-
恭喜您做的这个杰出的工作
我在运行train.py的时候出现如下报错：
there are total 200 batches for train
there are total 52 batches for val
student model params: 1675281
/home/C/pxd/.conda/envs/test/lib/python3.7/site-packages…
-
@MathiasGruber Hi, I've used your code to get pretty decent results but when ever there is a lighter background in image such as sky , some noise is added as a result. But your deployed model on [ ww…
-
Running this command `python -B main.py -t --batch_size 40 --epochs 200 --base_learning_rate=0.0001` gave me this error. Can you tell me where is that file ?
IOError: [Errno 2] No such file or dire…
-
```python
import coremltools as ct
import torch
import torchvision
import torch.nn as nn
class Wrapper(nn.Module):
def __init__(self, model_name):
super(Wrapper, self).__init__()
…
-
Thanks for your code about binlinaer CNN，but I have a question, I have read this paper, and I think there are two CNN in this model, but I can't find them in your code, I only find one VGG-16 net, di…
-
#359 Summary of the bug
I am running the tutorials found here - [Mapping vehicles](https://github.com/jshermeyer/solaris_cowc/blob/master/map_vehicles_cowc.ipynb) & [Tiling tutorial](https://solari…
-
Hello,
Abstract:
I tried to train SSD 512 on MS-COCO dataset.
By comparing my local train.log information with the official log https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/logs…
-
# Console Error Log
2018-05-06 17:38:44.599331: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: ConcatOp : Dimensions of inputs should match: shape[0] = [1,400,600,1] vs. shape[4] = …
-
I've tried to update py-faster-rcnn as @happyharrycn proposed here [https://github.com/rbgirshick/py-faster-rcnn/issues/172](url) (updated caffe branch and used the latest CudNN v5). After that I coul…
-
Hi. I've been trying to reproduce your example with the cat.txt file. However, the resulting number from the dense layers is 7, which is equivalent to the "cock" class.
I've used the weights that y…