kentaroy47 frcnn-from-scratch-with-keras issues

kentaroy47 / frcnn-from-scratch-with-keras

:collision:Faster R-CNN from scratch written with Keras

Apache License 2.0

168 stars 107 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Can't train RPN separately (train_rpn.py)

#108 mkvashennikov opened 1 year ago
0
SystemExit: 2

#107 Ayushithakre12 opened 2 years ago
0
AttributeError: module 'tensorflow' has no attribute 'ConfigProto', how can I fix it ?

#106 shirtenenbaum opened 2 years ago
1
Unable to reproduce performance with PASCALVOC2010 and backbone resnet

#105 FrancescoManigrass closed 3 years ago
0
Anchor box generation when calculating the rpn

#104 valentin-fngr opened 3 years ago
1
RPN is not producing bounding boxes that overlap the ground truth boxes. Check RPN settings or keep training.

#103 getabhishekified opened 3 years ago
0
Error during testing

#102 finleylee2507 closed 3 years ago
0
Problem with AttributeError: 'str' object has no attribute 'shape'

#101 saylideshmukh opened 3 years ago
2
Why is the epoch_length is choosen as 1000? when should we change this?

#100 sindhura234 opened 3 years ago
1
ModuleNotFoundError: No module named 'tensorflow.compat.v1'

#99 Tovion opened 3 years ago
1
Modify Network for Multi-task Learning

#98 zeroneptunes opened 3 years ago
0
Fit automated method instead of manually write it.

#97 thanoscs opened 4 years ago
0
Cross Validation

#96 linaemunsamy opened 4 years ago
1
How to plot feature maps from RPN model?

#95 ambigus9 opened 4 years ago
1
Write the values of the predicted bounding boxes in measure_map

#94 sivaramakrishnan-rajaraman opened 4 years ago
0
Keyerror using measure_map for custom data using the trained VGG16 model

#93 sivaramakrishnan-rajaraman opened 4 years ago
0
Attempting to fetch value instead of handling error Internal: no supported devices found for platform CUDA

#92 Shridharpawar77 opened 4 years ago
0
How to write the results from the test_frcnn to a CSV file?

#91 sivaramakrishnan-rajaraman closed 4 years ago
0
RPN weights are not saved

#90 sivaramakrishnan-rajaraman closed 4 years ago
2
classifier_layers not used in resnet.py

#89 YiJunLing closed 4 years ago
2
P_regr not used in test_frcnn

#88 TiasM opened 4 years ago
0
Mistake in Loss function! ("rpn_loss_cls" function in "losses.py")

#87 RohanUBagewadi opened 4 years ago
0
Mistake in positive anchor box calculation (calc_rpn in data_generator.py)

#86 RohanUBagewadi opened 4 years ago
1
Why 4.0 for std_scaling?

#85 dcb-framatome closed 4 years ago
1
data_gen_val didn't used in "train_frcnn.py"

#84 Jason-Lee0 closed 4 years ago
4
ResNet-50 architecture

#83 TiasM closed 4 years ago
0
how to change the receptive fields in faster rcnn?

#82 Qcatbot closed 4 years ago
1
Custom backbone

#81 Steffgroe closed 4 years ago
1
background class (bg) in faster rcnn

#80 Qcatbot closed 4 years ago
2
ValueError: Layer #314 (named "time_distributed_2"), weight <tf.Variable 'time_distributed_2/kernel:0' shape=(2048, 4096) dtype=float32_ref> has shape (2048, 4096), but the saved weight has shape (4096, 4096).

#79 Qcatbot opened 4 years ago
2
F1-score loss for RRN

#78 MjdMahasneh opened 4 years ago
0
Labeling images for HD5?

#77 Sequential-circuits opened 4 years ago
1
train_rpn.py resnet50 silently closed

#76 dsounded closed 3 years ago
4
Set Up Keras-FasterRCNN in local machine from scratch

#75 samrawitergrtr closed 4 years ago
9
Small object detection

#74 lorenzomare opened 4 years ago
0
TensorFlow 2 and current status

#73 haimat opened 4 years ago
4
RPN, Faster R-CNN training way & ResNet-50 Arch

#72 TiasM closed 4 years ago
2
measure_map.py

#71 adhityareski opened 4 years ago
2
CheckPoint option

#70 QuandoSJ opened 4 years ago
1
Exception: 'a' cannot be empty unless no samples are taken

#69 FBWseagate opened 4 years ago
5
Test with images of different size

#68 matheushent opened 4 years ago
2
Getting confidence score/distributions for all objects

#67 GMahdi closed 4 years ago
2
No detection in test_frcnn.py

#66 TaeheeJeong closed 4 years ago
1
Predicted bounding boxes always squared 16x16

#65 simoneriggi opened 4 years ago
0
timedistributed function

#64 TaeheeJeong opened 4 years ago
0
loss calculation

#63 TaeheeJeong closed 4 years ago
1
can you provide pre-trained model?

#62 TaeheeJeong closed 4 years ago
2
Strange behavior in "rpn_to_roi" function

#61 k1l1 opened 4 years ago
2
Hot to convert hdf5 to pb?

#60 TomasTrnkaPLC closed 4 years ago
3
Problem with AttributeError: 'NoneType' object has no attribute 'shape'

#59 TomasTrnkaPLC opened 4 years ago
4