sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning
Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
PythonMIT
Issues
- 3
Only the author mentions half the bleu-4 score
#198 opened by CallMeRabbit - 1
The code is wrong.....
#201 opened by Le-up - 1
Please help me with the error:RuntimeError: Expected target size [32, 9490], got [32, 51]
#195 opened by 2068439567 - 7
High loss and low bleu-4 for training
#192 opened by loserlulin9 - 1
I get this issues:Dimension out of range (expected to be in range of [-2, 1], but got 2)
#200 opened by Kevinskt - 1
- 5
I think this a bug. caption.py 140
#196 opened by tigerbrother222 - 5
caption.py:IndexError: tensors used as indices must be long, byte or bool tensors
#175 opened by AndreSun98 - 3
ValueError: too many values to unpack (expected 2)
#161 opened by sruthiiyer - 0
- 3
ValueError: max() arg is an empty sequence
#191 opened by loserlulin9 - 5
caption.py strange output
#149 opened by efacco - 0
In eval.py, it seems that for each image, the model has to recalculate 5 times, is it too inefficient?
#194 opened by fiora6 - 1
Example Notebook??
#193 opened by quaid281 - 3
Dataset not available
#190 opened by Leo-Thomas - 1
how to lable my own image data?
#154 opened by yjdqk - 2
about datasets
#167 opened by zms1304210716 - 0
- 3
Anyone , Please help to solve this error
#186 opened by MCA-eng - 2
bleu-4 does not increase
#184 opened by NguyenVietPhong - 1
Why does the DecoderWithAttention still need encoded captions in forwarding when validating
#150 opened by ssheroes - 3
why use LSTMCell not use LSTM directly
#181 opened by morestart - 2
Dimension error
#189 opened by yuhua666 - 3
- 0
eval.val is not working.
#188 opened by KillerGary - 0
If i want to use RL for this , how will i do ?
#187 opened by Chenxiaqule - 1
what is the pupose of these two lines in `create_input_files` function in "master/utils.py"?
#179 opened by naveen-marthala - 0
Code stopped @ train.py with this error,
#185 opened by MCA-eng - 0
Asking about List of Packages Version
#182 opened by supriamir - 0
Failed to create .hdf5 files
#183 opened by supriamir - 5
- 1
Expected output for running caption.py
#164 opened by lisaliu1997 - 0
Could I translate it?
#174 opened by ggoggori - 0
Same Captions generated
#173 opened by jainnipun11 - 6
eval.py script is not working
#157 opened by LealemTilahun - 1
ask for WORDMAP.json
#159 opened by zgfrcs - 1
ValueError: Index (1553) out of range (0-999)
#148 opened by chillaxkrish - 0
eval.py error!
#172 opened by jainnipun11 - 1
Indexerror from caption.py
#169 opened by tiva-OG - 0
Technical Quality of Image Unsatisfactory
#171 opened by antonie-z - 0
pretrain weight
#170 opened by AnPhamThien - 1
creat_input_files.py error
#168 opened by zms1304210716 - 1
Can't Reproduce Training
#165 opened by ryntwn88 - 0
- 0
error when i run creat_input_files.py
#160 opened by zxh19976666 - 0
- 0
prev_word_inds
#155 opened by CuongNN218 - 1
- 0
解決 RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #4 'other'
#152 opened by andy9420 - 0
Support for batch processing
#151 opened by Swapnillader21