ryankiros/visual-semantic-embedding
Implementation of the image-sentence embedding method described in "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"
PythonNOASSERTION
Issues
- 0
- 0
dataset page is not available
#14 opened by chagmgang - 3
TypeError: ('An update must have the same type as the original shared variable (shared_var=<TensorType(float32, matrix)>, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')
#13 opened by chandanmishra-03 - 2
run train.py
#9 opened by chirstinaFan - 3
- 0
Failed to train
#11 opened by cdluminate - 1
Bow model encodes sentence with an extra word
#4 opened by xthan - 0
cost is NaN
#10 opened by chirstinaFan - 0
- 0
The output of the encoder?
#7 opened by irfanICMLL - 0
- 1
No such file or directory: '/ais/gobi3/u/rkiros/uvsmodels/coco.npz.dictionary.pkl'
#5 opened by Tracy2014