Skip to content

Commit

Permalink
fix bug
Browse files Browse the repository at this point in the history
  • Loading branch information
@i-evi
i-evi committed Oct 4, 2020
1 parent d02985b commit 1563373
Show file tree
Hide file tree
Showing 5 changed files with 55 additions and 79 deletions.
2 changes: 1 addition & 1 deletion demo/lenet.lua
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ network = {
l4 = conv2d ({input = "l3", stride = 1, padding = 2}),
l5 = relu ({input = "l4"}),
l6 = maxPool2d ({input = "l5", stride = 2}),
l7 = reshape ({input = "l6", shape = {-1, 1}}),
l7 = reshape ({input = "l6", shape = {-1, 1, 1}}),
l8 = fullyConnected ({input = "l7"}),
l9 = relu ({input = "l8"}),
l10 = fullyConnected ({input = "l9"}),
Expand Down
5 changes: 1 addition & 4 deletions src/cc_basic.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -72,10 +72,7 @@ void cc_tensor_shape_fix(cc_int32 *shape, cc_int32 elems)
s *= v;
sptr++;
}
if (s != elems) {
#ifdef ENABLE_CC_ASSERT
cc_assert(f);
#endif
if (s != elems || f) {
shape[i] = elems / s;
}
}
Expand Down
26 changes: 8 additions & 18 deletions src/cc_dsc2d.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,24 +19,22 @@
#include "global_fn_cfg.h"
extern fn_conv2d _conv2d;
extern fn_array_add_ew _array_add_ew;
extern fn_array_mul_by _array_add_by;
extern fn_array_mul_by _array_mul_by;

