{"id":54058,"date":"2019-12-17T00:00:00","date_gmt":"2019-12-16T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard"},"modified":"2020-02-18T14:02:02","modified_gmt":"2020-02-18T11:02:02","slug":"14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","title":{"rendered":"14 projekte open-source p\u00ebr t\u00eb avancuar aft\u00ebsit\u00eb n\u00eb Data Science (leht\u00eb, mesatar, e v\u00ebshtir\u00eb)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Data Science p\u00ebr fillestar\u00ebt<\/i><\/p>\n

1. Analiza e Ndjenjave (Analiza e ndjenjave p\u00ebrmes tekstit)<\/h3>\n

\n\"14
\n
\nShikoni implementimin e plot\u00eb t\u00eb projektit Data Science duke p\u00ebrdorur kodin burimor \u2014 Projekti i Analiz\u00ebs s\u00eb Ndjenjave n\u00eb R<\/a><\/noindex>.<\/p>\n

Analiza e Ndjenjave \u2014 \u00ebsht\u00eb analiza e fjal\u00ebve p\u00ebr t\u00eb p\u00ebrcaktuar ndjenjat dhe opinionet, t\u00eb cilat mund t\u00eb jen\u00eb pozitive apo negative. Ky \u00ebsht\u00eb nj\u00eb lloj klasifikimi, ku klasat mund t\u00eb jen\u00eb binare (pozitive dhe negative) ose shum\u00ebzore (t\u00eb lumtura, t\u00eb zem\u00ebruara, t\u00eb trishtura, t\u00eb \u00e7uditshme \u2026). Ne do ta implementojm\u00eb k\u00ebt\u00eb projekt t\u00eb Shkenc\u00ebs s\u00eb t\u00eb Dh\u00ebnave n\u00eb gjuh\u00ebn R dhe do t\u00eb p\u00ebrdorim nj\u00eb set t\u00eb dh\u00ebnash n\u00eb paket\u00ebn \"janeaustenR\". Ne do t\u00eb p\u00ebrdorim fjalor\u00eb t\u00eb p\u00ebrgjithsh\u00ebm, si AFINN, bing dhe loughran, do t\u00eb kryejm\u00eb nj\u00eb bashk\u00ebngjitje t\u00eb brendshme, dhe n\u00eb fund do t\u00eb krijojm\u00eb nj\u00eb re fjal\u00ebsh p\u00ebr t\u00eb paraqitur rezultatin.<\/p>\n

Gjuha:<\/b> R
\nSeti i t\u00eb dh\u00ebnave\/Paketa:<\/b> janeaustenR
\n<\/a><\/noindex><\/p>\n

\"14<\/a><\/noindex>

\nArtikulli \u00ebsht\u00eb p\u00ebrkthyer me mb\u00ebshtetje nga kompania EDISON Software, e cila krijon kabina virtuale p\u00ebr dyqanet me shum\u00eb marka<\/a><\/noindex>, si dhe teston softuerin<\/a><\/noindex>.<\/p><\/blockquote>\n

2. Zbulimi i Lajmeve t\u00eb Rreme (Detektimi i lajmeve t\u00eb rreme)<\/h3>\n

\nNgjitni aft\u00ebsit\u00eb tuaja n\u00eb nj\u00eb nivel t\u00eb ri duke punuar n\u00eb nj\u00eb projekt Data Science p\u00ebr fillestar\u00ebt \u2014 zbulimi i lajmeve t\u00eb rreme me Python<\/a><\/noindex>.<\/p>\n

