Comments (4)
fp16 is not supported with nv_small
I have some instructions documented at https://github.com/prasshantg/personal check if it helps
from vp.
thanks prasshantg for sharing.
I used below setting same with you, there are some errors. How about you?
% ./nvdla_compiler --prototxt ResNet-50-deploy.prototxt --caffemodel ResNet-50-model.caffemodel --configtarget nv_small --profile fast-math --cprecision int8 --calibtable nvdla/sw-new/umd/utils/calibdata/resnet50.json --quantizationMode per-filter --batch 1 --informat nhwc
creating new wisdom context...
opening wisdom context...
parsing caffe network...
libnvdla<3> mark prob
Marking total 1 outputs
parsing calibration table...
attaching parsed network to the wisdom...
compiling profile "fast-math"... config "nv_small"...
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
libnvdla<2> Scale value 1 for 1.41276e-06 is too small (threshold: 2)
libnvdla<2> Scale value 1 for 1.01866e-06 is too small (threshold: 2)
libnvdla<2> Scale value 1 for 1.48463e-06 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 1.62639e-06 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 6.84193e-07 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 5.3635e-07 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 2.58676e-07 is too small (threshold: 2)
closing wisdom context...
from vp.
thanks prasshantg for sharing.
I used below setting same with you, there are some errors. How about you?% ./nvdla_compiler --prototxt ResNet-50-deploy.prototxt --caffemodel ResNet-50-model.caffemodel --configtarget nv_small --profile fast-math --cprecision int8 --calibtable nvdla/sw-new/umd/utils/calibdata/resnet50.json --quantizationMode per-filter --batch 1 --informat nhwc
creating new wisdom context...
opening wisdom context...
parsing caffe network...
libnvdla<3> mark prob
Marking total 1 outputs
parsing calibration table...
attaching parsed network to the wisdom...
compiling profile "fast-math"... config "nv_small"...
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
(DLA) Error 0x00000002: Don't support 0 (in engine-ast/ConvCoreNode.cpp, function tryToMergeWithBatchNormOp(), line 1240)
libnvdla<2> Scale value 1 for 1.41276e-06 is too small (threshold: 2)
libnvdla<2> Scale value 1 for 1.01866e-06 is too small (threshold: 2)
libnvdla<2> Scale value 1 for 1.48463e-06 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 1.62639e-06 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 6.84193e-07 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 5.3635e-07 is too small (threshold: 2)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
(DLA) Error 0x0000000b: Scale value is 0 for 0.000000
(in ./include/priv/LowPrecision.h, function scaleAndShiftFromScalarImpl2(), line 281)
libnvdla<2> Scale value 1 for 2.58676e-07 is too small (threshold: 2)
closing wisdom context...
hello, did you fix this problem?
from vp.
hello, I have the same problem, did you fix it?
hello, I have the same problem, did you fix it?
from vp.
Related Issues (20)
- Segmentation Fault while running VP HOT 1
- make error : Pixman HOT 1
- Debugging virtual platform with gdb ( related with #11 ) HOT 1
- VP Error for NV_Small and Int8 for LeNET Network HOT 3
- your-image-afi-global-id HOT 1
- VP FPGA Lenet Error ((DLA_TEST) Error 0x00000002 and NvDlaSubmit: Error IOCTL failed (No such process)) HOT 4
- nvdla / vp cmake error for nv_full HOT 2
- VP FPGA Compile Error:aarch64_toplevel.cpp:(.text+0x1932): undefined reference to `SimpleCPU::set_pci_bar_handle(int)' HOT 7
- VP FPGA Error: "modprobe: ERROR: could not insert 'edma_drv': Exec format error" HOT 14
- How to run VP on Computer Cluster?
- Huge Log Output Control (The size get more than 30GB ) HOT 2
- NV_SMALL_256 Error
- Errors in .json upon make of vp
- The gcc version when make vp HOT 1
- CMOD Build Error HOT 1
- undefined reference to `sc_core::sc_vector_base::make_name(char const*, unsigned long)'
- Performance Model Status?
- SystemC 2.3.3
- not aarch64 I want to use amd64
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vp.