DeepHash

DeepHash copied to clipboard

ValueError: Cannot feed value of shape (128, 0) for Tensor Placeholder_1:0, which has shape (?, 10)

1

When i try to train dch with train_val_script.py and its default args i get the following error: Traceback (most recent call last): File "train_val_script.py", line 61, in model_weights = model.train(train_img,...

nikkon3

AttributeError: module 'tensorflow' has no attribute 'placeholder_with_default'

2

Hello,there was a issue when I tried running the example. DTQ: > Traceback (most recent call last): > File "train_val_script.py", line 74, in > model_weights = model.train(train_img, database_img, query_img, args)...

a0wsxz9

DCH: low results

3

I trained DCH on COCO using the default parameters in val_train script, which sets the iter_num to 2000. The results too low compared to the paper: iter 33 prec 0.3673785145624646...

hbellafkir

Hi! I'm looking to do inference only, and not retrain. Would anybody be willing to share their model parameters that was trained on ImageNet or similar full size images (COCO,...

exnx

It seems that in all your models such as dch.py, dhn.py, you first load model and pretrained model weights and then run global initializer, ``` self.img_last_layer, self.deep_param_img, self.train_layers, self.train_last_layer =...

wanginwang

When we realize the DHN model, we encountered a problem. The three files in the directory “DeepHash/data/cifar10” only have the location of the picture, and the actual label of the...

milkboylyf

Seems it couldn't work with the latest tf2.0

ghost

Hi, I trained the model DHN using the default hyperparameters. However, I got a different result. The map is 0.9, precision is 0.9, recall is 0.001. It is quite strange....

zhangleai

Hello,I want to know if you use other training data sets, I should how to construct data set, I don't understand the dataset. TXT file: image path and name +...

Lisachinasd

Lisachinasd