\"14
\n
\nLajmet e rreme jan\u00eb informacion i rrem\u00eb q\u00eb shp\u00ebrndahet p\u00ebrmes mediave sociale dhe burimeve t\u00eb tjera t\u00eb njohura p\u00ebr p\u00ebrfitime politike. N\u00eb k\u00ebt\u00eb ide projekti p\u00ebr Data Science, ne do t\u00eb p\u00ebrdorim Python p\u00ebr t\u00eb nd\u00ebrtuar nj\u00eb model q\u00eb mund t\u00eb klasifikoj\u00eb sakt\u00ebsisht n\u00ebse nj\u00eb lajm \u00ebsht\u00eb i v\u00ebrtet\u00eb ose i rrem\u00eb. Ne do t\u00eb krijojm\u00eb TfidfVectorizer dhe do t\u00eb p\u00ebrdorim PassiveAggressiveClassifier p\u00ebr t\u00eb klasifikuar lajmet n\u00eb \u00abt\u00eb v\u00ebrteta\u00bb dhe \u00abt\u00eb rreme\u00bb. Ne do t\u00eb p\u00ebrdorim nj\u00eb set t\u00eb dh\u00ebnash me form\u00eb 7796 \u00d7 4 dhe do t\u00eb realizojm\u00eb gjith\u00e7ka n\u00eb Jupyter Lab.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> news.csv<\/p>\n

3. Zbulimi i S\u00ebmundjes s\u00eb Parkinsonit (Detektimi i s\u00ebmundjes s\u00eb Parkinsonit)<\/h3>\n

\nP\u00ebrparoni duke punuar n\u00eb iden\u00eb e projektit p\u00ebr Data Science \u2014 zbulimi i s\u00ebmundjes s\u00eb Parkinsonit me XGBoost<\/a><\/noindex>.<\/p>\n

\"14
\n
\nNe filluam t\u00eb p\u00ebrdorim Data Science p\u00ebr t\u00eb p\u00ebrmir\u00ebsuar sh\u00ebndetin dhe sh\u00ebrbimet \u2014 n\u00ebse mund t\u00eb parashikojm\u00eb s\u00ebmundjen n\u00eb faz\u00ebn fillestare, at\u00ebher\u00eb do t\u00eb kemi shum\u00eb p\u00ebrfitime. Pra, n\u00eb k\u00ebt\u00eb ide projekti p\u00ebr Data Science, ne do t\u00eb m\u00ebsojm\u00eb si t\u00eb zbulojm\u00eb s\u00ebmundjen e Parkinsonit me Python. Kjo \u00ebsht\u00eb nj\u00eb s\u00ebmundje neurodegjenerative dhe progresive e sistemit nervor qendror q\u00eb ndikon n\u00eb l\u00ebvizjen dhe shkakton dridhje dhe ngurt\u00ebsi. Ajo ndikon n\u00eb neuronet q\u00eb prodhojn\u00eb dopamin\u00eb n\u00eb trurin, dhe \u00e7do vit, prek m\u00eb shum\u00eb se 1 milion njer\u00ebz n\u00eb Indi.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> UCI ML Parkinsons dataset<\/p>\n

Projekte t\u00eb shkencave t\u00eb t\u00eb dh\u00ebnave me kompleksitet t\u00eb mes\u00ebm<\/i><\/p>\n

4. Njohja e Emoceve nga Z\u00ebri (Speech Emotion Recognition)<\/h3>\n

\nShihni implementimin e plot\u00eb t\u00eb projektit t\u00eb shkencave t\u00eb t\u00eb dh\u00ebnave \u2014 njohjen e z\u00ebrit me ndihm\u00ebn e Librosa<\/a><\/noindex>.<\/p>\n

