I'm trying to run a prediction on a model of caffe2, convert from caffe using the script included with caffe2. The script terminates correctly, giving me "init_net.pb" and "predict_net.pb".
When I try to call the Predictor method run() I get the following error message:
Traceback (most recent call last):
File "caffe2Inference.py", line 23, in <module>
results = p.run(input)
RuntimeError: [enforce fail at conv_op_impl.h:21] X.ndim() == filter.ndim(). 3 vs 4 Error from operator:
input: "data" input: "conv1/time_w" input: "conv1/time_b" output: "conv1/time" type: "Conv" arg { name: "stride" i: 1 } arg { name: "pad" i: 0 } arg { name: "kernel_h" i: 7 } arg { name: "kernel_w" i: 1 }
This is my code for performing the inference:
# load up the caffe2 workspace
from caffe2.python import workspace, core
import numpy as np
# helper image processing functions
#import caffe2.python.tutorials.helpers as helpers
name= "scnn+fc/"
INIT_NET = name+"/init_net.pb"
PREDICT_NET = name+"/predict_net.pb"
#read protobuf
with open(INIT_NET,"rb") as f:
init_net = f.read()
with open(PREDICT_NET,"rb") as f:
predict_net = f.read()
# you must name it something
workspace.RunNetOnce(init_net)
workspace.CreateNet(predict_net)
p = workspace.Predictor(init_net, predict_net)
input = np.ones((1,1,63,13))
# submit the image to net and get a tensor of results
results = p.run(input)
res= np.asarray(results)
#response = helpers.parseResults(results)
# and lookup our result from the list
And this is my original .prototxt
name: "UNIPINET"
#input:"data"
#input_shape: { dim: 1 dim: 1 dim: 63 dim: 13 }
layer { name: "data"
type: "Input"
top: "data"
input_param
{
shape
{
dim: 1
dim: 3
dim: 224
dim: 224
}
}
}
layer {
name: "conv1/time"
type: "Convolution"
bottom: "data"
top: "conv1/time"
convolution_param {
num_output: 1
bias_term: true
kernel_h: 7
kernel_w: 1
#engine: CAFFE
stride: 1
}
}
layer {
name: "conv1/freq"
type: "Convolution"
bottom: "conv1/time"
top: "conv1/freq"
convolution_param {
num_output: 32
bias_term: true
kernel_h:1
kernel_w:3
stride: 1
}
}
layer {
name: "conv1/freq/bn"
type: "BatchNorm"
bottom: "conv1/freq"
top: "conv1/freq/bn"
}
layer {
name: "conv1/freq/bn/scale"
type: "Scale"
bottom: "conv1/freq/bn"
top: "conv1/freq/bn/scale"
scale_param{
bias_term: true
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1/freq/bn/scale"
top: "relu1"
}
layer {
name: "conv2/time"
type: "Convolution"
bottom: "relu1"
top: "conv2/time"
convolution_param {
num_output: 32
bias_term: true
kernel_h: 15
kernel_w: 1
pad_h:7
#engine: CAFFE
stride: 1
}
}
layer {
name: "conv2/freq"
type: "Convolution"
bottom: "conv2/time"
top: "conv2/freq"
convolution_param {
num_output: 32
bias_term: true
kernel_h:1
kernel_w:3
pad_w:1
stride: 1
}
}
layer {
name: "conv2/freq/bn"
type: "BatchNorm"
bottom: "conv2/freq"
top: "conv2/freq/bn"
}
layer {
name: "conv2/freq/bn/scale"
type: "Scale"
bottom: "conv2/freq/bn"
top: "conv2/freq/bn/scale"
scale_param{
bias_term: true
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2/freq/bn/scale"
top: "relu2"
}
layer {
name: "conv3/time"
type: "Convolution"
bottom: "relu2"
top: "conv3/time"
convolution_param {
num_output: 32
bias_term: true
kernel_h: 13
kernel_w: 1
pad_h:6
#engine: CAFFE
stride: 1
}
}
layer {
name: "conv3/freq"
type: "Convolution"
bottom: "conv3/time"
top: "conv3/freq"
convolution_param {
num_output: 128
bias_term: true
kernel_h:1
kernel_w:3
pad_w:1
stride: 1
}
}
layer {
name: "conv3/freq/bn"
type: "BatchNorm"
bottom: "conv3/freq"
top: "conv3/freq/bn"
}
layer {
name: "conv3/freq/bn/scale"
type: "Scale"
bottom: "conv3/freq/bn"
top: "conv3/freq/bn/scale"
scale_param{
bias_term: true
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3/freq/bn/scale"
top: "relu3"
}
layer {
name: "avg_pool"
type: "Pooling"
bottom: "relu3"
top: "avg_pool"
pooling_param {
pool: MAX
global_pooling: true
}
}
layer {
name: "fc"
type: "InnerProduct"
bottom: "avg_pool"
top: "fc"
inner_product_param {
num_output: 12
}
}
layer {
name: "output"
type: "Softmax"
bottom: "fc"
top: "output"
}
