-
* 개요
> base 모델을 찾기 위한 pretrained 모델별 성능비교를 해봤습니다.
optimizer, dataset, batchsize, criterion 등은 동일하고,
모델에 따라 출력 레이어에서 1) dropout(0.5) 추가나 2) fc layer만 변경, 3) 기존 모델 그대로 사용 등 약간의 차이만 있습니다.
아래는 모델이외의 …
-
I get this error when I am doing graph_def.ParseFromString(fileContent). Any ideas on why this occurs or how to correct it?
-
When I ran ./train_fcn32s.py -g 0，I got this error
Traceback (most recent call last):
File "/home/jbwen/anaconda3/envs/py36/lib/python3.6/site-packages/urllib3/connection.py", line 160, in _new_co…
-
I confused about this paper and the code, you have two networks that produce pseudo point-level annotations and generate the localization map perspectively or one network to realize two functions ?
I…
-
Hi, farrajota
I trained and tested the fastrcnn with voc dataset, everything goes well.
I trained the fastrcnn in coco dataset with no error, when I tested the accuracy with the trained model, error…
-
It is quite slow to process one frame, like 300-400ms/fame on a titanX card.
R-FCN is faster from the paper, but I am not able to make it working because of lacking Matlab.
Just wondering how much spe…
-
In Notebook 5, the model is loaded by using:
model.load(r"C:\Users\Mathias Felix Gruber\Documents\GitHub\PConv-Keras\data\logs\imagenet_phase2\weights.26-1.07.h5", train_bn=False)
But where can I…
-
My training uses the voc2007 dataset, which only gets about 72.5% of mAP. The backbone network used for training uses vgg16_reducedfc.pth downloaded online. What is the reason? Is it because I didn't …
-
Projector.py converts your target image to RGB but this of course causes an assertion error with a network trained on greyscale images. I am working on resolving this on my own. Here is the snippet of…
-
Hi,
I followed the instruction on the README to extract feature from an image by using VGG16 model. When I did
```
features = model.predict(x)
```
I found the dimension of the features is of `(…