Skip to content

S
seminar-breakout
Commit 753afd0a authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

update load-resnet to share code

parent f793fa9f
Show whitespace changes
Inline Side-by-side
Showing with 41 additions and 67 deletions
examples/ResNet/README.md
View file @ 753afd0a
......@@ -31,7 +31,7 @@ See the [tutorial](http://tensorpack.readthedocs.io/en/latest/tutorial/efficient
## load-resnet.py
This script only converts and runs ImageNet-ResNet{50,101,152} Caffe models [released by Kaiming](https://github.com/KaimingHe/deep-residual-networks).
This script only converts and runs ImageNet-ResNet{50,101,152} Caffe models [released by MSRA](https://github.com/KaimingHe/deep-residual-networks).
Note that the architecture is different from the `imagenet-resnet.py` script and the models are not compatible.
Usage:
......@@ -47,9 +47,9 @@ The per-pixel mean used here is slightly different from the original.
| Model | Top 5 Error | Top 1 Error |
|:-------------------|-------------|------------:|
| ResNet 50 | 7.89% | 25.03% |
| ResNet 101 | 7.16% | 23.74% |
| ResNet 152 | 6.81% | 23.28% |
| ResNet 50 | 7.78% | 24.77% |
| ResNet 101 | 7.11% | 23.54% |
| ResNet 152 | 6.71% | 23.21% |
## cifar10-resnet.py
......
examples/ResNet/imagenet_utils.py
View file @ 753afd0a
......@@ -85,6 +85,7 @@ def get_imagenet_dataflow(
"""
assert name in ['train', 'val', 'test']
assert datadir is not None
assert isinstance(augmentors, list)
isTrain = name == 'train'
cpu = min(30, multiprocessing.cpu_count())
if isTrain:
......
examples/ResNet/load-resnet.py
View file @ 753afd0a
......@@ -21,7 +21,8 @@ from tensorpack.tfutils.symbolic_functions import *
from tensorpack.tfutils.summary import *
from tensorpack.dataflow.dataset import ILSVRCMeta, ILSVRC12
from imagenet_resnet_utils import eval_on_ILSVRC12
from imagenet_utils import eval_on_ILSVRC12, get_imagenet_dataflow
from resnet_model import resnet_group, apply_preactivation, resnet_shortcut, get_bn
MODEL_DEPTH = None
......@@ -31,41 +32,15 @@ class Model(ModelDesc):
return [InputDesc(tf.float32, [None, 224, 224, 3], 'input'),
InputDesc(tf.int32, [None], 'label')]
def _build_graph(self, input_vars):
image, label = input_vars
def shortcut(l, n_in, n_out, stride):
if n_in != n_out:
l = Conv2D('convshortcut', l, n_out, 1, stride=stride)
return BatchNorm('bnshortcut', l)
else:
return l
def _build_graph(self, inputs):
image, label = inputs
def bottleneck(l, ch_out, stride, preact):
ch_in = l.get_shape().as_list()[-1]
input = l
if preact == 'both_preact':
l = tf.nn.relu(l, name='preact-relu')
input = l
l = Conv2D('conv1', l, ch_out, 1, stride=stride)
l = BatchNorm('bn1', l)
l = tf.nn.relu(l)
l = Conv2D('conv2', l, ch_out, 3)
l = BatchNorm('bn2', l)
l = tf.nn.relu(l)
l = Conv2D('conv3', l, ch_out * 4, 1)
l = BatchNorm('bn3', l) # put bn at the bottom
return l + shortcut(input, ch_in, ch_out * 4, stride)
def layer(l, layername, features, count, stride, first=False):
with tf.variable_scope(layername):
with tf.variable_scope('block0'):
l = bottleneck(l, features, stride,
'no_preact' if first else 'both_preact')
for i in range(1, count):
with tf.variable_scope('block{}'.format(i)):
l = bottleneck(l, features, 1, 'both_preact')
return l
l, shortcut = apply_preactivation(l, preact)
l = Conv2D('conv1', l, ch_out, 1, stride=stride, nl=BNReLU)
l = Conv2D('conv2', l, ch_out, 3, nl=BNReLU)
l = Conv2D('conv3', l, ch_out * 4, 1, nl=get_bn())
return l + resnet_shortcut(shortcut, ch_out * 4, stride, nl=get_bn())
cfg = {
50: ([3, 4, 6, 3]),
......@@ -74,24 +49,26 @@ class Model(ModelDesc):
}
defs = cfg[MODEL_DEPTH]
with argscope(Conv2D, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_OUT')):
# tensorflow with padding=SAME will by default pad [2,3] here.
# but caffe conv with stride will pad [3,3]
image = tf.pad(image, [[0, 0], [3, 3], [3, 3], [0, 0]])
fc1000 = (LinearWrap(image)
image = tf.transpose(image, [0, 3, 1, 2])
with argscope([Conv2D, MaxPooling, GlobalAvgPooling, BatchNorm],
data_format='NCHW'), \
argscope(Conv2D, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_OUT')):
logits = (LinearWrap(image)
