Comments (3)
I did this:
export PYTHONPATH=$PYTHONPATH:~/repo/gap_sdk/tools/nntool/nntool
It found stats but raised errors:
Traceback (most recent call last):
File "/home/user/repo/gap_sdk/tools/nntool/scripts/nntool", line 107, in <module>
main()
File "/home/user/repo/gap_sdk/tools/nntool/scripts/nntool", line 89, in main
mod.generate_code(args)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/interpreter/generator.py", line 72, in generate_code
nntool_shell.load_state_file(args.graph_file)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/interpreter/nntool_shell_base.py", line 383, in load_state_file
self.replay_history()
File "/home/user/repo/gap_sdk/tools/nntool/nntool/interpreter/nntool_shell_base.py", line 365, in replay_history
if self.onecmd_plus_hooks(command, add_to_history=False):
File "/home/aurelio/environments/GAP/lib/python3.10/site-packages/cmd2/cmd2.py", line 1695, in onecmd_plus_hooks
self.pexcept(ex)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/interpreter/nntool_shell_base.py", line 357, in pexcept
raise msg
File "/home/aurelio/environments/GAP/lib/python3.10/site-packages/cmd2/cmd2.py", line 1661, in onecmd_plus_hooks
stop = self.onecmd(statement, add_to_history=add_to_history)
File "/home/aurelio/environments/GAP/lib/python3.10/site-packages/cmd2/cmd2.py", line 2081, in onecmd
stop = func(statement)
File "/home/aurelio/environments/GAP/lib/python3.10/site-packages/cmd2/decorators.py", line 223, in cmd_wrapper
return func(cmd2_app, args)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/interpreter/commands/fquant.py", line 113, in do_fquant
quantizer.quantize()
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 975, in quantize
self.bfs_pass()
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 651, in bfs_pass
self._bfs_pass(self._graph, node, self._qset, visited)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 587, in _bfs_pass
self._bfs_pass(cur_G, edge.to_node, qset,
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 553, in _bfs_pass
qrec = self._resolve_qrec(
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 613, in _resolve_qrec
qrec = self._call_quantizer(cur_G,
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/quantizer/new_quantizer.py", line 448, in _call_quantizer
return handler.quantize(node, in_qs, stats, **kwargs)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/unified_quantization_handler.py", line 123, in quantize
return cls._quantize(params, in_qs, stats, **kwargs)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/multiplicative/quantizers/filter_mult.py", line 300, in _quantize
return cls._quantize_sw(params, in_qs, stats, np.int8, **kwargs)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/multiplicative/quantizers/filter_mult.py", line 225, in _quantize_sw
min_val, max_val = stats.get_range_out(0, bits=out_bits)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/range_provider.py", line 50, in get_range_out
return self._provider.get_range(self._nid, 'out', idx, bits=bits, dtype=dtype,
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/range_provider.py", line 195, in get_range
return self.get_range_out(nid, idx, bits=bits, dtype=dtype)
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/range_provider.py", line 170, in get_range_out
stat = self.get_stat(nid)['range_out'][idx]
File "/home/user/repo/gap_sdk/tools/nntool/nntool/quantization/range_provider.py", line 135, in get_stat
raise RangesMissingError(f'no ranges found for {nid}')
nntool.quantization.range_provider.RangesMissingError: no ranges found for DEPTHWISE_CONV_2D_0_128
from gap_sdk.
Did you source the sdk?
from gap_sdk.
Yes. Through sourcream.sh and later through sourcing the ai_deck.sh config directly. Both lead to this error.
Info: I am trying to recreate the NanoFlowNet implementation for obstacle avoidance on the ai deck. I opened an issue in that git aswell, in case this error emerges from non gap_sdk related factors.
from gap_sdk.
Related Issues (20)
- Is Branch Prediction Possible in GAP8? HOT 1
- Deprecated function
- Unnable to setup the sdk, make doesn't work. HOT 6
- Error when trying to run helloworld example in the board HOT 15
- Nina's streamer libraries fail when compiling HOT 3
- Outputs of network different between runnning on AI-deck and as quantized network in tflite HOT 1
- Error when 'open *.onnx'.
- Failed to run the benchmarks HOT 2
- 2D DMA transfer expected behaviour
- Problem with generating the model in coco object detection notebook with nntools HOT 2
- TypeError: execute_on_target() got an unexpected keyword argument 'write_out_to_file'
- Error: Failed to allocate graph symbol memory for graph ssd_mobv2_quantCNN
- how to measure the power consumption and latency in gvsoc simulation HOT 4
- Graph constructor error HOT 1
- Errors when trying to modify architecture parameters of GVSOC(like RAM sizes)
- Issue Installing GAP SDK on macOS and Alternative Setup
- ValueError: missing generator: the matrix add generator only handles adds of tensors of the same size
- Using gap8 based perfxlab beetle board with OS X
- imp module outdated
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 gap_sdk.