alexmontgomerie / fpgaconvnet-tutorial Goto Github PK
View Code? Open in Web Editor NEWA collection of tutorials for the fpgaConvNet framework.
Home Page: https://fpgaconvnet.com
License: MIT License
A collection of tutorials for the fpgaConvNet framework.
Home Page: https://fpgaconvnet.com
License: MIT License
net.load_network("outputs/single_layer_opt.json")ERROR
# load the optimised network
net.load_network("outputs/single_layer_opt.json") # TODO: change name
net.update_partitions()
# print the performance and resource predictions
print(f"predicted latency (us): {net.get_latency()*1000000}")
print(f"predicted throughput (img/s): {net.get_throughput()} (batch size={net.batch_size})")
print(f"predicted resource usage: {net.partitions[0].get_resource_usage()}")
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[2], line 2
1 # load the optimised network
----> 2 net.load_network("outputs/single_layer_opt.json") # TODO: change name
3 net.update_partitions()
5 # print the performance and resource predictions
File ~\AppData\Roaming\Python\Python38\site-packages\fpgaconvnet\models\network\Network.py:274, in Network.load_network(self, network_path)
271 for layer in partition.layers:
272 # get layer type and hardware
273 layer_type = fpgaconvnet.tools.layer_enum.from_proto_layer_type(layer.type)
--> 274 layer_hw = self.get_layer_hardware(layer)
275 # add layer
276 graph.add_node( layer.name, type=layer_type, hw=layer_hw, inputs={} )
File ~\AppData\Roaming\Python\Python38\site-packages\fpgaconvnet\models\network\Network.py:193, in Network.get_layer_hardware(self, layer_proto)
191 # Convolution layer
192 if layer_type == LAYER_TYPE.Convolution:
--> 193 return ConvolutionLayer(
194 layer_proto.parameters.channels_out,
195 layer_proto.parameters.rows_in,
196 layer_proto.parameters.cols_in,
197 layer_proto.parameters.channels_in,
198 kernel_size =list(layer_proto.parameters.kernel_size),
199 stride =list(layer_proto.parameters.stride),
200 pad = [
201 layer_proto.parameters.pad_top,
202 layer_proto.parameters.pad_right,
203 layer_proto.parameters.pad_bottom,
204 layer_proto.parameters.pad_left],
205 groups =layer_proto.parameters.groups,
206 fine =layer_proto.parameters.fine,
207 coarse_in =layer_proto.parameters.coarse_in,
208 coarse_out =layer_proto.parameters.coarse_out
209 )
211 # Inner Product Layer
212 if layer_type == LAYER_TYPE.InnerProduct:
TypeError: 'module' object is not callable
I began to think that the ConvolutionLayer initialization failed, and the initialization function I added to it still failed
Hello. Could you please upload your "lenet.onnx" file used in "fpgaconvnet-optimiser-tutorial.ipynb"?The hyperlink is invalid and the code doesn't work correctly with my lenet model.
Thanks.
Hello,
your pypi package specifies fpgaconvnet homepage as /https://github.com/AlexMontgomerie/fpgaconvnet-optimiser this link does not work and I do not see it anywhere else.
Same applies to this tutorial:
https://github.com/AlexMontgomerie/fpgaconvnet-tutorial/blob/main/fpgaconvnet-hls-tutorial.md
https://github.com/AlexMontgomerie/fpgaconvnet-optimiser
https://github.com/AlexMontgomerie/fpgaconvnet-hls
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.