.Conv2D('conv0', 64, 7, stride=2, nl=BNReLU, padding='VALID')
.MaxPooling('pool0', shape=3, stride=2, padding='SAME')
.apply(layer, 'group0', 64, defs[0], 1, first=True)
.apply(layer, 'group1', 128, defs[1], 2)
.apply(layer, 'group2', 256, defs[2], 2)
.apply(layer, 'group3', 512, defs[3], 2)
.tf.nn.relu()
.apply(resnet_group, 'group0', bottleneck, 64, defs[0], 1)
.apply(resnet_group, 'group1', bottleneck, 128, defs[1], 2)
.apply(resnet_group, 'group2', bottleneck, 256, defs[2], 2)
.apply(resnet_group, 'group3', bottleneck, 512, defs[3], 2)
.GlobalAvgPooling('gap')
.FullyConnected('fc1000', 1000, nl=tf.identity)())
prob = tf.nn.softmax(fc1000, name='prob')
nr_wrong = prediction_incorrect(fc1000, label, name='wrong-top1')
nr_wrong = prediction_incorrect(fc1000, label, 5, name='wrong-top5')
.FullyConnected('linear', 1000, nl=tf.identity)())
prob = tf.nn.softmax(logits, name='prob')
prediction_incorrect(logits, label, name='wrong-top1')
prediction_incorrect(logits, label, 5, name='wrong-top5')
def get_inference_augmentor():
......@@ -105,11 +82,11 @@ def get_inference_augmentor():
pp_mean = meta.get_per_pixel_mean()
pp_mean_224 = pp_mean[16:-16, 16:-16, :]
transformers = imgaug.AugmentorList([
transformers = [
imgaug.ResizeShortestEdge(256),
imgaug.CenterCrop((224, 224)),
imgaug.MapImage(lambda x: x - pp_mean_224),
])
]
return transformers
......@@ -144,7 +121,7 @@ def name_conversion(caffe_layer_name):
'bn_conv1/mean/EMA': 'conv0/bn/mean/EMA',
'bn_conv1/variance/EMA': 'conv0/bn/variance/EMA',
'conv1/W': 'conv0/W', 'conv1/b': 'conv0/b',
'fc1000/W': 'fc1000/W', 'fc1000/b': 'fc1000/b'}
'fc1000/W': 'linear/W', 'fc1000/b': 'linear/b'}
if caffe_layer_name in NAME_MAP:
return NAME_MAP[caffe_layer_name]
......@@ -169,8 +146,10 @@ def name_conversion(caffe_layer_name):
TYPE_DICT = {'res': 'conv', 'bn': 'bn'}
tf_name = caffe_layer_name[caffe_layer_name.index('/'):]
layer_type = TYPE_DICT[layer_type] + \
(str(layer_id) if layer_branch == 2 else 'shortcut')
if layer_type == 'res':
layer_type = 'conv{}'.format(layer_id if layer_branch == 2 else 'shortcut')
else:
layer_type = 'conv{}/bn'.format(layer_id if layer_branch == 2 else 'shortcut')
tf_name = 'group{}/block{}/{}'.format(
int(layer_group) - 2, layer_block, layer_type) + tf_name
return tf_name
......@@ -178,7 +157,6 @@ def name_conversion(caffe_layer_name):
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', help='comma separated list of GPU(s) to use.')
parser.add_argument('--load', required=True,
help='.npy model file generated by tensorpack.utils.loadcaffe')
parser.add_argument('-d', '--depth', help='resnet depth', required=True, type=int, choices=[50, 101, 152])
......@@ -187,8 +165,6 @@ if __name__ == '__main__':
args = parser.parse_args()
assert args.input or args.eval, "Choose either input or eval!"
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
MODEL_DEPTH = args.depth
param = np.load(args.load, encoding='latin1').item()
......@@ -203,10 +179,7 @@ if __name__ == '__main__':
resnet_param[newname] = v
if args.eval:
ds = ILSVRC12(args.eval, 'val', shuffle=False)
ds = AugmentImageComponent(ds, get_inference_augmentor())
ds = BatchData(ds, 128, remainder=True)
ds = PrefetchDataZMQ(ds, 1)
ds = get_imagenet_dataflow(args.eval, 'val', 128, get_inference_augmentor())
eval_on_ILSVRC12(Model(), DictRestore(resnet_param), ds)
else:
run_test(resnet_param, args.input)
tensorpack/dataflow/common.py
View file @ 753afd0a
......@@ -86,7 +86,7 @@ class BatchData(ProxyDataFlow):
assert batch_size <= ds.size()
except NotImplementedError:
pass
self.batch_size = batch_size
self.batch_size = int(batch_size)
self.remainder = remainder
self.use_list = use_list
......
tensorpack/utils/loadcaffe.py
View file @ 753afd0a
......@@ -110,7 +110,7 @@ def load_caffe(model_desc, model_file):
net = caffe.Net(model_desc, model_file, caffe.TEST)
param_dict = CaffeLayerProcessor(net).process()
logger.info("Model loaded from caffe. Params: " +
" ".join(sorted(param_dict.keys())))
", ".join(sorted(param_dict.keys())))
return param_dict
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment