6.2 使用pytorch搭建ResNet并基于迁移学习训练-6.2 使用pytorch搭建ResNet并基于迁移学习训练
热门回复:
- 互里艾变换:感谢博主。作为一个“半路出家”之人,一个没有经过系统性培训的研究僧,能有这样的教程感到受益良多!
- 霹雳吧啦Wz:课件已经上传到我的github上了,需要的可以自行下载
- bili_39010804077:up主,如果测试集有多张图片该怎么修改,是这样吗?
model = resnet34(num_classes=5)
# load model weights
model_weight_path = "./resNet34.pth"
model.load_state_dict(torch.load(model_weight_path, map_location=device))
model.eval()
acc = 0.0 # accumulate accurate number / epoch
optimizer = optim.Adam(model.parameters(), lr=0.0001)
with torch.no_grad():
for val_data in validate_loader:
val_images, val_labels = val_data
#optimizer.zero_grad()
outputs = model(val_images.to(device))
predict_y = torch.max(outputs, dim=1)【1】
acc += (predict_y == val_labels.to(device)).sum().item()
val_accurate = acc / val_num
print('test_accuracy: %.3f' %(val_accurate))
- 慎独yfs:RuntimeError: Error(s) in loading state_dict for ResNet:
size mismatch for fc.weight: copying a param with shape torch.Size(【1000, 512】) from checkpoint, the shape in current model is torch.Size(【2, 512】).
size mismatch for fc.bias: copying a param with shape torch.Size(【1000】) from checkpoint, the shape in current model is torch.Size(【2】).
博主,请问我第一遍训练的时候没有问题,为啥再训练会报这种错误啊,谢谢
- 你把小熊还给我哦:感谢博主,跑了你所有的网络模型,请问可以给训练模型上加上可视化,使每个epoch的结果都能保存下来,最后输出一张折线图吗?