Problem that can not display image to be tested with Deep learning model YOLOv4

Hi

I have a problem that i can not display an image on a notebook when I tested with deep learning model YOLOv4

Herein the code and error

!./darknet detector test data/ceng.data cfg/yolov4-custom.cfg backup/yolov4-custom_5000.weights -dont_show test.jpg

CUDA-version: 10010 (10010), cuDNN: 7.6.5, GPU count: 1
OpenCV version: 3.2.0
0 : compute_capability = 750, cudnn_half = 0, GPU: Tesla T4
net.optimized_memory = 0
mini_batch = 1, batch = 64, time_steps = 1, train = 0
layer filters size/strd(dil) input output
0 conv 32 3 x 3/ 1 320 x 320 x 3 -> 320 x 320 x 32 0.177 BF
1 conv 64 3 x 3/ 2 320 x 320 x 32 -> 160 x 160 x 64 0.944 BF
2 conv 64 1 x 1/ 1 160 x 160 x 64 -> 160 x 160 x 64 0.210 BF
3 route 1 -> 160 x 160 x 64
4 conv 64 1 x 1/ 1 160 x 160 x 64 -> 160 x 160 x 64 0.210 BF
5 conv 32 1 x 1/ 1 160 x 160 x 64 -> 160 x 160 x 32 0.105 BF
6 conv 64 3 x 3/ 1 160 x 160 x 32 -> 160 x 160 x 64 0.944 BF
7 Shortcut Layer: 4, wt = 0, wn = 0, outputs: 160 x 160 x 64 0.002 BF
8 conv 64 1 x 1/ 1 160 x 160 x 64 -> 160 x 160 x 64 0.210 BF
9 route 8 2 -> 160 x 160 x 128
10 conv 64 1 x 1/ 1 160 x 160 x 128 -> 160 x 160 x 64 0.419 BF
11 conv 128 3 x 3/ 2 160 x 160 x 64 -> 80 x 80 x 128 0.944 BF
12 conv 64 1 x 1/ 1 80 x 80 x 128 -> 80 x 80 x 64 0.105 BF
13 route 11 -> 80 x 80 x 128
14 conv 64 1 x 1/ 1 80 x 80 x 128 -> 80 x 80 x 64 0.105 BF
15 conv 64 1 x 1/ 1 80 x 80 x 64 -> 80 x 80 x 64 0.052 BF
16 conv 64 3 x 3/ 1 80 x 80 x 64 -> 80 x 80 x 64 0.472 BF
17 Shortcut Layer: 14, wt = 0, wn = 0, outputs: 80 x 80 x 64 0.000 BF
18 conv 64 1 x 1/ 1 80 x 80 x 64 -> 80 x 80 x 64 0.052 BF
19 conv 64 3 x 3/ 1 80 x 80 x 64 -> 80 x 80 x 64 0.472 BF
20 Shortcut Layer: 17, wt = 0, wn = 0, outputs: 80 x 80 x 64 0.000 BF
21 conv 64 1 x 1/ 1 80 x 80 x 64 -> 80 x 80 x 64 0.052 BF
22 route 21 12 -> 80 x 80 x 128
23 conv 128 1 x 1/ 1 80 x 80 x 128 -> 80 x 80 x 128 0.210 BF
24 conv 256 3 x 3/ 2 80 x 80 x 128 -> 40 x 40 x 256 0.944 BF
25 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
26 route 24 -> 40 x 40 x 256
27 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
28 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
29 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
30 Shortcut Layer: 27, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
31 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
32 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
33 Shortcut Layer: 30, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
34 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
35 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
36 Shortcut Layer: 33, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
37 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
38 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
39 Shortcut Layer: 36, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
40 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
41 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
42 Shortcut Layer: 39, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
43 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
44 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
45 Shortcut Layer: 42, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
46 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
47 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
48 Shortcut Layer: 45, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
49 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
50 conv 128 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.472 BF
51 Shortcut Layer: 48, wt = 0, wn = 0, outputs: 40 x 40 x 128 0.000 BF
52 conv 128 1 x 1/ 1 40 x 40 x 128 -> 40 x 40 x 128 0.052 BF
53 route 52 25 -> 40 x 40 x 256
54 conv 256 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 256 0.210 BF
55 conv 512 3 x 3/ 2 40 x 40 x 256 -> 20 x 20 x 512 0.944 BF
56 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
57 route 55 -> 20 x 20 x 512
58 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
59 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
60 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
61 Shortcut Layer: 58, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
62 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
63 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
64 Shortcut Layer: 61, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
65 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
66 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
67 Shortcut Layer: 64, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
68 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
69 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
70 Shortcut Layer: 67, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
71 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
72 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
73 Shortcut Layer: 70, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
74 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
75 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
76 Shortcut Layer: 73, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
77 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
78 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
79 Shortcut Layer: 76, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
80 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
81 conv 256 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.472 BF
82 Shortcut Layer: 79, wt = 0, wn = 0, outputs: 20 x 20 x 256 0.000 BF
83 conv 256 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 256 0.052 BF
84 route 83 56 -> 20 x 20 x 512
85 conv 512 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 512 0.210 BF
86 conv 1024 3 x 3/ 2 20 x 20 x 512 -> 10 x 10 x1024 0.944 BF
87 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
