I want to use ImageNet to do regression, the label is the two coordinates of the object, such as (622 132 736 318), and I have converted the images to .lmdb files.But when I try to train it, find this error
I0510 16:50:06.576092 7167 layer_factory.hpp:77] Creating layer data
I0510 16:50:06.576848 7167 net.cpp:106] Creating Layer data
I0510 16:50:06.576869 7167 net.cpp:411] data -> data
I0510 16:50:06.576900 7167 net.cpp:411] data -> label
I0510 16:50:06.576916 7167 data_transformer.cpp:25] Loading mean file from: /home/sx/caffe-master/sx/person_location/data/conferenceroom_train_mean.binaryproto
I0510 16:50:06.578588 7171 db_lmdb.cpp:38] Opened lmdb /home/shawn/caffe-master/shawn/person_location/data/conferenceroom_train_lmdb
I0510 16:50:06.595842 7167 data_layer.cpp:41] output data size: 256,3,227,227
I0510 16:50:08.680726 7167 net.cpp:150] Setting up data
I0510 16:50:08.680807 7167 net.cpp:157] Top shape: 256 3 227 227 (39574272)
I0510 16:50:08.680817 7167 net.cpp:157] Top shape: 256 (256)
I0510 16:50:08.680824 7167 net.cpp:165] Memory required for data: 158298112
I0510 16:50:08.680842 7167 layer_factory.hpp:77] Creating layer conv1
I0510 16:50:08.680874 7167 net.cpp:106] Creating Layer conv1
I0510 16:50:08.680884 7167 net.cpp:454] conv1 <- data
I0510 16:50:08.680907 7167 net.cpp:411] conv1 -> conv1
F0510 16:50:08.927338 7167 blob.cpp:33] Check failed: shape[i] >= 0 (-281264070 vs. 0)
*** Check failure stack trace: ***
# 0x7fec6e186778 (unknown)
# 0x7fec6e1866b2 (unknown)
# 0x7fec6e1860b4 (unknown)
# 0x7fec6e189055 (unknown)
# 0x7fec73a13598 caffe::Blob<>::Reshape()
# 0x7fec7395206c caffe::BaseConvolutionLayer<>::Reshape()
# 0x7fec739a90ef caffe::CuDNNConvolutionLayer<>::Reshape()
# 0x7fec738d32fb caffe::Net<>::Init()
# 0x7fec738d4a98 caffe::Net<>::Net()
# 0x7fec73a1fd62 caffe::Solver<>::InitTrainNet()
# 0x7fec73a21262 caffe::Solver<>::Init()
# 0x7fec73a21599 caffe::Solver<>::Solver()
# 0x7fec738ebf43 caffe::Creator_SGDSolver<>()
# 0x4105bc caffe::SolverRegistry<>::CreateSolver()
# 0x4087ed train()
# 0x405d67 main
# 0x7fec64993b45 (unknown)
# 0x406588 (unknown)
# (nil) (unknown)
Aborted
Here is the train_val.prototxt
name: "AlexNet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "/home/shawn/caffe-master/person_location/data/conferenceroom_train_mean.binaryproto"
}
data_param {
source: "/home/shawn/caffe-master/person_location/data/conferenceroom_train_lmdb"
batch_size: 256
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 227
mean_file: "/home/shawn/caffe-master/person_location/data/conferenceroom_train_mean.binaryproto"
}
data_param {
source: "/home/shawn/caffe-master/person_location/data/conferenceroom_val_lmdb"
batch_size: 50
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "EuclideanLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
Related
I use AlexNet for images multiclass (9 classes) classification. Dataset saved in hdf5 format and have a shape [image, vector_of_lenght_9].
When I start train network following error occurs:
F1213 11:17:13.133412 50200 accuracy_layer.cpp:31] Check failed: outer_num_ * inner_num_ == bottom[1]->count() (1 vs. 9) Number of labels must match number of predictions; e.g., if label axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W, with integer values in {0, 1, ..., C-1}.
*** Check failure stack trace:
Aborted (core dumped)
Here is my file with network (train_val.prototxt):
name: "AlexNet"
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
hdf5_data_param {
source: "train.txt"
batch_size: 1
}
}
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: "test.txt"
batch_size: 1
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "conv4"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
Here is solver file:
net: "train_val.prototxt"
test_iter: 1000
test_interval: 1000
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "caffe_alexnet_train"
solver_mode: CPU
The first version contained error that dataset had format [image, class_label]. The output result was wrong but network trained without any error. Output of network has format of vector of length 9. So when shapes of output and label were different everything was ok (although it shouldn't). When they are the same error occurs.