\"14
\n
\nTani le t\u00eb m\u00ebsojm\u00eb si t\u00eb p\u00ebrdorim biblioteka t\u00eb ndryshme. Ky projekt n\u00eb shkencat e t\u00eb dh\u00ebnave p\u00ebrdor librosa p\u00ebr njohjen e z\u00ebrit. SER \u00ebsht\u00eb procesi i p\u00ebrcaktimit t\u00eb emocioneve dhe gjendjeve afektive t\u00eb njeriut p\u00ebrmes z\u00ebrit. Pasiq\u00eb ne p\u00ebrdorim tonin dhe lart\u00ebsin\u00eb e tonit p\u00ebr t\u00eb shprehur emocione me z\u00eb, SER \u00ebsht\u00eb i r\u00ebnd\u00ebsish\u00ebm. Por pasi q\u00eb emocionet jan\u00eb subjektive, annotimi i z\u00ebrit \u00ebsht\u00eb nj\u00eb detyr\u00eb e komplikuar. Ne do t\u00eb p\u00ebrdorim funksionet mfcc, chroma dhe mel dhe do t\u00eb p\u00ebrdorim setin e t\u00eb dh\u00ebnave RAVDESS p\u00ebr njohjen e emocioneve. Ne do t\u00eb krijojm\u00eb nj\u00eb klasifikues MLPC p\u00ebr k\u00ebt\u00eb model.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Seti i t\u00eb dh\u00ebnave RAVDESS<\/p>\n

5. Zbulimi i Gjenit dhe Mosh\u00ebs (Gender and Age Detection)<\/h3>\n

\nImpononi pun\u00ebdh\u00ebn\u00ebsit me projektin m\u00eb t\u00eb ri n\u00eb shkencat e t\u00eb dh\u00ebnave \u2014 zbulimi i gjenit dhe mosh\u00ebs me ndihm\u00ebn e OpenCV<\/a><\/noindex>.<\/p>\n

\"14
\n
\nKy \u00ebsht\u00eb nj\u00eb projekt interesante n\u00eb shkencat e t\u00eb dh\u00ebnave me Python. Duke p\u00ebrdorur vet\u00ebm nj\u00eb imazh, do t\u00eb m\u00ebsoni t\u00eb parashikoni gjenin dhe mosh\u00ebn e nj\u00eb personi. N\u00eb k\u00ebt\u00eb projekt, do t'ju njohim me vizionin kompjuterik (Computer Vision) dhe parimet e tij. Ne do t\u00eb nd\u00ebrtojm\u00eb rrjete neurale konvencionale<\/a><\/noindex> dhe do t\u00eb p\u00ebrdorim modelet e trenuara nga Tal Hassner dhe Gil Levi p\u00ebr setin e t\u00eb dh\u00ebnave Adience. Gjat\u00eb k\u00ebsaj rruge, do t\u00eb p\u00ebrdorim disa skedar\u00eb .pb, .pbtxt, .prototxt dhe .caffemodel.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Adience<\/p>\n

6. Analiza e t\u00eb Dh\u00ebnave t\u00eb Uber (Uber Data Analysis)<\/h3>\n

\nShihni implementimin e plot\u00eb t\u00eb projektit t\u00eb shkencave t\u00eb t\u00eb dh\u00ebnave me kod burimor \u2014 Projekti i Analiz\u00ebs s\u00eb t\u00eb Dh\u00ebnave t\u00eb Uber n\u00eb R<\/a><\/noindex>.<\/p>\n

\"14
\n
\nKy projekt \u00ebsht\u00eb nj\u00eb vizualizim t\u00eb dh\u00ebnash me ggplot2, ku ne do t\u00eb p\u00ebrdorim R dhe bibliotekat e tij p\u00ebr t\u00eb analizuar parametra t\u00eb ndrysh\u00ebm. Ne do t\u00eb p\u00ebrdorim setin e t\u00eb dh\u00ebnave Uber Pickups n\u00eb New York dhe do t\u00eb krijojm\u00eb vizualizime p\u00ebr kuadro t\u00eb ndryshme t\u00eb vitit. Kjo na tregon se si koha ndikon n\u00eb udh\u00ebtimet e klient\u00ebve.<\/p>\n

Gjuha:<\/b> R<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Seti i t\u00eb dh\u00ebnave Uber Pickups n\u00eb New York City<\/p>\n