88 route 86 -> 10 x 10 x1024
89 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
90 conv 512 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.052 BF
91 conv 512 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.472 BF
92 Shortcut Layer: 89, wt = 0, wn = 0, outputs: 10 x 10 x 512 0.000 BF
93 conv 512 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.052 BF
94 conv 512 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.472 BF
95 Shortcut Layer: 92, wt = 0, wn = 0, outputs: 10 x 10 x 512 0.000 BF
96 conv 512 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.052 BF
97 conv 512 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.472 BF
98 Shortcut Layer: 95, wt = 0, wn = 0, outputs: 10 x 10 x 512 0.000 BF
99 conv 512 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.052 BF
100 conv 512 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.472 BF
101 Shortcut Layer: 98, wt = 0, wn = 0, outputs: 10 x 10 x 512 0.000 BF
102 conv 512 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.052 BF
103 route 102 87 -> 10 x 10 x1024
104 conv 1024 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x1024 0.210 BF
105 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
106 conv 1024 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x1024 0.944 BF
107 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
108 max 5x 5/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.001 BF
109 route 107 -> 10 x 10 x 512
110 max 9x 9/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.004 BF
111 route 107 -> 10 x 10 x 512
112 max 13x13/ 1 10 x 10 x 512 -> 10 x 10 x 512 0.009 BF
113 route 112 110 108 107 -> 10 x 10 x2048
114 conv 512 1 x 1/ 1 10 x 10 x2048 -> 10 x 10 x 512 0.210 BF
115 conv 1024 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x1024 0.944 BF
116 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
117 conv 256 1 x 1/ 1 10 x 10 x 512 -> 10 x 10 x 256 0.026 BF
118 upsample 2x 10 x 10 x 256 -> 20 x 20 x 256
119 route 85 -> 20 x 20 x 512
120 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
121 route 120 118 -> 20 x 20 x 512
122 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
123 conv 512 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 512 0.944 BF
124 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
125 conv 512 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 512 0.944 BF
126 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
127 conv 128 1 x 1/ 1 20 x 20 x 256 -> 20 x 20 x 128 0.026 BF
128 upsample 2x 20 x 20 x 128 -> 40 x 40 x 128
129 route 54 -> 40 x 40 x 256
130 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
131 route 130 128 -> 40 x 40 x 256
132 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
133 conv 256 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 256 0.944 BF
134 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
135 conv 256 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 256 0.944 BF
136 conv 128 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 128 0.105 BF
137 conv 256 3 x 3/ 1 40 x 40 x 128 -> 40 x 40 x 256 0.944 BF
138 conv 30 1 x 1/ 1 40 x 40 x 256 -> 40 x 40 x 30 0.025 BF
139 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.20
nms_kind: greedynms (1), beta = 0.600000
140 route 136 -> 40 x 40 x 128
141 conv 256 3 x 3/ 2 40 x 40 x 128 -> 20 x 20 x 256 0.236 BF
142 route 141 126 -> 20 x 20 x 512
143 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
144 conv 512 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 512 0.944 BF
145 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
146 conv 512 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 512 0.944 BF
147 conv 256 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 256 0.105 BF
148 conv 512 3 x 3/ 1 20 x 20 x 256 -> 20 x 20 x 512 0.944 BF
149 conv 30 1 x 1/ 1 20 x 20 x 512 -> 20 x 20 x 30 0.012 BF
150 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.10
nms_kind: greedynms (1), beta = 0.600000
151 route 147 -> 20 x 20 x 256
152 conv 512 3 x 3/ 2 20 x 20 x 256 -> 10 x 10 x 512 0.236 BF
153 route 152 116 -> 10 x 10 x1024
154 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
155 conv 1024 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x1024 0.944 BF
156 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
157 conv 1024 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x1024 0.944 BF
158 conv 512 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 512 0.105 BF
159 conv 1024 3 x 3/ 1 10 x 10 x 512 -> 10 x 10 x1024 0.944 BF
160 conv 30 1 x 1/ 1 10 x 10 x1024 -> 10 x 10 x 30 0.006 BF
161 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000
Total BFLOPS 35.262
avg_outputs = 290120
Allocate additional workspace_size = 52.43 MB
Loading weights from backup/yolov4-custom_5000.weights…
seen 64, trained: 320 K-images (5 Kilo-batches_64)
Done! Loaded 162 layers from weights-file
Detection layer: 139 - type = 28
Detection layer: 150 - type = 28
Detection layer: 161 - type = 28
test.jpg: Predicted in 32.533000 milli-seconds.
car: 98%
car: 90%
car: 46%
car: 74%

import cv2

cv2_imshow(test.jpg)

Error


AttributeError Traceback (most recent call last)

in () ----> 1 cv2_imshow(test.jpg)

AttributeError: ‘PytestTester’ object has no attribute ‘jpg’

This isn’t a Jupyter issue. Looks to be just basic Python syntax, although maybe in pasting things some of the context got lost? (Note, to avoid that possibility in the future when you ask questions in appropriate locations you could take the notebook, edited down to the few cells you want to share, and post it as a gist at https://gist.github.com and share a link to it rendered via https://nbviewer.jupyter.org/ along with the basics of your question.)
Did you try putting quotes around the file name, i.e., cv2_imshow("test.jpg")? Plus, I take it you are on Google Colab and imported cv2_imshow correctly (see here)?

1 Like