cc_tensor_t *cc_dw_conv2d(cc_tensor_t *inp,
const cc_tensor_t *kernel, const cc_tensor_t *bias,
cc_int32 s, cc_int32 p, cc_int32 off, const char *name)
{
cc_uint8 *omp_out_buf = NULL;
cc_tensor_t *inp_pad, *oup = NULL;
cc_int32 o_ch_size, p_ch_mem_size, o_ch_mem_size,
k_ch_mem_size, k_mem_size, num_omp_threads, i;
cc_int32 o_ch_size, p_ch_mem_size, o_ch_mem_size, k_ch_mem_size, i;
cc_int32 shape[CC_CNN2D_SHAPE] = {0};
char pad_name[CC_CONV2D_PAD_NAME_LEN];
#ifdef ENABLE_CC_ASSERT
cc_assert_zero(cc_tensor_dimension(inp) - CC_CNN2D_DIM);
cc_assert_zero(cc_tensor_dimension(kernel) - CC_CONV2D_KERNEL_DIM);
cc_assert_zero(*inp->dtype - *kernel->dtype);
cc_assert_zero(inp->shape[CC_CNN2D_SHAPE_C]
- kernel->shape[CC_CONV2D_KERNEL_I]);
- kernel->shape[CC_CONV2D_KERNEL_O]);
#endif
if (p) {
sprintf(pad_name, "%s%s",
Expand All @@ -49,7 +47,7 @@ cc_tensor_t *cc_dw_conv2d(cc_tensor_t *inp,
oup = cc_tsrmgr_get(name);
#endif
if (!oup) {
shape[CC_CNN2D_SHAPE_C] = kernel->shape[CC_CONV2D_KERNEL_I];
shape[CC_CNN2D_SHAPE_C] = kernel->shape[CC_CONV2D_KERNEL_O];
shape[CC_CNN2D_SHAPE_H] = cc_conv2d_shape_calc(
inp->shape[CC_CNN2D_SHAPE_H],
kernel->shape[CC_CONV2D_KERNEL_H], s, p);
Expand All @@ -67,32 +65,24 @@ cc_tensor_t *cc_dw_conv2d(cc_tensor_t *inp,
k_ch_mem_size = kernel->shape[CC_CONV2D_KERNEL_W] *
kernel->shape[CC_CONV2D_KERNEL_H] *
cc_dtype_size(*kernel->dtype);
k_mem_size = k_ch_mem_size * kernel->shape[CC_CONV2D_KERNEL_I];
num_omp_threads = 1;
#ifdef ENABLE_OPENMP
num_omp_threads = omp_get_max_threads();
#endif
cc_assert_alloc(omp_out_buf =
(cc_uint8*)malloc(o_ch_mem_size * num_omp_threads));
#ifdef AUTO_TSRMGR
memset(oup->data, 0,
list_getlen(oup->container, CC_TENSOR_DATA));
#endif
#ifdef ENABLE_OPENMP
#pragma omp parallel for private(i)
#endif
for (i = 0; i < kernel->shape[CC_CONV2D_KERNEL_I]; ++i) {
for (i = 0; i < kernel->shape[CC_CONV2D_KERNEL_O]; ++i) {
_conv2d((inp_pad->data + i * p_ch_mem_size),
oup->data + i * o_ch_mem_size,
inp_pad->shape[CC_CNN2D_SHAPE_W],
inp_pad->shape[CC_CNN2D_SHAPE_H],
oup->shape[CC_CNN2D_SHAPE_W],
oup->shape[CC_CNN2D_SHAPE_H], s, s,
kernel->data + (k_mem_size * i),
kernel->data + (k_ch_mem_size * i),
kernel->shape[CC_CONV2D_KERNEL_W],
*kernel->dtype);
}
free(omp_out_buf);
if (!bias){
#ifndef AUTO_TSRMGR
if (p)
Expand Down Expand Up @@ -157,7 +147,7 @@ cc_tensor_t *cc_pw_conv2d(cc_tensor_t *inp, const cc_tensor_t *kernel,
for (j = 0; j < kernel->shape[CC_CONV2D_KERNEL_I]; ++j)
{
#ifdef ENABLE_OPENMP
_array_add_by(
_array_mul_by(
omp_out_buf + omp_get_thread_num() * o_ch_mem_size,
o_ch_size, inp->data + o_ch_mem_size * j,
kernel->data + k_mem_size * i + k_ch_mem_size * j,
Expand All @@ -167,7 +157,7 @@ cc_tensor_t *cc_pw_conv2d(cc_tensor_t *inp, const cc_tensor_t *kernel,
omp_out_buf + omp_get_thread_num() * o_ch_mem_size,
*oup->dtype);
#else
_array_add_by(omp_out_buf, o_ch_size,
_array_mul_by(omp_out_buf, o_ch_size,
inp->data + o_ch_mem_size * j,
kernel->data + k_mem_size * i + k_ch_mem_size * j,
*oup->dtype);
Expand Down
4 changes: 2 additions & 2 deletions src/cc_normfn.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -64,8 +64,8 @@ cc_tensor_t *cc_batch_norm2d(cc_tensor_t *inp,
ch_size = inp->shape[CC_CNN2D_SHAPE_H] *
inp->shape[CC_CNN2D_SHAPE_W];
ch_mem_size = ch_size * dt_size;
for (i = 0; i < inp->shape[CC_CNN2D_SHAPE_C]; ++i) {
_batch_norm(inp->data + ch_mem_size * i, ch_size,
for (i = 0; i < oup->shape[CC_CNN2D_SHAPE_C]; ++i) {
_batch_norm(oup->data + ch_mem_size * i, ch_size,
para->data + CC_NORM_PARAMETERS * dt_size * i,
*para->dtype);
}
Expand Down
97 changes: 43 additions & 54 deletions util/lua2cc.lua
View file
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
local parameterLv = 0 -- PKG: Begin at 0
local parameterLv = 0 -- PKG: Begin at 0
local shapeCounter = 0
local layerCounter = 1 -- MUST Begin at 1
local parameterCnt = 1 -- MUST Begin at 1
Expand Down Expand Up @@ -70,8 +70,8 @@ dwConv2d = function(args)
if type(scope) == "string" then
name = string.format("%s/%s", scope, name)
end
parals[info.paraId + 0] = string.format("%03d_w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d_b", info.paraLv)
parals[info.paraId + 0] = string.format("%03d.w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d.b", info.paraLv)
layerOutputs[ret.layerId] = output
if info.input == nil then
if info.layerId - 1 < 1 then
Expand All @@ -80,7 +80,7 @@ dwConv2d = function(args)
info.input = string.format("@%d", info.layerId - 1)
end
return string.format(
"%s = cc_conv2d(%s, __pls[%d], __pls[%d], %d, %d, %d, \"%s\");",
"%s = cc_dw_conv2d(%s, __pls[%d], __pls[%d], %d, %d, %d, \"%s\");",
output, info.input, info.paraId - 1, info.paraId, info.stride,
info.padding, info.offset, name)
end
Expand All @@ -100,8 +100,8 @@ pwConv2d = function(args)
if type(scope) == "string" then
name = string.format("%s/%s", scope, name)
end
parals[info.paraId + 0] = string.format("%03d_w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d_b", info.paraLv)
parals[info.paraId + 0] = string.format("%03d.w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d.b", info.paraLv)
layerOutputs[ret.layerId] = output
if info.input == nil then
if info.layerId - 1 < 1 then
Expand Down Expand Up @@ -129,8 +129,8 @@ fullyConnected = function(args)
if type(scope) == "string" then
name = string.format("%s/%s", scope, name)
end
parals[info.paraId + 0] = string.format("%03d_w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d_b", info.paraLv)
parals[info.paraId + 0] = string.format("%03d.w", info.paraLv)
parals[info.paraId + 1] = string.format("%03d.b", info.paraLv)
layerOutputs[ret.layerId] = output
if info.input == nil then
if info.layerId - 1 < 1 then
Expand Down Expand Up @@ -243,7 +243,7 @@ batchNorm2d = function(args)
if type(scope) == "string" then
name = string.format("%s/%s", scope, name)
end
parals[info.paraId] = string.format("%03d_n", info.paraLv)
parals[info.paraId] = string.format("%03d.n", info.paraLv)
layerOutputs[ret.layerId] = output
if info.input == nil then
if info.layerId - 1 < 1 then
Expand All @@ -252,7 +252,7 @@ batchNorm2d = function(args)
info.input = string.format("@%d", info.layerId - 1)
end
return string.format(
"%s = cc_batch_norm(%s, __pls[%d], \"%s\");",
"%s = cc_batch_norm2d(%s, __pls[%d], \"%s\");",
output, info.input, info.paraId - 1, name)
end
return ret
Expand Down Expand Up @@ -288,63 +288,50 @@ reshape = function(args)
return ret
end