Below is the train.Prototxt file that is used to train a pretrained model.
name: "TempWLDNET"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 224
mean_file: "mean.binaryproto"
}
image_data_param {
source: "train.txt"
batch_size: 25
new_height: 256
new_width: 256
}
}
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 224
mean_file: "painmean.binaryproto"
}
image_data_param {
source: "test.txt"
batch_size: 25
new_height: 256
new_width: 256
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 7
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
# Note that lr_mult can be set to 0 to disable any fine-tuning of this, and any other, layer
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8_temp"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_temp"
# lr_mult is set to higher than for other layers, because this layer is starting from random while the others are already trained
param {
lr_mult: 10
decay_mult: 1
}
param {
lr_mult: 20
decay_mult: 0
}
inner_product_param {
num_output: 16
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8_temp"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8_temp"
bottom: "label"
top: "loss"
}
Using the above prototxt file accuracy reported for test set at the end of the Training is 92%. For more details please see How to evaluate the accuracy and loss of a trained model is good or not in caffe?
I took the model snapshot at the end of 13000 iteration and using below python script, i tried to construct the confusion matrix, Accuracy reported is 74%.
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
import caffe
import numpy as np
import argparse
from collections import defaultdict
TRAIN_DATA_ROOT='/Images/test/'
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--proto', type=str, required=True)
parser.add_argument('--model', type=str, required=True)
parser.add_argument('--meanfile', type=str, required=True)
parser.add_argument('--labelfile', type=str, required=True)
args = parser.parse_args()
proto_data = open(args.meanfile, 'rb').read()
a = caffe.io.caffe_pb2.BlobProto.FromString(proto_data)
mean = caffe.io.blobproto_to_array(a)[0]
caffe.set_mode_gpu()
count = 0
correct = 0
matrix = defaultdict(int) # (real,pred) -> int
labels_set = set()
net = caffe.Net(args.proto, args.model, caffe.TEST)
# load input and configure preprocessing
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_mean('data', mean)
transformer.set_transpose('data', (2,0,1))
transformer.set_channel_swap('data', (2,1,0))
transformer.set_raw_scale('data', 1)
#note we can change the batch size on-the-fly
#since we classify only one image, we change batch size from 10 to 1
net.blobs['data'].reshape(1,3,224,224)
#load the image in the data layer
f = open(args.labelfile, "r")
for line in f.readlines():
parts = line.split()
example_image = parts[0]
label = int(parts[1])
im = caffe.io.load_image(TRAIN_DATA_ROOT + example_image)
print(im.shape)
net.blobs['data'].data[...] = transformer.preprocess('data', im)
out = net.forward()
plabel = int(out['prob'][0].argmax(axis=0))
count += 1
iscorrect = label == plabel
correct += (1 if iscorrect else 0)
matrix[(label, plabel)] += 1
labels_set.update([label, plabel])
if not iscorrect:
print("\rError: expected %i but predicted %i" \
% (label, plabel))
sys.stdout.write("\rAccuracy: %.1f%%" % (100.*correct/count))
sys.stdout.flush()
print(", %i/%i corrects" % (correct, count))
print ("")
print ("Confusion matrix:")
print ("(r , p) | count")
for l in labels_set:
for pl in labels_set:
print ("(%i , %i) | %i" % (l, pl, matrix[(l,pl)]))
I am using the deploy.protxt
name: "CaffeNet"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 224
dim: 224
}
layers {
name: "conv1"
type: CONVOLUTION
bottom: "data"
top: "conv1"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 7
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
}
}
layers {
name: "pool1"
type: POOLING
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layers {
name: "conv2"
type: CONVOLUTION
bottom: "pool1"
top: "conv2"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "pool2"
type: POOLING
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layers {
name: "conv3"
type: CONVOLUTION
bottom: "pool2"
top: "conv3"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
bottom: "conv3"
top: "conv4"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
bottom: "conv4"
top: "conv5"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layers {
name: "fc6"
type: INNER_PRODUCT
bottom: "pool5"
top: "fc6"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc7"
type: INNER_PRODUCT
bottom: "fc6"
top: "fc7"
# Note that blobs_lr can be set to 0 to disable any fine-tuning of this, and any other, layers
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc8_temp"
type: INNER_PRODUCT
bottom: "fc7"
top: "fc8_temp"
# blobs_lr is set to higher than for other layers, because this layers is starting from random while the others are already trained
blobs_lr: 10
weight_decay: 1
blobs_lr: 20
weight_decay: 0
inner_product_param {
num_output: 16
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "prob"
type: SOFTMAX
bottom: "fc8_temp"
top: "prob"
}
The command used to run the script is
python confusion.py --proto deploy.prototxt --model models/model_iter_13000.caffemodel --meanfile mean.binaryproto --labelfile NamesTest.txt
My doubt is Why there is a difference in accuracy when i am using the same model and same test set. Am i doing anything wrong?. Thank you in advance.
