tempdeltavalue

Also faced with this issue function start_model() { // const modelJson = require('https://tempdeltavalue.github.io/model.json'); // const modelWeights = require('https://tempdeltavalue.github.io/group1-shard1of1.bin'); model = tf.loadGraphModel('https://tempdeltavalue.github.io/f_w2223_js_graph/model.json'); states =[]; next_char = ['Пр '] result = [next_char]...

I'm experience this error , also ..  Here's my colab https://colab.research.google.com/drive/1zuwxvP-FZ4wRmaVqs-Wb7ODhP3FiPGWi?usp=sharing weights you can download here if you want https://drive.google.com/drive/folders/1D1x5T_2z6KQezQXiAizjWSylPcrINixh?usp=sharing fyi https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/UnicodeDecode

note about this example https://github.com/tensorflow/tfjs-examples/tree/master/lstm-text-generation Here's no explanation how to convert model from Keras to tfjs :( and it's pretty difficult to find example of that ..

one more thing , you can comment this line input_chars = tf.strings.unicode_split(inputs, 'UTF-8') (and change your code accordingly and you will be able to convert the model)

In my case problem was in inputs.shape[-1].value inside _inverted_res_block , so I just removed ".value" and everything worked (maybe for now :) ).

also issue on win10 (also I didn't figure out how to launch this into vs (I tried to create project with existed code to generate sln files, no 3dforest.exe file))...

some values inside of your tensors maybe lower than zero I'm also getting strange mask shape in my case is 1x1x1x1 @neophack Did you manage to run the decoder in...

@Gretanheee you can inherit SamPredictor from nn.Module and move "get embeddings functions" into forward function , but I'm not sure what everything will work correctly

I'm installed cuda 10.1 and torch==1.8.1+cu101 torchvision==0.9.1+cu101 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html and I get same issue as above but in this case is related to vs , probably Microsoft Visual Studio/2019/Community/VC/Tools/MSVC/14.29.30133/include\yvals_core.h(565):...

@ZhouHaonanShens I didn't solve it, I just find other example of ngp on PyTorch 🙂