7. Zbulimi i Gjumit te Shofer\u00ebve (Driver Drowsiness Detection)<\/h3>\n

\nP\u00ebrmir\u00ebsoni aft\u00ebsit\u00eb tuaja duke punuar n\u00eb projektin kryesor t\u00eb shkencave t\u00eb t\u00eb dh\u00ebnave \u2014 sistemi i zbulimit t\u00eb gjumit me OpenCV & Keras<\/a><\/noindex>.<\/p>\n

\"14
\n
\nGjumia gjat\u00eb drejtimit \u00ebsht\u00eb jasht\u00ebzakonisht e rrezikshme, dhe \u00e7do vit ndodhin rreth nj\u00eb mij\u00eb aksidente p\u00ebr shkak se shofer\u00ebt bien n\u00eb gjum\u00eb gjat\u00eb drejtimit. N\u00eb k\u00ebt\u00eb projekt me Python, ne do t\u00eb krijojm\u00eb nj\u00eb sistem q\u00eb do t\u00eb jet\u00eb n\u00eb gjendje t\u00eb zbuloj\u00eb shofer\u00ebt e gjumitur dhe t'i njoftoj\u00eb ata me nj\u00eb sinjal z\u00ebri.<\/p>\n

Ky ky projekt \u00ebsht\u00eb realizuar duke p\u00ebrdorur Keras dhe OpenCV. Ne do t\u00eb p\u00ebrdorim OpenCV p\u00ebr t\u00eb identifikuar fytyr\u00ebn dhe syt\u00eb, dhe me Keras do t\u00eb klasifikojm\u00eb gjendjen e syrit (T\u00eb Hapura ose T\u00eb Mbyllura) duke p\u00ebrdorur metoda t\u00eb rrjeteve neuronale t\u00eb thella.<\/p>\n

8. Chatbot<\/h3>\n

\nKrijoni nj\u00eb chatbot me Python dhe b\u00ebni nj\u00eb hap p\u00ebrpara n\u00eb karrier\u00ebn tuaj \u2014 Chatbot me NLTK & Keras<\/a><\/noindex>.<\/p>\n

\"14
\n
\nChatbot\u00ebt jan\u00eb nj\u00eb pjes\u00eb e pamundur e biznesit. Shum\u00eb biznese duhet t\u00eb ofrojn\u00eb sh\u00ebrbime p\u00ebr klient\u00ebt e tyre, dhe p\u00ebr t\u00eb mb\u00ebshtetur k\u00ebt\u00eb k\u00ebrkohet shum\u00eb forc\u00eb pune, koh\u00eb dhe p\u00ebrpjekje. Chatbot\u00ebt mund t\u00eb automatizojn\u00eb nj\u00eb pjes\u00eb t\u00eb madhe t\u00eb nd\u00ebrveprimit me klient\u00ebt, duke u p\u00ebrgjigjur disa pyetjeve t\u00eb shpeshta q\u00eb b\u00ebjn\u00eb klient\u00ebt. N\u00eb thelb ka dy lloje chatbot-\u00ebsh: Domain-specific dhe Open-domain. Chatbot\u00ebt Domain-specific p\u00ebrdoren shpesh p\u00ebr t\u00eb zgjidhur nj\u00eb problem specifik. Prandaj, ju duhet ta konfiguroni at\u00eb p\u00ebr t\u00eb punuar n\u00eb m\u00ebnyr\u00eb efektive n\u00eb fush\u00ebn tuaj. Chatbot\u00ebt Open-domain mund t\u2019u b\u00ebjn\u00eb \u00e7do lloj pyetje, prandaj p\u00ebr trajnimin e tyre k\u00ebrkohet nj\u00eb sasi e madhe t\u00eb dh\u00ebnash.<\/p>\n

Grupi i t\u00eb dh\u00ebnave:<\/b> Skedari intents json<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Projekte t\u00eb avancuara t\u00eb Shkenc\u00ebs s\u00eb t\u00eb Dh\u00ebnave<\/i><\/p>\n

