CRNN-Keras

CRNN-Keras copied to clipboard

K.set_learning_phase(0)

2

Hi, I don't get it why in training.py there's a line 7, which forces the learning_phase to 0 (=test)? `K.set_learning_phase(0)` As far as I know for example BatchNormalization() layer behaves...

soldierofhell

Hi I want to calculate the accuracy of the model during training, what do I do ? in the `model.compile,` there is a metrics option that can be `'accuracy'`, but...

DeeeepNet

increase input size of Network

2

Hi, Is it possible to increase the input size of network from 128x64 to 256x128 ?

ghost

Hi, @qjadud1994 Q1- what's downsample_factor? if i increase the input_size of network time 2, that's 256*128, is necessary to change this parameter? and also be difference length input sequence of...

ghost

frozenbeanxxx

Hi, thanks for your code above all. And I am using the repo as an initial stage of a wild filed OCR task for unfixing length sequence. How can I...

LinanYaooo

Hey, budy, Why did you slice the y_pred[:,2:,:] in the ctc_lambda_func?

1

https://github.com/qjadud1994/CRNN-Keras/blob/d8e2f552cd5260d590a3a9a6c202d1079833e26e/Model.py#L16 The original paper seems not to have this slicing trick.

HandsomeBrotherShuaiLi

image resize issue in training.py

1

**img = cv2.resize(img,(self.img_w, self.img_h),None) cv2.error: OpenCV(3.4.4) /io/opencv/modules/imgproc/src/resize.cpp:3784: error: (-215:Assertion failed) !ssize.empty() in function 'resize'** I keep getting the above error inspite of resizing my images to 128x64 and I am...

tykell

CNN - other architectures and transfer learning

2

Has anyone tried to replace default simple CNN structure with pretrained architectures like VGG, InceptionV3, etc.? On one hand the typical text image (like plates) is different in nature than...

soldierofhell

very bad result in the real-plate images

3

Hi, I've trained the VGG-GRU network for around 700k artificially generated images, and i got 96% accuracy for test data (about 140k generated image), but when i test the trained...

ghost