ValueError: a must be non-empty about keras-fasterrcnn HOT 8 OPEN

did you found a solution for that ?

from keras-fasterrcnn.

any one solved this error please???

from keras-fasterrcnn.

if len(neg_samples) != 0:
try:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
except:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()
Just put a test before selecting negative samples.

from keras-fasterrcnn.

if len(neg_samples) != 0:
try:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
except:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()
Just put a test before selecting negative samples.

after that i meet another question

File "train_frcnn.py", line 275, in
loss_class = model_classifier.train_on_batch([X, X2[:, sel_samples, :]], [Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
IndexError: index 4 is out of bounds for axis 1 with size 1

from keras-fasterrcnn.

(any one solved this error please???)

from keras-fasterrcnn.

    if C.num_rois > 1:
        if len(pos_samples) < C.num_rois//2:
            selected_pos_samples = pos_samples.tolist()
        else:
            if len(pos_samples) > 0:
                selected_pos_samples = np.random.choice(pos_samples, C.num_rois//2, replace=False).tolist()
            else:
                selected_pos_samples = []
        try:
            if len(neg_samples) > 0:
                selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
            else:
                selected_neg_samples = []
        except:
            if len(neg_samples) > 0:
                selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()
            else:
                selected_neg_samples = []

        sel_samples = selected_pos_samples + selected_neg_samples
    else:

from keras-fasterrcnn.

that seems to solve this issue

from keras-fasterrcnn.

I also met this problem. Anyone solve that? Help...

from keras-fasterrcnn.