9. Gjeneratori i p\u00ebrshkrimeve t\u00eb imazheve<\/h3>\n

\nKontrolloni realizimin e plot\u00eb t\u00eb projektit me kodin burimor \u2014 Gjeneratori i p\u00ebrshkrimeve t\u00eb imazheve me CNN & LSTM<\/a><\/noindex>.<\/p>\n

\"14
\n
\nP\u00ebrshkrimi i asaj q\u00eb ndodhet n\u00eb nj\u00eb imazh \u00ebsht\u00eb nj\u00eb detyr\u00eb e leht\u00eb p\u00ebr njer\u00ebzit, por p\u00ebr kompjuter\u00ebt, imazhi \u00ebsht\u00eb thjesht nj\u00eb grup numrash q\u00eb p\u00ebrfaq\u00ebsojn\u00eb vler\u00ebn e ngjyr\u00ebs p\u00ebr secilin piksel. Kjo \u00ebsht\u00eb nj\u00eb detyr\u00eb e v\u00ebshtir\u00eb p\u00ebr kompjuter\u00ebt. T\u00eb kuptosh se \u00e7far\u00eb ndodhet n\u00eb nj\u00eb imazh dhe m\u00eb pas t\u00eb krijosh nj\u00eb p\u00ebrshkrim n\u00eb nj\u00eb gjuh\u00eb natyrore (p\u00ebr shembull, n\u00eb anglisht) \u00ebsht\u00eb nj\u00eb tjet\u00ebr detyr\u00eb e v\u00ebshtir\u00eb. Ky projekt p\u00ebrdor metoda t\u00eb m\u00ebsimit t\u00eb thell\u00eb, ku ne zbatojm\u00eb nj\u00eb Rr\u00ebke Neurale Konvolucionale (CNN) me nj\u00eb Rr\u00ebke Neurale Recurrente (LSTM) p\u00ebr t\u00eb krijuar nj\u00eb gjenerator p\u00ebrshkrimesh p\u00ebr imazhe.<\/p>\n

Grupi i t\u00eb dh\u00ebnave:<\/b> Flickr 8K<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Framework:<\/b> Keras<\/p>\n

10. Identifikimi i Mashtrimit me Kartat e Kreditit<\/h3>\n

\nB\u00ebni gjith\u00e7ka q\u00eb \u00ebsht\u00eb e mundur duke punuar mbi iden\u00eb e projektit t\u00eb Shkenc\u00ebs s\u00eb t\u00eb Dh\u00ebnave \u2014 identifikimi i mashtrimit me kartat e kreditit duke p\u00ebrdorur m\u00ebsimin e makinerive<\/a><\/noindex>.<\/p>\n

\"14
\n
\nDerisa t\u00eb arritni tani, ju keni filluar t\u00eb kuptoni metodat dhe konceptet. Le t\u00eb kalojm\u00eb n\u00eb disa projekte t\u00eb avancuara n\u00eb shkenc\u00ebn e t\u00eb dh\u00ebnave. N\u00eb k\u00ebt\u00eb projekt, ne do t\u00eb p\u00ebrdorim gjuh\u00ebn R me algoritma t\u00eb till\u00eb si pem\u00ebt e vendimeve<\/a><\/noindex>, regresioni logjistik, rrjetet neurale artificiale dhe klasifikuesi i fuqis\u00eb gradienti. Ne do t\u00eb p\u00ebrdorim nj\u00eb grup t\u00eb dh\u00ebnash p\u00ebr transaksionet me karta, p\u00ebr t\u00eb klasifikuar transaksionet e kartave t\u00eb kreditit si mashtruese dhe t\u00eb v\u00ebrteta. Ne do t'i p\u00ebrshtatim atyre modele t\u00eb ndryshme dhe do t\u00eb ndjekim kurbat e performanc\u00ebs.<\/p>\n

Gjuha:<\/b> R<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Grupi i t\u00eb dh\u00ebnave p\u00ebr Transaksionet me Karta<\/p>\n

