ValueError: a must be non-empty

[bzburr]

823/1000 [=======================>......] - ETA: 3:08 - rpn_cls: 2.9711 - rpn_regr: 0.0832 - detector_cls: 0.3042 - detector_regr: 0.1486Traceback (most recent call last):
File "train_frcnn.py", line 261, in
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
File "mtrand.pyx", line 1126, in mtrand.RandomState.choice
ValueError: a must be non-empty

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train_frcnn.py", line 263, in
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()
File "mtrand.pyx", line 1126, in mtrand.RandomState.choice
ValueError: a must be non-empty

[kkawtar]

did you found a solution for that ?

[hodaatef]

any one solved this error please???

[attilab97]

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.

[gdut3118007086]

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

[gdut3118007086]

(any one solved this error please???)

[AdamJochna]

    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:

[AdamJochna]

that seems to solve this issue

[Try2ChangeX]

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