Hello!
Recently, I have finished some experiments, the refG's overIoU of test(u) is lower than the VLT in our experiments, but I find the overIoU of test(u) is much higher than other algorithms. Thus, I have tried to run your code. Unfortunately, the code gave an error, and no workaround was found. The reproduction process is as follows :
step1:
git clone https://github.com/henghuiding/Vision-Language-Transformer
step 2:
conda create -n vlt python=3.6
conda activate vlt
pip install -r requirement.txt
step 3:
python vlt.py test pretrain/config.yaml
Errors:
File "vlt.py", line 57, in
tester = Tester(config, GPUS=GPU_COUNTS, debug=args.debug)
File "/home/users3/workspace/Vision-Language-Transformer/executor.py", line 184, in init
super(Tester, self).init(config, **kwargs)
File "/home/users3/workspace/Vision-Language-Transformer/executor.py", line 39, in init
self.yolo_model, self.yolo_body, self.yolo_body_single = self.create_model()
File "/home/users3/workspace/Vision-Language-Transformer/executor.py", line 54, in create_model
model_body = yolo_body(image_input, q_input, self.config)
File "/home/users3/workspace/Vision-Language-Transformer/model/vlt_model.py", line 162, in yolo_body
mask_out = make_multitask_braches(Fv, fq, fq_word, config)
File "/home/users3/workspace/Vision-Language-Transformer/model/vlt_model.py", line 79, in make_multitask_braches
mask_out = vlt_transformer(F_tf, fq_word, query_out, config)
File "/home/users3/workspace/Vision-Language-Transformer/model/vlt_model.py", line 100, in vlt_transformer
head_num=config.transformer_head_num)
File "/home/users3/workspace/Vision-Language-Transformer/model/transfromer_model.py", line 79, in lang_tf_enc
)(lang_input)
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 881, in call
inputs, outputs, args, kwargs)
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2043, in set_connectivity_metadata
input_tensors=inputs, output_tensors=outputs, arguments=arguments)
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2059, in _add_inbound_node
input_tensors)
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/util/nest.py", line 536, in map_structure
structure[0], [func(*x) for x in entries],
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/util/nest.py", line 536, in
structure[0], [func(*x) for x in entries],
File "/home/users3/anaconda3/envs/vlt/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2058, in
inbound_layers = nest.map_structure(lambda t: t._keras_history.layer,
AttributeError: 'tuple' object has no attribute 'layer'
If it is convenient, I would be grateful if you could provide the logs of your code running and testing on refG, or more detailed environment configuration, thanks.
Hello,
How are you going? I saw in Step 2 that your Python version is 3.6. So your reproduction is based entirely on the version in the requirement.txt? Not the latest version, like TensorFlow 2.13.0 and so on. Because I continually met some problems due to the version differences. And some of them I can't find a solution, so I'm thinking to create an exact virtual environment as the repository. Even it's better to use the latest version...
Thank you in advance.
@Shuaicong24, we do the environment configuration exactly as requirement.txt. Now, we found the problem stems from the Keras package and Keras module of TensorFlow. The original code used a mix of them, resulting in API obfuscation. If you want to succeed, one of them must be replaced by another.
henghuiding