11. Sistemi i Rekomandimeve p\u00ebr Filma<\/h3>\n

\nStudio realizimin e projektit m\u00eb t\u00eb mir\u00eb t\u00eb Data Science me Kodin Burimor \u2014 Sistemi i Rekomandimeve p\u00ebr Filma n\u00eb gjuh\u00ebn R<\/a><\/noindex><\/p>\n

\"14
\n
\nN\u00eb k\u00ebt\u00eb projekt t\u00eb Data Science, ne do t\u00eb p\u00ebrdorim R p\u00ebr t\u00eb ofruar rekomandime filmash p\u00ebrmes m\u00ebsimit t\u00eb makinerive. Sistemi i rekomandimeve d\u00ebrgon sugjerime p\u00ebrdoruesve p\u00ebrmes nj\u00eb procesi filtrimi, t\u00eb bazuar n\u00eb preferencat e p\u00ebrdoruesve t\u00eb tjer\u00eb dhe historin\u00eb e shikimeve. N\u00ebse A dhe B i p\u00eblqen Home Alone, dhe B e do Mean Girls, at\u00ebher\u00eb mund t'i sugjerohet A \u2014 ata gjithashtu mund t'i p\u00eblqejn\u00eb. Kjo lejon klient\u00ebt t\u00eb interaktin me platform\u00ebn.<\/p>\n

Gjuha:<\/b> R<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Grupi i t\u00eb dh\u00ebnave t\u00eb MovieLens<\/p>\n

12. Segmentimi i Klient\u00ebve<\/h3>\n

\nB\u00ebni nj\u00eb p\u00ebrshtypje tek pun\u00ebdh\u00ebn\u00ebsit me projektin e Data Science (duke p\u00ebrfshir\u00eb kodin burimor) \u2014 Segmentimi i Klient\u00ebve p\u00ebrmes M\u00ebsimit t\u00eb Makinerive<\/a><\/noindex>.<\/p>\n

\"14
\n
\nSegmentimi i klient\u00ebve \u00ebsht\u00eb nj\u00eb aplikacion popullor i m\u00ebsimit t\u00eb pa mbik\u00ebqyrur.<\/a><\/noindex>Duke p\u00ebrdorur klasterizimin, kompanit\u00eb p\u00ebrcaktojn\u00eb segmente klient\u00ebsh p\u00ebr t\u00eb punuar me baz\u00ebn e potenciale t\u00eb p\u00ebrdoruesve. Ato ndajn\u00eb klient\u00ebt n\u00eb grupe sipas karakteristikave t\u00eb zakonshme, si gjinia, mosha, interesat dhe zakonet e shpenzimit, n\u00eb m\u00ebnyr\u00eb q\u00eb t\u00eb mund t\u00eb shesin produktet e tyre me efikasitet p\u00ebr \u00e7do grup. Ne do t\u00eb p\u00ebrdorim klasterizimin K-means<\/a><\/noindex>, si dhe do t\u00eb vizualizojm\u00eb shp\u00ebrndarjen sipas gjinive dhe mosh\u00ebs. M\u00eb pas do t\u00eb analizojm\u00eb t\u00eb ardhurat vjetore dhe nivelin e shpenzimeve t\u00eb tyre.<\/p>\n

Gjuha:<\/b> R<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> Grupi i t\u00eb dh\u00ebnave t\u00eb Mall_Customers<\/p>\n

13. Klasifikimi i Kancerit t\u00eb Gjirit<\/h3>\n

\nShikoni realizimin e plot\u00eb t\u00eb projektit t\u00eb Data Science n\u00eb Python \u2014 Klasifikimi i Kancerit t\u00eb Gjirit p\u00ebrmes M\u00ebsimit t\u00eb Thell\u00eb<\/a><\/noindex>.<\/p>\n

