def get_inference_augmentor():
meta = ILSVRCMeta()
pp_mean = meta.get_per_pixel_mean()
pp_mean_224 = pp_mean[16:-16, 16:-16, :]
transformers = imgaug.AugmentorList([
imgaug.ResizeShortestEdge(256),
imgaug.CenterCrop((224, 224)),
imgaug.MapImage(lambda x: x - pp_mean_224),
])
return transformers
def run_test(path, input):
param_dict = dict(np.load(path))
predict_func = OfflinePredictor(
PredictConfig(
inputs_desc=[InputDesc(tf.float32, (None, 224, 224, 3), 'input')],
tower_func=tower_func,
session_init=DictRestore(param_dict),
input_names=['input'],
output_names=['prob'] # prob:0 is the probability distribution
))
im = cv2.imread(input)
assert im is not None, input
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (224, 224)).reshape((1, 224, 224, 3)).astype('float32')
# VGG19 requires channelwise mean substraction
VGG_MEAN = [103.939, 116.779, 123.68]
im -= VGG_MEAN[::-1]
outputs = predict_func(im)[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
def run_test(path, input):
param_dict = np.load(path).item()
pred_config = PredictConfig(
model=Model(),
input_var_names=['input'],
session_init=ParamRestore(param_dict),
session_config=get_default_sess_config(0.9),
output_var_names=['output'] # output:0 is the probability distribution
)
predict_func = get_predict_func(pred_config)
import cv2
im = cv2.imread(input)
assert im is not None
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (224, 224))
im = np.reshape(im, (1, 224, 224, 3)).astype('float32')
im = im - 110
outputs = predict_func([im])[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print(ret)
meta = ILSVRCMeta().get_synset_words_1000()
print([meta[k] for k in ret])
def run_test(path, input):
param_dict = dict(np.load(path))
param_dict = {k.replace('/W', '/kernel').replace('/b', '/bias'): v for k, v in six.iteritems(param_dict)}
predict_func = OfflinePredictor(PredictConfig(
input_signature=[tf.TensorSpec((None, 224, 224, 3), tf.float32, 'input')],
tower_func=tower_func,
session_init=SmartInit(param_dict),
input_names=['input'],
output_names=['prob'] # prob:0 is the probability distribution
))
im = cv2.imread(input)
assert im is not None, input
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (224, 224)).reshape((1, 224, 224, 3)).astype('float32')
# VGG19 requires channelwise mean substraction
VGG_MEAN = [103.939, 116.779, 123.68]
im -= VGG_MEAN[::-1]
outputs = predict_func(im)[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
def run_test(path, input):
param_dict = np.load(path).item()
pred_config = PredictConfig(
model=Model(),
input_data_mapping=[0],
session_init=ParamRestore(param_dict),
output_var_names=['output:0', 'pool5/MaxPool:0'])
predict_func = get_predict_func(pred_config)
im = cv2.imread(input)
assert im is not None
im = im.astype('float32')
im = cv2.resize(im, (224, 224)).reshape((1, 224, 224, 3))
im = im - 110
raw_out = predict_func([im])
tfout = raw_out[1][0]
from tensorio import read_value
dumpf = 'dump.tensortxt'
with open(dumpf) as f:
name, arr = read_value(f)
os.unlink(dumpf)
hout = arr[:, :, :, 0]
diff = hout - tfout
maxdiff = np.abs(diff).max()
print "Diff:", maxdiff
assert maxdiff < 1e-3
return
prob = raw_out[0][0]
ret = prob.argsort()[-10:][::-1]
print ret
meta = ILSVRCMeta().get_synset_words_1000()
print[meta[k] for k in ret]
def get_inference_augmentor():
# load ResNet mean from Kaiming:
# from tensorpack.utils.loadcaffe import get_caffe_pb
# obj = get_caffe_pb().BlobProto()
# obj.ParseFromString(open('ResNet_mean.binaryproto').read())
# pp_mean_224 = np.array(obj.data).reshape(3, 224, 224).transpose(1,2,0)
meta = ILSVRCMeta()
pp_mean = meta.get_per_pixel_mean()
pp_mean_224 = pp_mean[16:-16, 16:-16, :]
transformers = [
imgaug.ResizeShortestEdge(256),
imgaug.CenterCrop((224, 224)),
imgaug.MapImage(lambda x: x - pp_mean_224),
]
return transformers
def get_inference_augmentor():
# load ResNet mean from Kaiming:
# from tensorpack.utils.loadcaffe import get_caffe_pb
# obj = get_caffe_pb().BlobProto()
# obj.ParseFromString(open('ResNet_mean.binaryproto').read())
# pp_mean_224 = np.array(obj.data).reshape(3, 224, 224).transpose(1,2,0)
meta = ILSVRCMeta()
pp_mean = meta.get_per_pixel_mean()
pp_mean_224 = pp_mean[16:-16, 16:-16, :]
transformers = [
imgaug.ResizeShortestEdge(256),
imgaug.CenterCrop((224, 224)),
imgaug.MapImage(lambda x: x - pp_mean_224),
]
return transformers
def get_inference_augmentor():
# load ResNet mean from Kaiming:
#from tensorpack.utils.loadcaffe import get_caffe_pb
#obj = get_caffe_pb().BlobProto()
#obj.ParseFromString(open('ResNet_mean.binaryproto').read())
#pp_mean_224 = np.array(obj.data).reshape(3, 224, 224).transpose(1,2,0)