There are differences between your validation step (TEST phase) and the python code you are running:
You are using a different mean file for train and test (!): for phase: TRAIN you are using mean_file: "mean.binaryproto" while for phase: TEST you are using mean_file: "painmean.binaryproto". Your python evaluation code uses the training mean file and not the validation.
It is not a good practice to have different settings for train/validation.
Your input images have new_height: 256 and copr_size: 224. This settings means caffe reads the image, scales it to 256x256 and then crops the center to size 224x224. Your python code seems to only scale the input to 224x224 without cropping: you feed your net with different inputs.
Please verify that you do not have any other differences between your training prototxt and deploy prototxt.
Below is the train.Prototxt file that is used to train a pretrained model.
name: "TempWLDNET"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 224
mean_file: "mean.binaryproto"
}
image_data_param {
source: "train.txt"
batch_size: 25
new_height: 256
new_width: 256
}
}
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 224
mean_file: "painmean.binaryproto"
}
image_data_param {
source: "test.txt"
batch_size: 25
new_height: 256
new_width: 256
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 7
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
# Note that lr_mult can be set to 0 to disable any fine-tuning of this, and any other, layer
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8_temp"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_temp"
# lr_mult is set to higher than for other layers, because this layer is starting from random while the others are already trained
param {
lr_mult: 10
decay_mult: 1
}
param {
lr_mult: 20
decay_mult: 0
}
inner_product_param {
num_output: 16
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8_temp"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8_temp"
bottom: "label"
top: "loss"
}
Using the above prototxt file accuracy reported for test set at the end of the Training is 92%. For more details please see How to evaluate the accuracy and loss of a trained model is good or not in caffe?
I took the model snapshot at the end of 13000 iteration and using below python script, i tried to construct the confusion matrix, Accuracy reported is 74%.
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
import caffe
import numpy as np
import argparse
from collections import defaultdict
TRAIN_DATA_ROOT='/Images/test/'
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--proto', type=str, required=True)
parser.add_argument('--model', type=str, required=True)
parser.add_argument('--meanfile', type=str, required=True)
parser.add_argument('--labelfile', type=str, required=True)
args = parser.parse_args()
proto_data = open(args.meanfile, 'rb').read()
a = caffe.io.caffe_pb2.BlobProto.FromString(proto_data)
mean = caffe.io.blobproto_to_array(a)[0]
caffe.set_mode_gpu()
count = 0
correct = 0
matrix = defaultdict(int) # (real,pred) -> int
labels_set = set()
net = caffe.Net(args.proto, args.model, caffe.TEST)
# load input and configure preprocessing
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_mean('data', mean)
transformer.set_transpose('data', (2,0,1))
transformer.set_channel_swap('data', (2,1,0))
transformer.set_raw_scale('data', 1)
#note we can change the batch size on-the-fly
#since we classify only one image, we change batch size from 10 to 1
net.blobs['data'].reshape(1,3,224,224)
#load the image in the data layer
f = open(args.labelfile, "r")
for line in f.readlines():
parts = line.split()
example_image = parts[0]
label = int(parts[1])
im = caffe.io.load_image(TRAIN_DATA_ROOT + example_image)
print(im.shape)
net.blobs['data'].data[...] = transformer.preprocess('data', im)
out = net.forward()
plabel = int(out['prob'][0].argmax(axis=0))
count += 1
iscorrect = label == plabel
correct += (1 if iscorrect else 0)
matrix[(label, plabel)] += 1
labels_set.update([label, plabel])
if not iscorrect:
print("\rError: expected %i but predicted %i" \
% (label, plabel))
sys.stdout.write("\rAccuracy: %.1f%%" % (100.*correct/count))
sys.stdout.flush()
