Tahlil Ahmed Chowdhury

I think this [stackoverflow answer](https://stats.stackexchange.com/a/187404/114218) covers the confusion.

Same question here. Also /data/fonts/ directory missing as well.

Also I tried downloading data from [https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/YDEPUT](this) link. The E50 file is only 245MB instead of ~600 MB. But it downloaded successfully.

I'm having same issue. Mean IOU and focal loss are always 0. I am using mscoco data set. I have modified the data set such that the segmentation map has...

The iou actually going to the opposite direction. Its decreasing. First couple of iteration we can see that it decreased to nearly 0.  I have used...

Hi @YuhuiMa thanks very much for replying. To resolve the OOM error I rescaled each input and segmentation image to 256x256. After that I could train with 8 batch size....

The output segmentation map during training contains negative values. This is not supposed to happen. Each step the max min values of the seg map image is like on the...

On each iteration, the absolute value of the max min pixel value of the output segmentation map are almost equal. On the below image, the two values after `Training for...

After calculating softmax, first couple of step result 

The above images are generated from the prediction and ground_truth values calculated by the `evaluation` function on the dfn_model.py file.