meta = ILSVRCMeta()
pp_mean = meta.get_per_pixel_mean()
pp_mean_224 = pp_mean[16:-16,16:-16,:]
def resize_func(im):
h, w = im.shape[:2]
scale = 256.0 / min(h, w)
desSize = map(int, [scale * w, scale * h])
im = cv2.resize(im, tuple(desSize), interpolation=cv2.INTER_CUBIC)
return im
transformers = imgaug.AugmentorList([
imgaug.MapImage(resize_func),
imgaug.CenterCrop((224, 224)),
imgaug.MapImage(lambda x: x - pp_mean_224),
])
return transformers
def run_test(params, input):
image_mean = np.array([0.485, 0.456, 0.406], dtype='float32')
pred_config = PredictConfig(model=Model(),
input_var_names=['input'],
session_init=ParamRestore(params),
output_var_names=['prob_output'])
predict_func = get_predict_func(pred_config)
im = cv2.imread(input)
im = cv2.resize(im, (224, 224)) - image_mean * 255
im = np.reshape(im, (1, 224, 224, 3)).astype('float32')
prob = predict_func([im])[0]
ret = prob[0].argsort()[-10:][::-1]
print(ret)
meta = ILSVRCMeta().get_synset_words_1000()
print([meta[k] for k in ret])
def run_test(params, input):
pred_config = PredictConfig(model=Model(),
session_init=DictRestore(params),
input_names=['input'],
output_names=['prob'])
predict_func = OfflinePredictor(pred_config)
prepro = get_inference_augmentor()
im = cv2.imread(input).astype('float32')
im = prepro.augment(im)
im = np.reshape(im, (1, 224, 224, 3))
outputs = predict_func([im])
prob = outputs[0]
ret = prob[0].argsort()[-10:][::-1]
print(ret)
meta = ILSVRCMeta().get_synset_words_1000()
print([meta[k] for k in ret])
def run_test(path, input):
param_dict = np.load(path, encoding='latin1').item()
predict_func = OfflinePredictor(
PredictConfig(model=Model(),
session_init=ParamRestore(param_dict),
input_names=['input'],
output_names=['prob']))
im = cv2.imread(input)
assert im is not None, input
im = cv2.resize(im, (227, 227))[:, :, ::-1].reshape(
(1, 227, 227, 3)).astype('float32') - 110
outputs = predict_func([im])[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
def run_test(path, input):
param_dict = dict(np.load(path))
predictor = OfflinePredictor(
PredictConfig(
inputs_desc=[InputDesc(tf.float32, (None, 227, 227, 3), 'input')],
tower_func=tower_func,
session_init=DictRestore(param_dict),
input_names=['input'],
output_names=['prob']))
im = cv2.imread(input)
assert im is not None, input
im = cv2.resize(im, (227, 227))[None, :, :, ::-1].astype('float32') - 110
outputs = predictor(im)[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
def run_test(path, input):
predictor = OfflinePredictor(
PredictConfig(input_signature=[
tf.TensorSpec((None, 227, 227, 3), tf.float32, 'input')
],
tower_func=tower_func,
session_init=SmartInit(path),
input_names=['input'],
output_names=['prob']))
im = cv2.imread(input)
assert im is not None, input
im = cv2.resize(im, (227, 227))[None, :, :, ::-1].astype('float32') - 110
outputs = predictor(im)[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
def run_test(path, input):
param_dict = np.load(path, encoding='latin1').item()
predict_func = OfflinePredictor(PredictConfig(
model=Model(),
session_init=DictRestore(param_dict),
input_names=['input'],
output_names=['prob'] # prob:0 is the probability distribution
))
im = cv2.imread(input)
assert im is not None, input
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (224, 224)).reshape((1, 224, 224, 3)).astype('float32')
im = im - 110
outputs = predict_func([im])[0]
prob = outputs[0]
ret = prob.argsort()[-10:][::-1]
print("Top10 predictions:", ret)
meta = ILSVRCMeta().get_synset_words_1000()
print("Top10 class names:", [meta[k] for k in ret])
choices=[50, 101, 152])
parser.add_argument('--arch',
help='Name of architectures defined in nets.py',
default='ResNetDenoise')
parser.add_argument('--load', help='path to checkpoint')
parser.add_argument('--input', help='path to input image')
args = parser.parse_args()
model = getattr(nets, args.arch + 'Model')(args)
input = tf.placeholder(tf.float32, shape=(None, 224, 224, 3))
image = input / 127.5 - 1.0
image = tf.transpose(image, [0, 3, 1, 2])
with TowerContext('', is_training=False):
logits = model.get_logits(image)
sess = tf.Session()
get_model_loader(args.load).init(sess)
sample = cv2.imread(args.input) # this is a BGR image, not RGB
# imagenet evaluation uses standard imagenet pre-processing
# (resize shortest edge to 256 + center crop 224).
# However, for images of unknown sources, let's just do a naive resize.
sample = cv2.resize(sample, (224, 224))
prob = sess.run(logits, feed_dict={input: np.array([sample])})
print("Prediction: ", prob.argmax())
synset = ILSVRCMeta().get_synset_words_1000()
print("Top 5: ", [synset[k] for k in prob[0].argsort()[-5:][::-1]])