print(", %i/%i corrects" % (correct, count))
print ("")
print ("Confusion matrix:")
print ("(r , p) | count")
for l in labels_set:
for pl in labels_set:
print ("(%i , %i) | %i" % (l, pl, matrix[(l,pl)]))
I am using the deploy.protxt
name: "CaffeNet"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 224
dim: 224
}
layers {
name: "conv1"
type: CONVOLUTION
bottom: "data"
top: "conv1"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 7
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
}
}
layers {
name: "pool1"
type: POOLING
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layers {
name: "conv2"
type: CONVOLUTION
bottom: "pool1"
top: "conv2"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "pool2"
type: POOLING
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layers {
name: "conv3"
type: CONVOLUTION
bottom: "pool2"
top: "conv3"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
bottom: "conv3"
top: "conv4"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
bottom: "conv4"
top: "conv5"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 3
}
}
layers {
name: "fc6"
type: INNER_PRODUCT
bottom: "pool5"
top: "fc6"
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc7"
type: INNER_PRODUCT
bottom: "fc6"
top: "fc7"
# Note that blobs_lr can be set to 0 to disable any fine-tuning of this, and any other, layers
blobs_lr: 1
weight_decay: 1
blobs_lr: 2
weight_decay: 0
inner_product_param {
num_output: 4048
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc8_temp"
type: INNER_PRODUCT
bottom: "fc7"
top: "fc8_temp"
# blobs_lr is set to higher than for other layers, because this layers is starting from random while the others are already trained
blobs_lr: 10
weight_decay: 1
blobs_lr: 20
weight_decay: 0
inner_product_param {
num_output: 16
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "prob"
type: SOFTMAX
bottom: "fc8_temp"
top: "prob"
}
The command used to run the script is
python confusion.py --proto deploy.prototxt --model models/model_iter_13000.caffemodel --meanfile mean.binaryproto --labelfile NamesTest.txt
My doubt is Why there is a difference in accuracy when i am using the same model and same test set. Am i doing anything wrong?. Thank you in advance.
There are differences between your validation step (TEST phase) and the python code you are running:
You are using a different mean file for train and test (!): for phase: TRAIN you are using mean_file: "mean.binaryproto" while for phase: TEST you are using mean_file: "painmean.binaryproto". Your python evaluation code uses the training mean file and not the validation.
It is not a good practice to have different settings for train/validation.
Your input images have new_height: 256 and copr_size: 224. This settings means caffe reads the image, scales it to 256x256 and then crops the center to size 224x224. Your python code seems to only scale the input to 224x224 without cropping: you feed your net with different inputs.
Please verify that you do not have any other differences between your training prototxt and deploy prototxt.
when I run train_caffenet.sh, I get the following errors:
I0906 10:56:42.327703 21556 solver.cpp:91] Creating training net from net file: /home/pris/caffe-master/examples/myself/train_val.prototxt
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 26:12: Message type "caffe.ImageDataParameter" has no field named "backend".
F0906 10:56:42.327837 21556 upgrade_proto.cpp:79] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/pris/caffe-master/examples/myself/train_val.prototxt
*** Check failure stack trace: ***
# 0x7f5013ca0daa (unknown)
# 0x7f5013ca0ce4 (unknown)
# 0x7f5013ca06e6 (unknown)
# 0x7f5013ca3687 (unknown)
# 0x7f50142b019e caffe::ReadNetParamsFromTextFileOrDie()
# 0x7f501429e76b caffe::Solver<>::InitTrainNet()
# 0x7f501429f83c caffe::Solver<>::Init()
# 0x7f501429fb6a caffe::Solver<>::Solver()
# 0x7f50143de663 caffe::Creator_SGDSolver<>()
# 0x40e9be caffe::SolverRegistry<>::CreateSolver()
# 0x407b62 train()
# 0x4059ec main
# 0x7f5012faef45 (unknown)
# 0x406121 (unknown)
# (nil) (unknown)
Aborted (core dumped)
I've tried to solve it for a few days but still can't figure out how it comes wrong.
