)
meta = scipy.io.loadmat("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/meta.mat")
original_idx_to_synset = {} original_idx_to_synset = {}
synset_to_name = {} synset_to_name = {}
for i in range(1000): for i in range(1000):
ilsvrc2012_id = int(meta["synsets"][i,0][0][0][0]) ilsvrc2012_id = int(meta['synsets'][i,0][0][0][0])
synset = meta["synsets"][i,0][1][0] synset = meta['synsets'][i,0][1][0]
name = meta["synsets"][i,0][2][0] name = meta['synsets'][i,0][2][0]
original_idx_to_synset[ilsvrc2012_id] = synset original_idx_to_synset[ilsvrc2012_id] = synset
synset_to_name[synset] = name synset_to_name[synset] = name
synset_to_keras_idx = {} synset_to_keras_idx = {}
keras_idx_to_name = {} keras_idx_to_name = {}
f = open("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/synset_words.txt","r") f = open(IMAGENET_DIR + 'ILSVRC2012_devkit_t12/data/synset_words.txt', 'r')
c = 0 c = 0
for line in f: for line in f:
parts = line.split(" ") parts = line.split(' ')
synset_to_keras_idx[parts[0]] = c synset_to_keras_idx[parts[0]] = c
keras_idx_to_name[c] = " ".join(parts[1:]) keras_idx_to_name[c] = ' '.join(parts[1:])
c += 1 c += 1
f.close() f.close()
def convert_original_idx_to_keras_idx(idx):
return synset_to_keras_idx[original_idx_to_synset[idx]]
with open("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/ILSVRC2012_validation_ground_truth.txt","r") as f:
y_true = f.read().strip().split("\n")
y_true = list(map(int, y_true))
y_true = np.array([convert_original_idx_to_keras_idx(idx) for idx in y_true])[idx]
y_true = y_true.astype(np.uint32)
y_true = np.expand_dims(y_true, axis=-1)
model = get_vgg16_nchw_keras()
X_tune, X_test = [], []
y_tune, y_true = [], []
classes = glob.glob(IMAGENET_DIR + 'val/*')
for c in np.random.permutation(len(classes))[:NUM_CLASSES]:
x = glob.glob(classes[c] + '/*')
x = np.array(x)
idx = np.random.permutation(len(x))
idx = idx[:max(len(idx), IMAGES_PER_CLASS)]
synset = classes[c].split('/')[-1]
images = list(map(lambda x : load_image(x), x[idx]))
labels = [synset_to_keras_idx[synset]] * len(x[idx])
X_test += images[:IMAGES_PER_CLASS // 2]
y_true += labels[:IMAGES_PER_CLASS // 2]
X_tune += images[IMAGES_PER_CLASS // 2:]
y_tune += labels[IMAGES_PER_CLASS // 2:]
X_test = np.array(X_test)
y_true = np.array(y_true)
X_tune = np.array(X_tune)
y_tune = np.array(y_tune)
translate_to_approxhpvm(model, OUTPUT_DIR, X_tune, y_tune, 1000)
# dumpCalibrationData2(OUTPUT_DIR + 'test_input_10K.bin', X_test, OUTPUT_DIR + 'test_labels_10K.bin', y_true)
dumpCalibrationData2(OUTPUT_DIR + 'tune_input.bin', X_tune, OUTPUT_DIR + 'tune_labels.bin', y_tune)
dumpCalibrationData2(OUTPUT_DIR + 'test_input.bin', X_test, OUTPUT_DIR + 'test_labels.bin', y_true)
translate_to_approxhpvm(model_nchw, "data/vgg16_imagenet/", X_test[:val_size], y_true[:val_size], 1000)
dumpCalibrationData("data/vgg16_imagenet/test_input.bin", X_test, "data/vgg16_imagenet/test_labels.bin", y_true)
pred = np.argmax(model_nchw.predict(X_test), axis=1) pred = np.argmax(model.predict(X_test), axis=1)
print ('val accuracy', np.sum(pred == y_true.ravel()) / val_size) print ('val accuracy', np.sum(pred == y_true.ravel()) / len(X_test))
pred = np.argmax(model.predict(X_tune), axis=1)
print ('val accuracy', np.sum(pred == y_tune.ravel()) / len(X_tune))
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment