jiewen

thanks the code, when use discriminator, gl inpaint input maybe use `input_gd_fake = x * (1 - mask) + input_gd_fake * mask`, while in this line `input_gd_fake ` direct use...

thanks you code , when i read the code , the discriminator use sigmoid output, but you also return D_real_logits ,and when caluate the loss real or fake ,you use...

infer_simple.py error ?

1

- i run the scripts use you main result models ,but get error : ``` /home/rjw/anaconda3/envs/tf1.8_torch0.4_py3.5/bin/python /home/rjw/desktop/maskrcnn/PANet-master/tools/infer_simple.py --dataset coco --cfg ./configs/panet/e2e_panet_R-50-FPN_2x_mask.yaml --load_detectron /home/rjw/desktop/maskrcnn/PANet-master/panet_mask_step179999.pth --image_dir ./demo/sample_images --output_dir ./demo/ Called with args:...

deep-learning-models/vgg16.py

2

when i run the vgg16.py models, i meet a problem > File "F:/RANJIEWEN/Deep_learning/keras_tflearn/VGG16.py", line 186, in model = VGG16(include_top=True, weights='imagenet') File "F:/RANJIEWEN/Deep_learning/keras_tflearn/VGG16.py", line 94, in VGG16 include_top=include_top) TypeError: _obtain_input_shape() got...

how can use the attritute scores?

1

i use the mobilenetv2 fine tune aadb and get regression six class attritute scores and total scores . the result : `SROCC_v: 0.484 SROCC_v: 0.404 SROCC_v: 0.616 SROCC_v: 0.455 SROCC_v:...

how the caffeCustom use ?

1

can you add readme how to use the caffeCustom, the env require and step ? thanks

about attribute and content net ?

4

- in this picture , the (b)and(c)net are one of branch for(a); it is (b)and(c) net also input ranks pair of image? - another question is how the feature fusion...

我想学习一下，能写一下详细的使用方法吗？

Panoptic Segmentation for help !

1

thanks for you share; recently i am also interest in Panoptic Segmentation; now i also train [Mask R-CNN](https://arxiv.org/abs/1703.06870) and [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611v1) model for...

maybe overfitting?

1

- thanks for you code. now i am run the code . - but i fond maybe the model overfitting. ``` 2019-05-21 16:26:02.627367 Iter 5040: Training Loss = 0.0148, Accuracy...