here is my train_val.prototxt, mainly modified from the one in $CAFFE_TOOT/models/bvlc_reference_caffenet
name: "CaffeNet"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "/home/pris/caffe-master/data/myself/myimagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: true
# }
image_data_param {
source: "/home/pris/caffe-master/examples/myself/imagenet_train_leveldb"
batch_size: 256
backend: LEVELDB
}
}
layer
{
name: "data"
type: "ImageData"
top: "data"
top: "label"
include { phase: TEST }
transform_param
{
mirror: false
crop_size: 227
mean_file: "/home/pris/caffe-master/data/myself/myimagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: false
# }
image_data_param
{
source: "/home/pris/caffe-master/examples/myself/imagenet_val_leveldb"
batch_size: 50
backend: LEVELDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
convolution_param
{
num_output: 96
kernel_size: 11
stride: 4
weight_filler
{
type: "gaussian"
std: 0.01
}
bias_filler
{
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
top: "conv2"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
convolution_param
{
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler
{
type: "gaussian"
std: 0.01
}
bias_filler
{
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
convolution_param
{
num_output: 384
pad: 1
kernel_size: 3
weight_filler
{
type: "gaussian"
std: 0.01
}
bias_filler
{
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
convolution_param
{
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler
{
type: "gaussian"
std: 0.01
}
bias_filler
{
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param
{
lr_mult: 1
decay_mult: 1
}
param
{
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
and the sovler.prototxt
net: "/home/pris/caffe-master/examples/myself/train_val.prototxt"
test_iter: 10
test_interval: 500
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 2000
snapshot_prefix:"/home/pris/caffe-master/examples/myself/result"
solver_mode: GPU
train_caffenet.sh:
#!/usr/bin/env sh
/home/pris/caffe-master/build/tools/caffe train \
--solver=/home/pris/caffe-master/examples/myself/solver.prototxt
I will really appreciate if someone could help me fixed it.
You are reading training data from leveldb database, you should use input layer of type "Data" and not "ImageData".
I wrote a caffe net about multi-label classification using HDF5, here is the prototxt file named 'auto_train.prototxt'
name: "multilabel_net"
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
hdf5_data_param {
source: "examples/corel5k/train.h5list"
batch_size: 50
shuffle: 1
}
}
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: "examples/corel5k/test.h5list"
batch_size: 50
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "score"
type: "InnerProduct"
bottom: "fc7"
top: "score"
inner_product_param {
num_output: 260
}
}
layer {
name: "loss"
type: "SigmoidCrossEntropyLoss"
bottom: "score"
bottom: "label"
top: "loss"
}
layer {
name: "score"
type: "InnerProduct"
bottom: "fc7"
top: "score"
inner_product_param {
num_output: 260
}
include {
phase: TEST}
}
and this is the train.sh
./build/tools/caffe train \
-solver examples/corel5k/auto_train.prototxt \
-weights examples/corel5k/bvlc_reference_caffenet.caffemodel
But when I run this script, it got something wrong
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.SolverParameter: 1:5: Message type "caffe.SolverParameter" has no field named "name".
F0316 15:57:16.892113 3464 upgrade_proto.cpp:1063] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse SolverParameter file: examples/corel5k/auto_train.prototxt
*** Check failure stack trace: ***
# 0x7f79b3a4011d google::LogMessage::Fail()
# 0x7f79b3a41fbd google::LogMessage::SendToLog()
# 0x7f79b3a3fd38 google::LogMessage::Flush()
# 0x7f79b3a4281e google::LogMessageFatal::~LogMessageFatal()
# 0x7f79b4065ee7 caffe::ReadSolverParamsFromTextFileOrDie()
# 0x40a8c5 train()
# 0x407544 main
# 0x7f79b25a0ec5 (unknown)
# 0x407615 (unknown)
Aborted (core dumped)
I don't know what happened, look for help
You are confusion the net structure definition prototxt (a.k.a train_val.prototxt) with the solver definition prototxt (a.k.a solver.prototxt).
See, e.g., AlexNet example for these two different prototxt files.
The net structure definition, train_val.prototxt defines the net structure and looks like the auto_train.prototxt file you wrote.
However, you are missing the solver definition prototxt, solver.prototxt that defines meta parameters for the optimization process.
In your case a solver.prototxt would look something like:
net: "examples/corel5k/auto_train.prototxt" # here is where you put the net structure file
test_iter: 1000
test_interval: 1000
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "examples/corel5k/my_auto_snapshots"
solver_mode: GPU
You can find information on how to set the meta parameters in the solver.protoxt here and here.
Once you have a proper solver.prototxt you can run caffe:
./build/tools/caffe train \
-solver examples/corel5k/solver.prototxt \
-weights examples/corel5k/bvlc_reference_caffenet.caffemodel