Saleem Ahmed

What is the default value used for the tokenizer-merges-file ? Do you use the default merges_gpt2.txt or the custom digits removed file merges_gpt2_single_digit_numbers.txt My understanding is that the file merges.txt...

Transpose layer breaks caffe installation

1

Hi, Please advice : ``` PROTOC src/caffe/proto/caffe.proto CXX src/caffe/solvers/sgd_solver.cpp CXX src/caffe/solvers/nesterov_solver.cpp CXX src/caffe/solvers/rmsprop_solver.cpp CXX src/caffe/solvers/adadelta_solver.cpp CXX src/caffe/solvers/adam_solver.cpp CXX src/caffe/parallel.cpp CXX src/caffe/solvers/adagrad_solver.cpp CXX src/caffe/internal_thread.cpp CXX src/caffe/solver.cpp CXX src/caffe/layers/accuracy_layer.cpp CXX src/caffe/layers/recurrent_layer.cpp CXX...

Synthtext pre processing and table 2 accuracies

2

Hi, Please can you tell the steps taken for pre-procesing synthtext labels ?? your model uses fixed max length of 25 but synthtext dataset has boxes with labels length(number of...

Train branch

5

Hi, What is the status of the train branch ? I'd be down for contributing if you wish ?

'GlobalStorage' object has no attribute 'face'

1

Context : ``` (pop) sahmed9@alice:~/reps/deep-graph-matching-consensus/examples$ CUDA_VISIBLE_DEVICES=3 python pascal.py Processing... Done! Traceback (most recent call last): File "/home/sahmed9/anaconda3/envs/pop/lib/python3.8/site-packages/torch_geometric/data/storage.py", line 48, in __getattr__ return self[key] File "/home/sahmed9/anaconda3/envs/pop/lib/python3.8/site-packages/torch_geometric/data/storage.py", line 68, in __getitem__ return...

Is it possible for the author to provide a clean code base, there is a lot of garbage in the current repository from previous implements of corner-net lite and then...

While training Full traceback ``` Traceback (most recent call last): File "train_chart.py", line 265, in train(training_dbs, validation_db, args.start_iter) File "train_chart.py", line 181, in train training, ind = sample_data(training_dbs[0], ind) File...

what is "lighting" transformation

1

How were the hard coded values below calculated : db> coco.py> Line> init() ``` self._eig_val = np.array([0.2141788, 0.01817699, 0.00341571], dtype=np.float32) self._eig_vec = np.array([ [-0.58752847, -0.69563484, 0.41340352], [-0.5832747, 0.00994535, -0.81221408], [-0.56089297,...

Recreate numbers in table 2

3

Hi, is there an evaluation script to re-create numbers of table 2 from paper. The test_pipe_type_cloud.py only gives json as output. Where are the eval metrics ?

Hi, Thank you for making a public codebase. Please point to the implementation of the query network described in Section 3.3.3 of the paper.