Open eekarot opened 1 week ago
2024.2.0-15519-5c0f38f83f6-releases/2024/2
Ubuntu 22.04 (LTS)
CPU
PyPi
Python
x86 (64 bits)
full-connected network
Yes
CPU: Intel Xeon Gold 5433N
network: self.fc1 = nn.Linear(64,128) self.fc2 = nn.Linear(128,128) self.fc3 = nn.Linear(128,128) self.fc4 = nn.Linear(128,64) Input shape : [1,64,64]
Convert & quantization step: input = torch.rand(1,64,64) ov_model = ov.convert_model(net, example_input=input) quant_ov_model = nncf.quantize(ov_model, quantization_dataset)
Result: fp32 : 12872fps int8 : 12843fps
No response
@MaximProshin, @alexsu52, please take a look.
Regards, Roman
OpenVINO Version
2024.2.0-15519-5c0f38f83f6-releases/2024/2
Operating System
Ubuntu 22.04 (LTS)
Device used for inference
CPU
OpenVINO installation
PyPi
Programming Language
Python
Hardware Architecture
x86 (64 bits)
Model used
full-connected network
Model quantization
Yes
Target Platform
CPU: Intel Xeon Gold 5433N
Performance issue description
network: self.fc1 = nn.Linear(64,128) self.fc2 = nn.Linear(128,128) self.fc3 = nn.Linear(128,128) self.fc4 = nn.Linear(128,64) Input shape : [1,64,64]
Convert & quantization step: input = torch.rand(1,64,64) ov_model = ov.convert_model(net, example_input=input) quant_ov_model = nncf.quantize(ov_model, quantization_dataset)
Result: fp32 : 12872fps int8 : 12843fps
Step-by-step reproduction
No response
Issue submission checklist