[英]Pytorch object detection model optimization
I want to reduce the object detection model size.我想减小 object 检测 model 大小。 For the same, I tried optimising Faster R-CNN model for object detection using pytorch-mobile optimiser, but the
.pt
zip
file generated is of the same size as that of the original model size. For the same, I tried optimising Faster R-CNN model for object detection using pytorch-mobile optimiser, but the
.pt
zip
file generated is of the same size as that of the original model size.
I used the code mention below我使用了下面提到的代码
import torch
import torchvision
from torch.utils.mobile_optimizer import optimize_for_mobile
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()
script_model = torch.jit.script(model)
from torch.utils.mobile_optimizer import optimize_for_mobile
script_model_vulkan = optimize_for_mobile(script_model, backend='Vulkan')
torch.jit.save(script_model_vulkan, "frcnn.pth")
You have to quantize your model first你必须先量化你的 model
follow these steps here在此处按照以下步骤操作
& then use these methods & 然后使用这些方法
from torch.utils.mobile_optimizer import optimize_for_mobile
script_model_vulkan = optimize_for_mobile(script_model, backend='Vulkan')
torch.jit.save(script_model_vulkan, "frcnn.pth")
EDIT:编辑:
Quantization process for resnet50 model resnet50 model的量化过程
import torchvision
model = torchvision.models.resnet50(pretrained=True)
import os
import torch
def print_model_size(mdl):
torch.save(mdl.state_dict(), "tmp.pt")
print("%.2f MB" %(os.path.getsize("tmp.pt")/1e6))
os.remove('tmp.pt')
print_model_size(model) # will print original model size
backend = "qnnpack"
model.qconfig = torch.quantization.get_default_qconfig(backend)
torch.backends.quantized.engine = backend
model_static_quantized = torch.quantization.prepare(model, inplace=False)
model_static_quantized = torch.quantization.convert(model_static_quantized, inplace=False)
print_model_size(model_static_quantized) ## will print quantized model size
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.