\"14
\n
\nDuke u kthyer n\u00eb kontributin mjek\u00ebsor t\u00eb shkencave t\u00eb dh\u00ebnave, le t\u00eb m\u00ebsojm\u00eb t\u00eb identifikojm\u00eb kancerin e gjirit me ndihm\u00ebn e Python. Ne do t\u00eb p\u00ebrdorim setin e t\u00eb dh\u00ebnave IDC_regular p\u00ebr t\u00eb identifikuar karcinom\u00ebn invazive t\u00eb kanaleve, form\u00ebn m\u00eb t\u00eb zakonshme t\u00eb kancerit t\u00eb gjirit. Ai zhvillohet n\u00eb kanalet e gjirit, duke u p\u00ebrhapur n\u00eb indin fibror ose yndyror t\u00eb gjirit p\u00ebrtej kanalit. N\u00eb k\u00ebt\u00eb ide t\u00eb projektit shkencor p\u00ebr mbledhjen e t\u00eb dh\u00ebnave do t\u00eb p\u00ebrdorim M\u00ebsimi i thell\u00eb<\/a><\/noindex> dhe bibliotek\u00ebn Keras p\u00ebr klasifikim.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Seti i t\u00eb dh\u00ebnave\/Paketa:<\/b> IDC_regular<\/p>\n

14. Njohja e Shenjave Trafiku<\/h3>\n

\nArritja e sakt\u00ebsis\u00eb n\u00eb teknologjin\u00eb e vet\u00eb-ndihm\u00ebs p\u00ebr vozitjen e automjeteve p\u00ebrmes nj\u00eb projekti Shkenc\u00eb t\u00eb Dh\u00ebnash p\u00ebr njohjen e shenjave t\u00eb trafikut duke p\u00ebrdorur CNN<\/a><\/noindex> me burim t\u00eb hapur.<\/p>\n

\"14
\n
\nShenjat e trafikut dhe rregullat e qarkullimit jan\u00eb shum\u00eb t\u00eb r\u00ebnd\u00ebsishme p\u00ebr \u00e7do vozit\u00ebs p\u00ebr t\u00eb shmangur aksidentet. P\u00ebr t\u00eb ndjekur rregullin, fillimisht duhet t\u00eb kuptohet se si duket nj\u00eb shenj\u00eb trafiku. Njer\u00ebzit duhet t\u00eb m\u00ebsojn\u00eb t\u00eb gjitha shenjat e trafikut p\u00ebrpara se t'u jepet leja p\u00ebr t\u00eb drejtuar ndonj\u00eb mjet. Por tani numri i automjeteve autonome po rritet, dhe n\u00eb t\u00eb ardhmen e af\u00ebrt njer\u00ebzit ndoshta nuk do t\u00eb drejtojn\u00eb makin\u00ebn m\u00eb vet\u00eb. N\u00eb projektin \u201cNjohja e Shenjave Trafikut\u201d do t\u00eb m\u00ebsoni si nj\u00eb program mund t\u00eb identifikoj\u00eb llojin e shenjave t\u00eb trafikut duke pranuar nj\u00eb imazh si hyrje. Seti i t\u00eb dh\u00ebnave p\u00ebr njohjen e shenjave t\u00eb trafikut n\u00eb Gjermani (GTSRB) p\u00ebrdoret p\u00ebr t\u00eb nd\u00ebrtuar nj\u00eb rrjet t\u00eb thell\u00eb nervor p\u00ebr t\u00eb njohur klas\u00ebn e shenj\u00ebs s\u00eb trafikut. Ne gjithashtu krijojm\u00eb nj\u00eb nd\u00ebrfaqe grafike t\u00eb thjesht\u00eb p\u00ebr nd\u00ebrveprimin me aplikacionin.<\/p>\n

Gjuha:<\/b> Python<\/p>\n

Grupi i t\u00eb dh\u00ebnave:<\/b> GTSRB (Benchmark p\u00ebr Njohjen e Shenjave t\u00eb Trafikut n\u00eb Gjermani)<\/p>\n

Lexo m\u00eb shum\u00eb<\/h3>\n

<\/p>\n