local fprint = function(fp, ...)
local fputs = function(fp, ...)
local args = { ... }
local flag = false
for k, v in pairs(args) do
if not flag then
flag = true
else
fp:write('\t')
end
fp:write(v)
end
fp:write('\n')
end

local printLine = function(line, indent)
if indent == nil then indent = 0 end
local lineLimit = 80
local indentOff = indent * 8
local llen = #line + indentOff
local indentStr = string.rep("\t", indent)
line = indentStr..line
if llen <= 80 then
fprint(_ctrlfp, line)
return
end
local prev = 0
local curr = 0
local csr = 1
local brk = 0
local pos = 0
local nextword = ""

repeat
curr, _ = string.find(line, ',', prev + 1)
if curr == nil then
break
if pos == 0 then
pos = indentOff
fputs(_ctrlfp, indentStr)
end
if (curr + indentOff) >= 80 then
local buf = string.sub(line, 1, prev)
fprint(_ctrlfp, buf)
line = string.sub(line, prev + 1)
if string.byte(line, 1) == 32 then
line = string.sub(line, 2)
end
brk, _ = string.find(line, ',', csr)
if brk ~= nil then
nextword = string.sub(line, csr, brk)
else
nextword = string.sub(line, csr)
end
csr = csr + #nextword
if pos + #nextword >= lineLimit then
fputs(_ctrlfp, '\n');
pos = indentOff
fputs(_ctrlfp, indentStr)
end
prev = curr
until (#line + indentOff) < 80
if #line > 80 then
local looking = string.byte(',', 1)
for i = #line, 60, -1 do
if string.byte(line, i) == looking then
fprint(_ctrlfp, string.sub(line, 1, i))
line = string.sub(line, i + 1)
break
if pos == indentOff then
local off, _ = string.find(nextword, ' ')
if off == 1 then
nextword = string.sub(nextword, 2)
end
end
end
curr, _ = string.find(line, ' ')
if curr == 1 then
line = string.sub(line, 2)
end
line = indentStr..line
fprint(_ctrlfp, line)
fputs(_ctrlfp, string.format("%s", nextword))
pos = pos + #nextword
until csr >= #line
fputs(_ctrlfp, '\n')
end

local runningFlag = true
Expand Down Expand Up @@ -418,7 +405,8 @@ ccCodeTranslator = function(net, cfg)
"static cc_tensor_t *__pls[%d];", #paraxList), indentOff + 0)

local layerDef = "cc_tensor_t "
for k, v in pairs(createTsr) do
for k = 1, #createTsr do
v = createTsr[k]
layerDef = layerDef..string.format("*%s, ", v)
end
layerDef = string.sub(layerDef, 1, #layerDef - 2)..";"
Expand All @@ -431,7 +419,8 @@ ccCodeTranslator = function(net, cfg)
"__pls[i] = cc_tsrmgr_get(p_namels[i]);"), indentOff + 1)
printLine("}", indentOff + 0)

for k, v in pairs(codeLines) do
for k = 1, #codeLines do
v = codeLines[k]
v = string.gsub(v, "@%d*,",
function(s)
return string.format("%s,",
Expand Down

0 comments on commit 1563373

Please sign in to comment.